From be6ed5c52a4f34631dc9266165be613971a37cfc Mon Sep 17 00:00:00 2001 From: Nirmayi Date: Mon, 1 Jul 2024 14:47:52 +0200 Subject: [PATCH 1/2] update spatial decomposition results to v2 --- .../data/dataset_info.json | 207 +- .../data/method_info.json | 370 +- .../data/metric_execution_info.json | 1640 ++++++ .../data/metric_info.json | 25 +- .../data/quality_control.json | 554 +- .../spatial_decomposition/data/results.json | 4853 +++++++++-------- results/spatial_decomposition/data/state.yaml | 9 + .../spatial_decomposition/data/task_info.json | 14 +- 8 files changed, 4819 insertions(+), 2853 deletions(-) create mode 100644 results/spatial_decomposition/data/metric_execution_info.json create mode 100644 results/spatial_decomposition/data/state.yaml diff --git a/results/spatial_decomposition/data/dataset_info.json b/results/spatial_decomposition/data/dataset_info.json index ae46c1833..113a646cb 100644 --- a/results/spatial_decomposition/data/dataset_info.json +++ b/results/spatial_decomposition/data/dataset_info.json @@ -1,86 +1,123 @@ [ - { - "dataset_name": "DestVI", - "image": "openproblems-python-pytorch", - "data_url": "https://github.com/romain-lopez/DestVI-reproducibility/blob/master/simulations/make_dataset.py", - "data_reference": "lopez2022destvi", - "dataset_summary": "scRNA-seq is generated based on learn NB parameters from the destVI manuscripts leveraging sparsePCA. Number of cells and cell types present in each spatial spot is computed via combination of kernel-based parametrization of a categorical distribution and the NB model.", - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "dataset_id": "destvi", - "source_dataset_id": "openproblems_v1/destvi", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/destvi/generate.py" - }, - { - "dataset_name": "Pancreas (alpha=0.5)", - "image": "openproblems", - "data_url": "https://ndownloader.figshare.com/files/36086813", - "data_reference": "luecken2022benchmarking", - "dataset_summary": "Human pancreas cells aggregated from single-cell (Dirichlet alpha=0.5)", - "task_id": "spatial_decomposition", - "commit_sha": "c2470ce02e6f196267cec1c554ba7ae389c0956a", - "dataset_id": "pancreas_alpha_0_5", - "source_dataset_id": "openproblems_v1/pancreas", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/pancreas.py" - }, - { - "dataset_name": "Pancreas (alpha=1)", - "image": "openproblems", - "data_url": "https://ndownloader.figshare.com/files/36086813", - "data_reference": "luecken2022benchmarking", - "dataset_summary": "Human pancreas cells aggregated from single-cell (Dirichlet alpha=1)", - "task_id": "spatial_decomposition", - "commit_sha": "c2470ce02e6f196267cec1c554ba7ae389c0956a", - "dataset_id": "pancreas_alpha_1", - "source_dataset_id": "openproblems_v1/pancreas", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/pancreas.py" - }, - { - "dataset_name": "Pancreas (alpha=5)", - "image": "openproblems", - "data_url": "https://ndownloader.figshare.com/files/36086813", - "data_reference": "luecken2022benchmarking", - "dataset_summary": "Human pancreas cells aggregated from single-cell (Dirichlet alpha=5)", - "task_id": "spatial_decomposition", - "commit_sha": "c2470ce02e6f196267cec1c554ba7ae389c0956a", - "dataset_id": "pancreas_alpha_5", - "source_dataset_id": "openproblems_v1/pancreas", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/pancreas.py" - }, - { - "dataset_name": "Tabula muris senis (alpha=0.5)", - "image": "openproblems", - "data_url": "https://tabula-muris-senis.ds.czbiohub.org/", - "data_reference": "tabula2020single", - "dataset_summary": "Mouse lung cells aggregated from single-cell (Dirichlet alpha=0.5)", - "task_id": "spatial_decomposition", - "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "source_dataset_id": "openproblems_v1/tabula_muris_senis_droplet_lung", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/tabula_muris_senis.py" - }, - { - "dataset_name": "Tabula muris senis (alpha=1)", - "image": "openproblems", - "data_url": "https://tabula-muris-senis.ds.czbiohub.org/", - "data_reference": "tabula2020single", - "dataset_summary": "Mouse lung cells aggregated from single-cell (Dirichlet alpha=1)", - "task_id": "spatial_decomposition", - "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887", - "dataset_id": "tabula_muris_senis_alpha_1", - "source_dataset_id": "openproblems_v1/tabula_muris_senis_droplet_lung", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/tabula_muris_senis.py" - }, - { - "dataset_name": "Tabula muris senis (alpha=5)", - "image": "openproblems", - "data_url": "https://tabula-muris-senis.ds.czbiohub.org/", - "data_reference": "tabula2020single", - "dataset_summary": "Mouse lung cells aggregated from single-cell (Dirichlet alpha=5)", - "task_id": "spatial_decomposition", - "commit_sha": "9d1665076cf6215a31f89ed2be8be20a02502887", - "dataset_id": "tabula_muris_senis_alpha_5", - "source_dataset_id": "openproblems_v1/tabula_muris_senis_droplet_lung", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/datasets/tabula_muris_senis.py" - } -] \ No newline at end of file + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/gtex_v9", + "dataset_name": "GTEX v9", + "dataset_summary": "Single-nucleus cross-tissue molecular reference maps to decipher disease gene function", + "dataset_description": "Understanding the function of genes and their regulation in tissue homeostasis and disease requires knowing the cellular context in which genes are expressed in tissues across the body. Single cell genomics allows the generation of detailed cellular atlases in human tissues, but most efforts are focused on single tissue types. Here, we establish a framework for profiling multiple tissues across the human body at single-cell resolution using single nucleus RNA-Seq (snRNA-seq), and apply it to 8 diverse, archived, frozen tissue types (three donors per tissue). We apply four snRNA-seq methods to each of 25 samples from 16 donors, generating a cross-tissue atlas of 209,126 nuclei profiles, and benchmark them vs. scRNA-seq of comparable fresh tissues. We use a conditional variational autoencoder (cVAE) to integrate an atlas across tissues, donors, and laboratory methods. We highlight shared and tissue-specific features of tissue-resident immune cells, identifying tissue-restricted and non-restricted resident myeloid populations. These include a cross-tissue conserved dichotomy between LYVE1- and HLA class II-expressing macrophages, and the broad presence of LAM-like macrophages across healthy tissues that is also observed in disease. For rare, monogenic muscle diseases, we identify cell types that likely underlie the neuromuscular, metabolic, and immune components of these diseases, and biological processes involved in their pathology. For common complex diseases and traits analyzed by GWAS, we identify the cell types and gene modules that potentially underlie disease mechanisms. The experimental and analytical frameworks we describe will enable the generation of large-scale studies of how cellular and molecular processes vary across individuals and populations.", + "data_reference": "eraslan2022singlenucleus", + "data_url": "https://cellxgene.cziscience.com/collections/a3ffde6c-7ad2-498a-903c-d58e732f7470", + "date_created": "28-06-2024", + "file_size": 3003208 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/dkd", + "dataset_name": "Diabetic Kidney Disease", + "dataset_summary": "Multimodal single cell sequencing implicates chromatin accessibility and genetic background in diabetic kidney disease progression", + "dataset_description": "Multimodal single cell sequencing is a powerful tool for interrogating cell-specific changes in transcription and chromatin accessibility. We performed single nucleus RNA (snRNA-seq) and assay for transposase accessible chromatin sequencing (snATAC-seq) on human kidney cortex from donors with and without diabetic kidney disease (DKD) to identify altered signaling pathways and transcription factors associated with DKD. Both snRNA-seq and snATAC-seq had an increased proportion of VCAM1+ injured proximal tubule cells (PT_VCAM1) in DKD samples. PT_VCAM1 has a pro-inflammatory expression signature and transcription factor motif enrichment implicated NFkB signaling. We used stratified linkage disequilibrium score regression to partition heritability of kidney-function-related traits using publicly-available GWAS summary statistics. Cell-specific PT_VCAM1 peaks were enriched for heritability of chronic kidney disease (CKD), suggesting that genetic background may regulate chromatin accessibility and DKD progression. snATAC-seq found cell-specific differentially accessible regions (DAR) throughout the nephron that change accessibility in DKD and these regions were enriched for glucocorticoid receptor (GR) motifs. Changes in chromatin accessibility were associated with decreased expression of insulin receptor, increased gluconeogenesis, and decreased expression of the GR cytosolic chaperone, FKBP5, in the diabetic proximal tubule. Cleavage under targets and release using nuclease (CUT&RUN) profiling of GR binding in bulk kidney cortex and an in vitro model of the proximal tubule (RPTEC) showed that DAR co-localize with GR binding sites. CRISPRi silencing of GR response elements (GRE) in the FKBP5 gene body reduced FKBP5 expression in RPTEC, suggesting that reduced FKBP5 chromatin accessibility in DKD may alter cellular response to GR. We developed an open-source tool for single cell allele specific analysis (SALSA) to model the effect of genetic background on gene expression. Heterozygous germline single nucleotide variants (SNV) in proximal tubule ATAC peaks were associated with allele-specific chromatin accessibility and differential expression of target genes within cis-coaccessibility networks. Partitioned heritability of proximal tubule ATAC peaks with a predicted allele-specific effect was enriched for eGFR, suggesting that genetic background may modify DKD progression in a cell-specific manner.", + "data_reference": "wilson2022multimodal", + "data_url": "https://cellxgene.cziscience.com/collections/b3e2c6e3-9b05-4da9-8f42-da38a664b45b", + "date_created": "28-06-2024", + "file_size": 2766040 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "openproblems_v1/immune_cells", + "dataset_name": "Human immune", + "dataset_summary": "Human immune cells dataset from the scIB benchmarks", + "dataset_description": "Human immune cells from peripheral blood and bone marrow taken from 5 datasets comprising 10 batches across technologies (10X, Smart-seq2).", + "data_reference": "luecken2022benchmarking", + "data_url": "https://theislab.github.io/scib-reproducibility/dataset_immune_cell_hum.html", + "date_created": "28-06-2024", + "file_size": 1398520 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/hcla", + "dataset_name": "Human Lung Cell Atlas", + "dataset_summary": "An integrated cell atlas of the human lung in health and disease (core)", + "dataset_description": "The integrated Human Lung Cell Atlas (HLCA) represents the first large-scale, integrated single-cell reference atlas of the human lung. It consists of over 2 million cells from the respiratory tract of 486 individuals, and includes 49 different datasets. It is split into the HLCA core, and the extended or full HLCA. The HLCA core includes data of healthy lung tissue from 107 individuals, and includes manual cell type annotations based on consensus across 6 independent experts, as well as demographic, biological and technical metadata.", + "data_reference": "sikkema2023integrated", + "data_url": "https://cellxgene.cziscience.com/collections/6f6d381a-7701-4781-935c-db10d30de293", + "date_created": "28-06-2024", + "file_size": 2463000 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "openproblems_v1/pancreas", + "dataset_name": "Human pancreas", + "dataset_summary": "Human pancreas cells dataset from the scIB benchmarks", + "dataset_description": "Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq).", + "data_reference": "luecken2022benchmarking", + "data_url": "https://theislab.github.io/scib-reproducibility/dataset_pancreas.html", + "date_created": "28-06-2024", + "file_size": 1962344 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "dataset_name": "Mouse Pancreatic Islet Atlas", + "dataset_summary": "Mouse pancreatic islet scRNA-seq atlas across sexes, ages, and stress conditions including diabetes", + "dataset_description": "To better understand pancreatic β-cell heterogeneity we generated a mouse pancreatic islet atlas capturing a wide range of biological conditions. The atlas contains scRNA-seq datasets of over 300,000 mouse pancreatic islet cells, of which more than 100,000 are β-cells, from nine datasets with 56 samples, including two previously unpublished datasets. The samples vary in sex, age (ranging from embryonic to aged), chemical stress, and disease status (including T1D NOD model development and two T2D models, mSTZ and db/db) together with different diabetes treatments. Additional information about data fields is available in anndata uns field 'field_descriptions' and on https://github.com/theislab/mm_pancreas_atlas_rep/blob/main/resources/cellxgene.md.", + "data_reference": "hrovatin2023delineating", + "data_url": "https://cellxgene.cziscience.com/collections/296237e2-393d-4e31-b590-b03f74ac5070", + "date_created": "28-06-2024", + "file_size": 2262488 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/hypomap", + "dataset_name": "HypoMap", + "dataset_summary": "A unified single cell gene expression atlas of the murine hypothalamus", + "dataset_description": "The hypothalamus plays a key role in coordinating fundamental body functions. Despite recent progress in single-cell technologies, a unified catalogue and molecular characterization of the heterogeneous cell types and, specifically, neuronal subtypes in this brain region are still lacking. Here we present an integrated reference atlas “HypoMap” of the murine hypothalamus consisting of 384,925 cells, with the ability to incorporate new additional experiments. We validate HypoMap by comparing data collected from SmartSeq2 and bulk RNA sequencing of selected neuronal cell types with different degrees of cellular heterogeneity.", + "data_reference": "steuernagel2022hypomap", + "data_url": "https://cellxgene.cziscience.com/collections/d86517f0-fa7e-4266-b82e-a521350d6d36", + "date_created": "28-06-2024", + "file_size": 3652072 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "openproblems_v1/cengen", + "dataset_name": "CeNGEN", + "dataset_summary": "Complete Gene Expression Map of an Entire Nervous System", + "dataset_description": "100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics.", + "data_reference": "hammarlund2018cengen", + "data_url": "https://www.cengen.org", + "date_created": "28-06-2024", + "file_size": 1944360 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/immune_cell_atlas", + "dataset_name": "Immune Cell Atlas", + "dataset_summary": "Cross-tissue immune cell analysis reveals tissue-specific features in humans", + "dataset_description": "Despite their crucial role in health and disease, our knowledge of immune cells within human tissues remains limited. We surveyed the immune compartment of 16 tissues from 12 adult donors by single-cell RNA sequencing and VDJ sequencing generating a dataset of ~360,000 cells. To systematically resolve immune cell heterogeneity across tissues, we developed CellTypist, a machine learning tool for rapid and precise cell type annotation. Using this approach, combined with detailed curation, we determined the tissue distribution of finely phenotyped immune cell types, revealing hitherto unappreciated tissue-specific features and clonal architecture of T and B cells. Our multitissue approach lays the foundation for identifying highly resolved immune cell types by leveraging a common reference dataset, tissue-integrated expression analysis, and antigen receptor sequencing.", + "data_reference": "dominguez2022crosstissue", + "data_url": "https://cellxgene.cziscience.com/collections/62ef75e4-cbea-454e-a0ce-998ec40223d3", + "date_created": "28-06-2024", + "file_size": 2506312 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "openproblems_v1/zebrafish", + "dataset_name": "Zebrafish embryonic cells", + "dataset_summary": "Single-cell mRNA sequencing of zebrafish embryonic cells.", + "dataset_description": "90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene.", + "data_reference": "wagner2018single", + "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112294", + "date_created": "28-06-2024", + "file_size": 2553912 + }, + { + "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/tabula_sapiens", + "dataset_name": "Tabula Sapiens", + "dataset_summary": "A multiple-organ, single-cell transcriptomic atlas of humans", + "dataset_description": "Tabula Sapiens is a benchmark, first-draft human cell atlas of nearly 500,000 cells from 24 organs of 15 normal human subjects. This work is the product of the Tabula Sapiens Consortium. Taking the organs from the same individual controls for genetic background, age, environment, and epigenetic effects and allows detailed analysis and comparison of cell types that are shared between tissues. Our work creates a detailed portrait of cell types as well as their distribution and variation in gene expression across tissues and within the endothelial, epithelial, stromal and immune compartments.", + "data_reference": "consortium2022tabula", + "data_url": "https://cellxgene.cziscience.com/collections/e5f58829-1a66-40b5-a624-9046778e74f5", + "date_created": "28-06-2024", + "file_size": 3719656 + } +] diff --git a/results/spatial_decomposition/data/method_info.json b/results/spatial_decomposition/data/method_info.json index a2c3f402f..edcbf5af4 100644 --- a/results/spatial_decomposition/data/method_info.json +++ b/results/spatial_decomposition/data/method_info.json @@ -1,227 +1,145 @@ [ - { - "method_name": "Cell2location (alpha=20, amortised, hard-coded)", - "method_summary": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. Note that since batch information is unavailable in this task, here we use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.", - "paper_name": "Cell2location maps fine-grained cell types in spatial transcriptomics", - "paper_reference": "kleshchevnikov2022cell2location", - "paper_year": 2022, - "code_url": "https://github.com/BayraktarLab/cell2location", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "154ccb9fd99113f3d28d9c3f139194539a0290f9", - "method_id": "cell2location_amortised_detection_alpha_20", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/cell2location.py" - }, - { - "method_name": "Cell2location (alpha=1, reference hard-coded)", - "method_summary": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. Note that since batch information is unavailable in this task, here we use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.", - "paper_name": "Cell2location maps fine-grained cell types in spatial transcriptomics", - "paper_reference": "kleshchevnikov2022cell2location", - "paper_year": 2022, - "code_url": "https://github.com/BayraktarLab/cell2location", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "154ccb9fd99113f3d28d9c3f139194539a0290f9", - "method_id": "cell2location_detection_alpha_1", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/cell2location.py" - }, - { - "method_name": "Cell2location (alpha=20, reference hard-coded)", - "method_summary": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. Note that since batch information is unavailable in this task, here we use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.", - "paper_name": "Cell2location maps fine-grained cell types in spatial transcriptomics", - "paper_reference": "kleshchevnikov2022cell2location", - "paper_year": 2022, - "code_url": "https://github.com/BayraktarLab/cell2location", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "154ccb9fd99113f3d28d9c3f139194539a0290f9", - "method_id": "cell2location_detection_alpha_20", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/cell2location.py" - }, - { - "method_name": "Cell2location (alpha=200, reference hard-coded)", - "method_summary": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. Note that since batch information is unavailable in this task, here we use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.", - "paper_name": "Cell2location maps fine-grained cell types in spatial transcriptomics", - "paper_reference": "kleshchevnikov2022cell2location", - "paper_year": 2022, - "code_url": "https://github.com/BayraktarLab/cell2location", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "154ccb9fd99113f3d28d9c3f139194539a0290f9", - "method_id": "cell2location_detection_alpha_200", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/cell2location.py" - }, - { - "method_name": "Cell2location (alpha=20, NB reference)", - "method_summary": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. Note that since batch information is unavailable in this task, here we use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.", - "paper_name": "Cell2location maps fine-grained cell types in spatial transcriptomics", - "paper_reference": "kleshchevnikov2022cell2location", - "paper_year": 2022, - "code_url": "https://github.com/BayraktarLab/cell2location", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "154ccb9fd99113f3d28d9c3f139194539a0290f9", - "method_id": "cell2location_detection_alpha_20_nb", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/cell2location.py" - }, - { - "method_name": "DestVI", - "method_summary": "destVI is a decomposition method that leverages a conditional generative model of spatial transcriptomics down to the sub-cell-type variation level, which is then used to decompose the cell-type proportions determining the spatial organization of a tissue.", - "paper_name": "DestVI identifies continuums of cell types in spatial transcriptomics data", - "paper_reference": "lopez2022destvi", - "paper_year": 2022, - "code_url": "https://github.com/YosefLab/scvi-tools", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "destvi", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/destvi.py" - }, - { - "method_name": "Non-Negative Matrix Factorization (NMF)", - "method_summary": "NMF is a decomposition method based on Non-negative Matrix Factorization (NMF) that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It is a simpler baseline than NMFreg as it only performs the NMF step based on mean expression signatures of cell types, returning the weights loading of the NMF as (normalized) cell type proportions, without the regression step.", - "paper_name": "Fast local algorithms for large scale nonnegative matrix and tensor factorizations", - "paper_reference": "cichocki2009fast", - "paper_year": 2009, - "code_url": "https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.NMF.html", - "image": "openproblems", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "nmf", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/vanillanmf.py" - }, - { - "method_name": "NMF-reg", - "method_summary": "NMFreg is a decomposition method based on Non-negative Matrix Factorization Regression (NMFreg) that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It was originally developed for Slide-seq data.", - "paper_name": "Slide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution", - "paper_reference": "rodriques2019slide", - "paper_year": 2019, - "code_url": "https://github.com/tudaga/NMFreg_tutorial", - "image": "openproblems", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "nmfreg", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/nmfreg.py" - }, - { - "method_name": "Non-Negative Least Squares", - "method_summary": "NNLS13 is a decomposition method based on Non-Negative Least Square Regression (NNLS). It was originally introduced by the method AutoGenes", - "paper_name": "AutoGeneS: Automatic gene selection using multi-objective optimization for RNA-seq deconvolution", - "paper_reference": "aliee2021autogenes", - "paper_year": 2021, - "code_url": "https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.nnls.html", - "image": "openproblems", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "nnls_scipy", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/nnls.py" - }, - { - "method_name": "Random Proportions", - "method_summary": "Random assignment of predicted celltype proportions from a Dirichlet distribution.", - "paper_name": "Open Problems for Single Cell Analysis", - "paper_reference": "openproblems", - "paper_year": 2022, - "code_url": "https://github.com/openproblems-bio/openproblems", - "image": "openproblems", - "is_baseline": true, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "random_proportions", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/baseline.py" - }, - { - "method_name": "RCTD", - "method_summary": "RCTD (Robust Cell Type Decomposition) is a decomposition method that uses signatures learnt from single-cell data to decompose spatial expression of tissues. It is able to platform effect normalization step, which normalizes the scRNA-seq cell type profiles to match the platform effects of the spatial transcriptomics dataset.", - "paper_name": "Robust decomposition of cell type mixtures in spatial transcriptomics", - "paper_reference": "cable2021robust", - "paper_year": 2020, - "code_url": "https://github.com/dmcable/spacexr", - "image": "openproblems-r-extras", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "rctd", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/rctd.py" - }, - { - "method_name": "SeuratV3", - "method_summary": "SeuratV3 is a decomposition method that is based on Canonical Correlation Analysis (CCA).", - "paper_name": "Comprehensive Integration of Single-Cell Data", - "paper_reference": "stuart2019comprehensive", - "paper_year": 2019, - "code_url": "https://satijalab.org/seurat/archive/v3.2/spatial_vignette.html", - "image": "openproblems-r-extras", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "seuratv3", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/seuratv3.py" - }, - { - "method_name": "Stereoscope", - "method_summary": "Stereoscope is a decomposition method based on Negative Binomial regression. It is similar in scope and implementation to cell2location but less flexible to incorporate additional covariates such as batch effects and other type of experimental design annotations.", - "paper_name": "Single-cell and spatial transcriptomics enables probabilistic inference of cell type topography", - "paper_reference": "andersson2020single", - "paper_year": 2020, - "code_url": "https://github.com/scverse/scvi-tools", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "stereoscope", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/stereoscope.py" - }, - { - "method_name": "Tangram", - "method_summary": "Tangram is a method to map gene expression signatures from scRNA-seq data to spatial data. It performs the cell type mapping by learning a similarity matrix between single-cell and spatial locations based on gene expression profiles.", - "paper_name": "Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram", - "paper_reference": "biancalani2021deep", - "paper_year": 2021, - "code_url": "https://github.com/broadinstitute/Tangram", - "image": "openproblems-python-pytorch", - "is_baseline": false, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "tangram", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/tangram.py" - }, - { - "method_name": "True Proportions", - "method_summary": "Perfect assignment of predicted celltype proportions from the ground truth.", - "paper_name": "Open Problems for Single Cell Analysis", - "paper_reference": "openproblems", - "paper_year": 2022, - "code_url": "https://github.com/openproblems-bio/openproblems", - "image": "openproblems", - "is_baseline": true, - "code_version": null, - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "method_id": "true_proportions", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/methods/baseline.py" - } -] \ No newline at end of file + { + "task_id": "spatial_decomposition", + "method_id": "random_proportions", + "method_name": "Random Proportions", + "method_summary": "Negative control method that randomly assigns celltype proportions from a Dirichlet distribution.", + "method_description": "A negative control method with random assignment of predicted celltype proportions from a Dirichlet distribution.\n", + "is_baseline": true, + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/control_methods/random_proportions/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "true_proportions", + "method_name": "True Proportions", + "method_summary": "Positive control method that assigns celltype proportions from the ground truth.", + "method_description": "A positive control method with perfect assignment of predicted celltype proportions from the ground truth.\n", + "is_baseline": true, + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/control_methods/true_proportions/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "cell2location", + "method_name": "Cell2Location", + "method_summary": "Cell2location uses a Bayesian model to resolve cell types in spatial transcriptomic data and create comprehensive cellular maps of diverse tissues.", + "method_description": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. \nNote that when batch information is unavailable for this task, we can use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.\n", + "is_baseline": false, + "paper_reference": "kleshchevnikov2022cell2location", + "code_url": "https://github.com/BayraktarLab/cell2location", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/cell2location/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "destvi", + "method_name": "DestVI", + "method_summary": "DestVI is a probabilistic method for multi-resolution analysis for spatial transcriptomics that explicitly models continuous variation within cell types", + "method_description": "Deconvolution of Spatial Transcriptomics profiles using Variational Inference (DestVI) is a spatial decomposition method that leverages a conditional generative model of spatial transcriptomics down to the sub-cell-type variation level, which is then used to decompose the cell-type proportions determining the spatial organization of a tissue.\n", + "is_baseline": false, + "paper_reference": "lopez2022destvi", + "code_url": "https://github.com/scverse/scvi-tools", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/destvi/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "nmfreg", + "method_name": "NMFreg", + "method_summary": "NMFreg reconstructs gene expression as a weighted combination of cell type signatures defined by scRNA-seq.", + "method_description": "Non-Negative Matrix Factorization regression (NMFreg) is a decomposition method that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It was originally developed for Slide-seq data. This is a re-implementation from https://github.com/tudaga/NMFreg_tutorial.\n", + "is_baseline": false, + "paper_reference": "rodriques2019slide", + "code_url": "https://github.com/tudaga/NMFreg_tutorial/tree/master?tab=readme-ov-file", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/nmfreg/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "nnls", + "method_name": "NNLS", + "method_summary": "NNLS is a decomposition method based on Non-Negative Least Square Regression.", + "method_description": "NonNegative Least Squares (NNLS), is a convex optimization problem with convex constraints. It was used by the AutoGeneS method to infer cellular proporrtions by solvong a multi-objective optimization problem.\n", + "is_baseline": false, + "paper_reference": "aliee2021autogenes", + "code_url": "https://github.com/scipy/scipy", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/nnls/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "rctd", + "method_name": "RCTD", + "method_summary": "RCTD learns cell type profiles from scRNA-seq to decompose cell type mixtures while correcting for differences across sequencing technologies.", + "method_description": "RCTD (Robust Cell Type Decomposition) is a decomposition method that uses signatures learnt from single-cell data to decompose spatial expression of tissues. It is able to use a platform effect normalization step, which normalizes the scRNA-seq cell type profiles to match the platform effects of the spatial transcriptomics dataset.\n", + "is_baseline": false, + "paper_reference": "cable2021robust", + "code_url": "https://github.com/dmcable/spacexr", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/rctd/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "seurat", + "method_name": "Seurat", + "method_summary": "Seurat method that is based on Canonical Correlation Analysis (CCA).", + "method_description": "This method applies the 'anchor'-based integration workflow introduced in Seurat v3, that enables the probabilistic transfer of annotations from a reference to a query set. First, mutual nearest neighbors (anchors) are identified from the reference scRNA-seq and query spatial datasets. Then, annotations are transfered from the single cell reference data to the sptial data along with prediction scores for each spot.\n", + "is_baseline": false, + "paper_reference": "stuart2019comprehensive", + "code_url": "https://github.com/satijalab/seurat", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/seurat/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "stereoscope", + "method_name": "Stereoscope", + "method_summary": "Stereoscope is a decomposition method based on Negative Binomial regression.", + "method_description": "Stereoscope is a decomposition method based on Negative Binomial regression. It is similar in scope and implementation to cell2location but less flexible to incorporate additional covariates such as batch effects and other type of experimental design annotations.\n", + "is_baseline": false, + "paper_reference": "andersson2020single", + "code_url": "https://github.com/scverse/scvi-tools", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/stereoscope/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "tangram", + "method_name": "Tangram", + "method_summary": "Tanagram maps single-cell gene expression data onto spatial gene expression data by fitting gene expression on shared genes", + "method_description": "Tangram is a method to map gene expression signatures from scRNA-seq data to spatial data. It performs the cell type mapping by learning a similarity matrix between single-cell and spatial locations based on gene expression profiles.\n", + "is_baseline": false, + "paper_reference": "biancalani2021deep", + "code_url": "https://github.com/broadinstitute/Tangram", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/tangram/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + }, + { + "task_id": "spatial_decomposition", + "method_id": "vanillanmf", + "method_name": "NMF", + "method_summary": "NMF reconstructs gene expression as a weighted combination of cell type signatures defined by scRNA-seq.", + "method_description": "NMF is a decomposition method based on Non-negative Matrix Factorization (NMF) that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It is a simpler baseline than NMFreg as it only performs the NMF step based on mean expression signatures of cell types, returning the weights loading of the NMF as (normalized) cell type proportions, without the regression step.\n", + "is_baseline": false, + "paper_reference": "cichocki2009fast", + "code_url": "https://github.com/scikit-learn/scikit-learn/blob/92c9b1866/sklearn/decomposition/", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/vanillanmf/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + } +] diff --git a/results/spatial_decomposition/data/metric_execution_info.json b/results/spatial_decomposition/data/metric_execution_info.json new file mode 100644 index 000000000..79ba11489 --- /dev/null +++ b/results/spatial_decomposition/data/metric_execution_info.json @@ -0,0 +1,1640 @@ +[ + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 459.5, + "peak_memory_mb": 3482, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.8, + "cpu_pct": 279.6, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 250.6, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 207, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 337.7, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 306, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 322, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 4, + "cpu_pct": 326.1, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 321.1, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.2, + "cpu_pct": 171.6, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/dkd", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 306.2, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 333, + "peak_memory_mb": 3482, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 82, + "cpu_pct": 16.7, + "peak_memory_mb": 5530, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 384.3, + "peak_memory_mb": 2765, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 395.5, + "peak_memory_mb": 3584, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 327.3, + "peak_memory_mb": 3482, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.9, + "cpu_pct": 291.2, + "peak_memory_mb": 2868, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.2, + "cpu_pct": 355, + "peak_memory_mb": 2868, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 302.3, + "peak_memory_mb": 2868, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 6.6, + "cpu_pct": 169.5, + "peak_memory_mb": 5632, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 336, + "peak_memory_mb": 3482, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 330.9, + "peak_memory_mb": 3482, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.1, + "cpu_pct": 428.7, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 297.7, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.3, + "cpu_pct": 174.4, + "peak_memory_mb": 5632, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 328.4, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 232.3, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.8, + "cpu_pct": 291.3, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 1.9, + "cpu_pct": 231.9, + "peak_memory_mb": 1434, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 327.5, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 7.9, + "cpu_pct": 156.7, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hcla", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 207.6, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 289.7, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.1, + "cpu_pct": 361.2, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 369.3, + "peak_memory_mb": 3482, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 12.7, + "cpu_pct": 124.4, + "peak_memory_mb": 2765, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 259.2, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 26.3, + "cpu_pct": 56.9, + "peak_memory_mb": 2765, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 221.6, + "peak_memory_mb": 1434, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 281.6, + "peak_memory_mb": 2868, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.7, + "cpu_pct": 374.4, + "peak_memory_mb": 5530, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/hypomap", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 392.8, + "peak_memory_mb": 3584, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 390.3, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.1, + "cpu_pct": 367.6, + "peak_memory_mb": 1536, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 338.9, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 716.8, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 8, + "cpu_pct": 156.5, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.1, + "cpu_pct": 169.3, + "peak_memory_mb": 1536, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.3, + "cpu_pct": 454.7, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.2, + "cpu_pct": 356.6, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 322.1, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 1.9, + "cpu_pct": 727.7, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.5, + "cpu_pct": 580.1, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 289.2, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 1.9, + "cpu_pct": 700.1, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 297.3, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.8, + "cpu_pct": 385.3, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5, + "cpu_pct": 305.7, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 327.5, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 327.4, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.5, + "cpu_pct": 310.1, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.3, + "cpu_pct": 332.9, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.9, + "cpu_pct": 356, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 279.5, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 290.4, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.3, + "cpu_pct": 339.5, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 12.7, + "cpu_pct": 107.8, + "peak_memory_mb": 2765, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 317.5, + "peak_memory_mb": 5530, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.3, + "cpu_pct": 337.7, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.9, + "cpu_pct": 289.4, + "peak_memory_mb": 2868, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 301.6, + "peak_memory_mb": 2868, + "disk_read_mb": 33, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 304.7, + "peak_memory_mb": 5530, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 289.2, + "peak_memory_mb": 5530, + "disk_read_mb": 34, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 322.6, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.1, + "cpu_pct": 202.5, + "peak_memory_mb": 1434, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 279.4, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.8, + "cpu_pct": 361.6, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.3, + "cpu_pct": 224.7, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 319.7, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 327.4, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.1, + "cpu_pct": 220.1, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 4, + "cpu_pct": 333.8, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 8, + "cpu_pct": 121.6, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/cengen", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 299.2, + "peak_memory_mb": 5530, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 282.9, + "peak_memory_mb": 2868, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 258.2, + "peak_memory_mb": 2868, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 278.2, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 248.3, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.7, + "cpu_pct": 355.2, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 244.4, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 173.9, + "peak_memory_mb": 1536, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.1, + "cpu_pct": 372.5, + "peak_memory_mb": 2765, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 267.1, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 242.5, + "peak_memory_mb": 5530, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 12.6, + "cpu_pct": 104.9, + "peak_memory_mb": 2765, + "disk_read_mb": 30, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.5, + "cpu_pct": 328.1, + "peak_memory_mb": 3482, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 1.8, + "cpu_pct": 240.2, + "peak_memory_mb": 1434, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 327.4, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.9, + "cpu_pct": 290.8, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 302.3, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.1, + "cpu_pct": 173, + "peak_memory_mb": 1536, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 322.8, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.5, + "cpu_pct": 310.4, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.1, + "cpu_pct": 169.2, + "peak_memory_mb": 1536, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.3, + "cpu_pct": 330.2, + "peak_memory_mb": 2868, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/pancreas", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 387.8, + "peak_memory_mb": 2765, + "disk_read_mb": 31, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "cell2location", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 366.3, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3.4, + "cpu_pct": 229.8, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "nmfreg", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.7, + "cpu_pct": 324.5, + "peak_memory_mb": 3482, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "nnls", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 6.6, + "cpu_pct": 183.6, + "peak_memory_mb": 5632, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "random_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.1, + "cpu_pct": 319.2, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "rctd", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 3, + "cpu_pct": 176.1, + "peak_memory_mb": 1536, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.4, + "cpu_pct": 317.5, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "stereoscope", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.2, + "cpu_pct": 354.5, + "peak_memory_mb": 2868, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "tangram", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.9, + "cpu_pct": 436.6, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "true_proportions", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 6.6, + "cpu_pct": 150.6, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "normalization_id": "log_cp10k", + "method_id": "vanillanmf", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 5.2, + "cpu_pct": 280, + "peak_memory_mb": 5530, + "disk_read_mb": 32, + "disk_write_mb": 1 + } + } +] diff --git a/results/spatial_decomposition/data/metric_info.json b/results/spatial_decomposition/data/metric_info.json index 4da11a831..8a2176676 100644 --- a/results/spatial_decomposition/data/metric_info.json +++ b/results/spatial_decomposition/data/metric_info.json @@ -1,13 +1,14 @@ [ - { - "metric_name": "r2", - "metric_summary": "R2, or the \u201ccoefficient of determination\u201d, reports the fraction of the true proportion values\u2019 variance that can be explained by the predicted proportion values. The best score, and upper bound, is 1.0. There is no fixed lower bound for the metric. The uniform/non-weighted average across all cell types/states is used to summarise performance.", - "paper_reference": "miles2005rsquared", - "maximize": true, - "image": "openproblems", - "task_id": "spatial_decomposition", - "commit_sha": "b3456fd73c04c28516f6df34c57e6e3e8b0dab32", - "metric_id": "r2", - "implementation_url": "https://github.com/openproblems-bio/openproblems/blob/main/openproblems/tasks/spatial_decomposition/metrics/r2.py" - } -] \ No newline at end of file + { + "task_id": "spatial_decomposition", + "metric_id": "r2", + "metric_name": "R2", + "metric_summary": "R2 represents the proportion of variance in the true proportions which is explained by the predicted proportions.", + "metric_description": "R2, or the “coefficient of determination”, reports the fraction of the true proportion values' variance that can be explained by the predicted proportion values. The best score, and upper bound, is 1.0. There is no fixed lower bound for the metric. The uniform/non-weighted average across all cell types/states is used to summarise performance. By default, cases resulting in a score of NaN (perfect predictions) or -Inf (imperfect predictions) are replaced with 1.0 (perfect predictions) or 0.0 (imperfect predictions) respectively.\n", + "paper_reference": "miles2005rsquared", + "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/metrics/r2/config.vsh.yaml", + "code_version": null, + "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc", + "maximize": true + } +] diff --git a/results/spatial_decomposition/data/quality_control.json b/results/spatial_decomposition/data/quality_control.json index 85bd39a03..4af4f0b96 100644 --- a/results/spatial_decomposition/data/quality_control.json +++ b/results/spatial_decomposition/data/quality_control.json @@ -9,16 +9,6 @@ "code": "percent_missing([task_info], field)", "message": "Task metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" }, - { - "task_id": "spatial_decomposition", - "category": "Task info", - "name": "Pct 'commit_sha' missing", - "value": 0.0, - "severity": 0, - "severity_value": 0.0, - "code": "percent_missing([task_info], field)", - "message": "Task metadata field 'commit_sha' should be defined\n Task id: spatial_decomposition\n Field: commit_sha\n" - }, { "task_id": "spatial_decomposition", "category": "Task info", @@ -199,16 +189,6 @@ "code": "percent_missing(dataset_info, field)", "message": "Dataset metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" }, - { - "task_id": "spatial_decomposition", - "category": "Dataset info", - "name": "Pct 'commit_sha' missing", - "value": 0.0, - "severity": 0, - "severity_value": 0.0, - "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'commit_sha' should be defined\n Task id: spatial_decomposition\n Field: commit_sha\n" - }, { "task_id": "spatial_decomposition", "category": "Dataset info", @@ -251,542 +231,692 @@ }, { "task_id": "spatial_decomposition", - "category": "Raw data", - "name": "Number of results", - "value": 105, + "category": "Dataset info", + "name": "Pct 'data_url' missing", + "value": 0.0, "severity": 0, "severity_value": 0.0, + "code": "percent_missing(dataset_info, field)", + "message": "Dataset metadata field 'data_url' should be defined\n Task id: spatial_decomposition\n Field: data_url\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw data", + "name": "Number of results", + "value": 121, + "severity": 3, + "severity_value": 6.666666666666667, "code": "len(results) == len(method_info) * len(metric_info) * len(dataset_info)", - "message": "Number of results should be equal to #methods × #metrics × #datasets.\n Task id: spatial_decomposition\n Number of results: 105\n Number of methods: 15\n Number of metrics: 1\n Number of datasets: 7\n" + "message": "Number of results should be equal to #methods × #metrics × #datasets.\n Task id: spatial_decomposition\n Number of results: 121\n Number of methods: 11\n Number of metrics: 1\n Number of datasets: 33\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", "name": "Metric 'r2' %missing", + "value": 0.6776859504132231, + "severity": 3, + "severity_value": 6.776859504132231, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n Metric id: r2\n Percentage missing: 68%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'random_proportions' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: random_proportions\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'true_proportions' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: true_proportions\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'cell2location' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'destvi' %missing", + "value": 0.7575757575757576, + "severity": 3, + "severity_value": 7.575757575757575, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: destvi\n Percentage missing: 76%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'nmfreg' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nmfreg\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'nnls' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nnls\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'rctd' %missing", + "value": 0.696969696969697, + "severity": 3, + "severity_value": 6.96969696969697, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: rctd\n Percentage missing: 70%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'seurat' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: seurat\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'stereoscope' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: stereoscope\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'tangram' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: tangram\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Method 'vanillanmf' %missing", + "value": 0.6666666666666667, + "severity": 3, + "severity_value": 6.666666666666667, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: vanillanmf\n Percentage missing: 67%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Dataset 'cellxgene_census/gtex_v9' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n Metric id: r2\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'cell2location_amortised_detection_alpha_20' %missing", + "name": "Dataset 'cellxgene_census/dkd' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location_amortised_detection_alpha_20\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'cell2location_detection_alpha_1' %missing", + "name": "Dataset 'cellxgene_census/dkd' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location_detection_alpha_1\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'cell2location_detection_alpha_20' %missing", + "name": "Dataset 'openproblems_v1/cengen' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location_detection_alpha_20\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'cell2location_detection_alpha_200' %missing", + "name": "Dataset 'openproblems_v1/zebrafish' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location_detection_alpha_200\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'cell2location_detection_alpha_20_nb' %missing", + "name": "Dataset 'openproblems_v1/immune_cells' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location_detection_alpha_20_nb\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'destvi' %missing", + "name": "Dataset 'openproblems_v1/cengen' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: destvi\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'nmf' %missing", - "value": 0.0, + "name": "Dataset 'cellxgene_census/hcla' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": 0.0, + "severity_value": 0.9090909090909094, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nmf\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'nmfreg' %missing", + "name": "Dataset 'openproblems_v1/immune_cells' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nmfreg\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'nnls_scipy' %missing", + "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", + "value": 0.18181818181818177, + "severity": 1, + "severity_value": 1.8181818181818177, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Dataset 'openproblems_v1/zebrafish' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nnls_scipy\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'random_proportions' %missing", + "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", + "value": 0.18181818181818177, + "severity": 1, + "severity_value": 1.8181818181818177, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" + }, + { + "task_id": "spatial_decomposition", + "category": "Raw results", + "name": "Dataset 'openproblems_v1/pancreas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: random_proportions\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'rctd' %missing", + "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: rctd\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'seuratv3' %missing", - "value": 0.0, + "name": "Dataset 'cellxgene_census/hypomap' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": 0.0, + "severity_value": 0.9090909090909094, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: seuratv3\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'stereoscope' %missing", - "value": 0.0, + "name": "Dataset 'cellxgene_census/hypomap' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": 0.0, + "severity_value": 0.9090909090909094, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: stereoscope\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'tangram' %missing", + "name": "Dataset 'openproblems_v1/pancreas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: tangram\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Method 'true_proportions' %missing", + "name": "Dataset 'openproblems_v1/cengen' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: true_proportions\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'destvi' %missing", + "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: destvi\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'pancreas_alpha_0_5' %missing", - "value": 0.0, + "name": "Dataset 'cellxgene_census/hcla' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": 0.0, + "severity_value": 0.9090909090909094, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: pancreas_alpha_0_5\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'pancreas_alpha_1' %missing", + "name": "Dataset 'cellxgene_census/gtex_v9' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: pancreas_alpha_1\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'pancreas_alpha_5' %missing", + "name": "Dataset 'openproblems_v1/immune_cells' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: pancreas_alpha_5\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'tabula_muris_senis_alpha_0_5' %missing", + "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: tabula_muris_senis_alpha_0_5\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'tabula_muris_senis_alpha_1' %missing", + "name": "Dataset 'openproblems_v1/pancreas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: tabula_muris_senis_alpha_1\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Raw results", - "name": "Dataset 'tabula_muris_senis_alpha_5' %missing", + "name": "Dataset 'cellxgene_census/gtex_v9' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: tabula_muris_senis_alpha_5\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Worst score cell2location_amortised_detection_alpha_20 r2", - "value": 0.7322662159563939, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", + "value": 0.0, "severity": 0, - "severity_value": -0.7322662159563939, - "code": "worst_score >= -1", - "message": "Method cell2location_amortised_detection_alpha_20 performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_amortised_detection_alpha_20\n Metric id: r2\n Worst score: 0.7322662159563939%\n" + "severity_value": 0.0, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Best score cell2location_amortised_detection_alpha_20 r2", - "value": 0.9296807723092618, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/hypomap' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": 0.4648403861546309, - "code": "best_score <= 2", - "message": "Method cell2location_amortised_detection_alpha_20 performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_amortised_detection_alpha_20\n Metric id: r2\n Best score: 0.9296807723092618%\n" + "severity_value": 0.9090909090909094, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Worst score cell2location_detection_alpha_1 r2", - "value": 0.7628569130883237, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", + "value": 0.0, "severity": 0, - "severity_value": -0.7628569130883237, - "code": "worst_score >= -1", - "message": "Method cell2location_detection_alpha_1 performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_1\n Metric id: r2\n Worst score: 0.7628569130883237%\n" + "severity_value": 0.0, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Best score cell2location_detection_alpha_1 r2", - "value": 0.924062466633372, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", + "value": 0.0, "severity": 0, - "severity_value": 0.462031233316686, - "code": "best_score <= 2", - "message": "Method cell2location_detection_alpha_1 performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_1\n Metric id: r2\n Best score: 0.924062466633372%\n" + "severity_value": 0.0, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Worst score cell2location_detection_alpha_20 r2", - "value": 0.7600385322353121, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/hcla' %missing", + "value": 0.09090909090909094, "severity": 0, - "severity_value": -0.7600385322353121, - "code": "worst_score >= -1", - "message": "Method cell2location_detection_alpha_20 performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_20\n Metric id: r2\n Worst score: 0.7600385322353121%\n" + "severity_value": 0.9090909090909094, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Best score cell2location_detection_alpha_20 r2", - "value": 0.9255602599770386, + "category": "Raw results", + "name": "Dataset 'openproblems_v1/zebrafish' %missing", + "value": 0.0, "severity": 0, - "severity_value": 0.4627801299885193, - "code": "best_score <= 2", - "message": "Method cell2location_detection_alpha_20 performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_20\n Metric id: r2\n Best score: 0.9255602599770386%\n" + "severity_value": 0.0, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Worst score cell2location_detection_alpha_200 r2", - "value": 0.7573527011136858, - "severity": 0, - "severity_value": -0.7573527011136858, - "code": "worst_score >= -1", - "message": "Method cell2location_detection_alpha_200 performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_200\n Metric id: r2\n Worst score: 0.7573527011136858%\n" + "category": "Raw results", + "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", + "value": 0.18181818181818177, + "severity": 1, + "severity_value": 1.8181818181818177, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" }, { "task_id": "spatial_decomposition", - "category": "Scaling", - "name": "Best score cell2location_detection_alpha_200 r2", - "value": 0.9245426815606511, + "category": "Raw results", + "name": "Dataset 'cellxgene_census/dkd' %missing", + "value": 0.0, "severity": 0, - "severity_value": 0.46227134078032556, - "code": "best_score <= 2", - "message": "Method cell2location_detection_alpha_200 performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_200\n Metric id: r2\n Best score: 0.9245426815606511%\n" + "severity_value": 0.0, + "code": "pct_missing <= .1", + "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score cell2location_detection_alpha_20_nb r2", - "value": 0.7429603420853899, + "name": "Worst score random_proportions r2", + "value": 0, "severity": 0, - "severity_value": -0.7429603420853899, + "severity_value": -0.0, "code": "worst_score >= -1", - "message": "Method cell2location_detection_alpha_20_nb performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_20_nb\n Metric id: r2\n Worst score: 0.7429603420853899%\n" + "message": "Method random_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Worst score: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score cell2location_detection_alpha_20_nb r2", - "value": 0.9258766602045444, + "name": "Best score random_proportions r2", + "value": 0, "severity": 0, - "severity_value": 0.4629383301022722, + "severity_value": 0.0, "code": "best_score <= 2", - "message": "Method cell2location_detection_alpha_20_nb performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location_detection_alpha_20_nb\n Metric id: r2\n Best score: 0.9258766602045444%\n" + "message": "Method random_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Best score: 0%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score destvi r2", - "value": 0.6573217977221304, + "name": "Worst score true_proportions r2", + "value": 1, "severity": 0, - "severity_value": -0.6573217977221304, + "severity_value": -1.0, "code": "worst_score >= -1", - "message": "Method destvi performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Worst score: 0.6573217977221304%\n" + "message": "Method true_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Worst score: 1%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score destvi r2", - "value": 0.9109316825645927, + "name": "Best score true_proportions r2", + "value": 1, "severity": 0, - "severity_value": 0.45546584128229634, + "severity_value": 0.5, "code": "best_score <= 2", - "message": "Method destvi performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Best score: 0.9109316825645927%\n" + "message": "Method true_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Best score: 1%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score nmf r2", - "value": 0.16824737874223977, - "severity": 0, - "severity_value": -0.16824737874223977, + "name": "Worst score cell2location r2", + "value": -3.4575, + "severity": 3, + "severity_value": 3.4575, "code": "worst_score >= -1", - "message": "Method nmf performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nmf\n Metric id: r2\n Worst score: 0.16824737874223977%\n" + "message": "Method cell2location performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Worst score: -3.4575%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score nmf r2", - "value": 0.6480698040854727, + "name": "Best score cell2location r2", + "value": 0.8529, "severity": 0, - "severity_value": 0.32403490204273633, + "severity_value": 0.42645, "code": "best_score <= 2", - "message": "Method nmf performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nmf\n Metric id: r2\n Best score: 0.6480698040854727%\n" + "message": "Method cell2location performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Best score: 0.8529%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score nmfreg r2", - "value": -0.614982949875505, + "name": "Worst score destvi r2", + "value": -0.5927, "severity": 0, - "severity_value": 0.614982949875505, + "severity_value": 0.5927, "code": "worst_score >= -1", - "message": "Method nmfreg performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Worst score: -0.614982949875505%\n" + "message": "Method destvi performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Worst score: -0.5927%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score nmfreg r2", - "value": 0.6429807958978149, + "name": "Best score destvi r2", + "value": 0.7543, "severity": 0, - "severity_value": 0.32149039794890744, + "severity_value": 0.37715, "code": "best_score <= 2", - "message": "Method nmfreg performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Best score: 0.6429807958978149%\n" + "message": "Method destvi performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Best score: 0.7543%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score nnls_scipy r2", - "value": 0.5091300326149931, - "severity": 0, - "severity_value": -0.5091300326149931, + "name": "Worst score nmfreg r2", + "value": -2.2265, + "severity": 2, + "severity_value": 2.2265, "code": "worst_score >= -1", - "message": "Method nnls_scipy performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nnls_scipy\n Metric id: r2\n Worst score: 0.5091300326149931%\n" + "message": "Method nmfreg performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Worst score: -2.2265%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score nnls_scipy r2", - "value": 0.8912139273243389, + "name": "Best score nmfreg r2", + "value": 0.2474, "severity": 0, - "severity_value": 0.44560696366216945, + "severity_value": 0.1237, "code": "best_score <= 2", - "message": "Method nnls_scipy performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nnls_scipy\n Metric id: r2\n Best score: 0.8912139273243389%\n" + "message": "Method nmfreg performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Best score: 0.2474%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score random_proportions r2", - "value": 0.0, - "severity": 0, - "severity_value": -0.0, + "name": "Worst score nnls r2", + "value": -3.3901, + "severity": 3, + "severity_value": 3.3901, "code": "worst_score >= -1", - "message": "Method random_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Worst score: 0.0%\n" + "message": "Method nnls performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nnls\n Metric id: r2\n Worst score: -3.3901%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score random_proportions r2", - "value": 0.0, + "name": "Best score nnls r2", + "value": 0.706, "severity": 0, - "severity_value": 0.0, + "severity_value": 0.353, "code": "best_score <= 2", - "message": "Method random_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Best score: 0.0%\n" + "message": "Method nnls performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nnls\n Metric id: r2\n Best score: 0.706%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Worst score rctd r2", - "value": 0.11381600395286309, + "value": -0.7795, "severity": 0, - "severity_value": -0.11381600395286309, + "severity_value": 0.7795, "code": "worst_score >= -1", - "message": "Method rctd performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Worst score: 0.11381600395286309%\n" + "message": "Method rctd performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Worst score: -0.7795%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Best score rctd r2", - "value": 0.7115782201250389, + "value": 0.8478, "severity": 0, - "severity_value": 0.35578911006251945, + "severity_value": 0.4239, "code": "best_score <= 2", - "message": "Method rctd performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Best score: 0.7115782201250389%\n" + "message": "Method rctd performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Best score: 0.8478%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score seuratv3 r2", - "value": -4.847694679925471, + "name": "Worst score seurat r2", + "value": -3.0585, "severity": 3, - "severity_value": 4.847694679925471, + "severity_value": 3.0585, "code": "worst_score >= -1", - "message": "Method seuratv3 performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: seuratv3\n Metric id: r2\n Worst score: -4.847694679925471%\n" + "message": "Method seurat performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: seurat\n Metric id: r2\n Worst score: -3.0585%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score seuratv3 r2", - "value": 0.09101688053106151, + "name": "Best score seurat r2", + "value": 0.1364, "severity": 0, - "severity_value": 0.045508440265530754, + "severity_value": 0.0682, "code": "best_score <= 2", - "message": "Method seuratv3 performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: seuratv3\n Metric id: r2\n Best score: 0.09101688053106151%\n" + "message": "Method seurat performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: seurat\n Metric id: r2\n Best score: 0.1364%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Worst score stereoscope r2", - "value": 0.33840796092701175, + "value": 0.2221, "severity": 0, - "severity_value": -0.33840796092701175, + "severity_value": -0.2221, "code": "worst_score >= -1", - "message": "Method stereoscope performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Worst score: 0.33840796092701175%\n" + "message": "Method stereoscope performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Worst score: 0.2221%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Best score stereoscope r2", - "value": 0.6838455221001754, + "value": 0.7132, "severity": 0, - "severity_value": 0.3419227610500877, + "severity_value": 0.3566, "code": "best_score <= 2", - "message": "Method stereoscope performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Best score: 0.6838455221001754%\n" + "message": "Method stereoscope performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Best score: 0.7132%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Worst score tangram r2", - "value": -2.638332193078756, - "severity": 2, - "severity_value": 2.638332193078756, + "value": -0.8664, + "severity": 0, + "severity_value": 0.8664, "code": "worst_score >= -1", - "message": "Method tangram performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Worst score: -2.638332193078756%\n" + "message": "Method tangram performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Worst score: -0.8664%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", "name": "Best score tangram r2", - "value": -0.14276174898446656, + "value": -0.0668, "severity": 0, - "severity_value": -0.07138087449223328, + "severity_value": -0.0334, "code": "best_score <= 2", - "message": "Method tangram performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Best score: -0.14276174898446656%\n" + "message": "Method tangram performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Best score: -0.0668%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Worst score true_proportions r2", - "value": 1.0, + "name": "Worst score vanillanmf r2", + "value": -0.7005, "severity": 0, - "severity_value": -1.0, + "severity_value": 0.7005, "code": "worst_score >= -1", - "message": "Method true_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Worst score: 1.0%\n" + "message": "Method vanillanmf performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Worst score: -0.7005%\n" }, { "task_id": "spatial_decomposition", "category": "Scaling", - "name": "Best score true_proportions r2", - "value": 1.0, + "name": "Best score vanillanmf r2", + "value": 0.5231, "severity": 0, - "severity_value": 0.5, + "severity_value": 0.26155, "code": "best_score <= 2", - "message": "Method true_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Best score: 1.0%\n" + "message": "Method vanillanmf performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Best score: 0.5231%\n" } ] \ No newline at end of file diff --git a/results/spatial_decomposition/data/results.json b/results/spatial_decomposition/data/results.json index 079187cda..30adea7e0 100644 --- a/results/spatial_decomposition/data/results.json +++ b/results/spatial_decomposition/data/results.json @@ -1,2312 +1,2543 @@ [ - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.527", - "code_version": "1.9.3", - "resources": { - "duration_sec": 159.0, - "cpu_pct": 58.7, - "peak_memory_mb": 267.5, - "disk_read_mb": 215.6, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 0.6725510350137964 - }, - "scaled_scores": { - "r2": 0.8138047668183754 - }, - "mean_score": 0.8138047668183754 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.697", - "code_version": "0.7.0", - "resources": { - "duration_sec": 180.0, - "cpu_pct": 29.6, - "peak_memory_mb": 137.6, - "disk_read_mb": 215.6, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": -0.7586323741531706 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.728", - "code_version": "1.1.3", - "resources": { - "duration_sec": 180.0, - "cpu_pct": 278.1, - "peak_memory_mb": 658.8, - "disk_read_mb": 215.6, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": -0.36350799618859575 - }, - "scaled_scores": { - "r2": 0.22467707507934284 - }, - "mean_score": 0.22467707507934284 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.914", - "code_version": "0.7.0", - "resources": { - "duration_sec": 279.0, - "cpu_pct": 10.8, - "peak_memory_mb": 658.8, - "disk_read_mb": 215.6, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.878", - "code_version": "1.1.3", - "resources": { - "duration_sec": 319.0, - "cpu_pct": 369.0, - "peak_memory_mb": 1400.0, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 0.13173574042239503 - }, - "scaled_scores": { - "r2": 0.5062843876079002 - }, - "mean_score": 0.5062843876079002 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.875", - "code_version": "1.0.4", - "resources": { - "duration_sec": 529.0, - "cpu_pct": 176.1, - "peak_memory_mb": 1000.0, - "disk_read_mb": 229.0, - "disk_write_mb": 4.8 - }, - "metric_values": { - "r2": -1.101045973606621 - }, - "scaled_scores": { - "r2": -0.19470447859708698 - }, - "mean_score": -0.19470447859708698 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:53.052", - "code_version": "2.1.7", - "resources": { - "duration_sec": 538.0, - "cpu_pct": 51.2, - "peak_memory_mb": 2400.0, - "disk_read_mb": 644.2, - "disk_write_mb": 4.7 - }, - "metric_values": { - "r2": 0.2903002397814603 - }, - "scaled_scores": { - "r2": 0.5964479156365585 - }, - "mean_score": 0.5964479156365585 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 17:57:52.796", - "code_version": "4.3.0", - "resources": { - "duration_sec": 549.0, - "cpu_pct": 114.4, - "peak_memory_mb": 13500.0, - "disk_read_mb": 439.5, - "disk_write_mb": 137.9 - }, - "metric_values": { - "r2": -1.9505696555450878 - }, - "scaled_scores": { - "r2": -0.6777637548983865 - }, - "mean_score": -0.6777637548983865 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 18:35:14.429", - "code_version": "0.20.0", - "resources": { - "duration_sec": 1027.0, - "cpu_pct": 693.1, - "peak_memory_mb": 1200.0, - "disk_read_mb": 237.2, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": 0.15972377629022472 - }, - "scaled_scores": { - "r2": 0.5221990473623623 - }, - "mean_score": 0.5221990473623623 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 23:00:54.269", - "code_version": "0.1.3", - "resources": { - "duration_sec": 3738.0, - "cpu_pct": 1326.8, - "peak_memory_mb": 1200.0, - "disk_read_mb": 240.1, - "disk_write_mb": 14.9 - }, - "metric_values": { - "r2": 0.8255229018687685 - }, - "scaled_scores": { - "r2": 0.9007881916109687 - }, - "mean_score": 0.9007881916109687 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 23:00:54.042", - "code_version": "0.1.3", - "resources": { - "duration_sec": 3959.0, - "cpu_pct": 1272.7, - "peak_memory_mb": 4700.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.0 - }, - "metric_values": { - "r2": 0.8257661429009254 - }, - "scaled_scores": { - "r2": 0.9009265042200916 - }, - "mean_score": 0.9009265042200916 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 22:56:51.772", - "code_version": "0.1.3", - "resources": { - "duration_sec": 4501.0, - "cpu_pct": 1461.6, - "peak_memory_mb": 3200.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.2 - }, - "metric_values": { - "r2": 0.8375905223286515 - }, - "scaled_scores": { - "r2": 0.9076501262809101 - }, - "mean_score": 0.9076501262809101 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 23:00:53.298", - "code_version": "0.1.3", - "resources": { - "duration_sec": 4669.0, - "cpu_pct": 1951.5, - "peak_memory_mb": 18100.0, - "disk_read_mb": 240.1, - "disk_write_mb": 47.5 - }, - "metric_values": { - "r2": 0.8476392540121584 - }, - "scaled_scores": { - "r2": 0.9133640729995048 - }, - "mean_score": 0.9133640729995048 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 23:00:51.704", - "code_version": "0.20.0", - "resources": { - "duration_sec": 7421.0, - "cpu_pct": 2176.3, - "peak_memory_mb": 17500.0, - "disk_read_mb": 237.2, - "disk_write_mb": 7.3 - }, - "metric_values": { - "r2": 0.4200536311539451 - }, - "scaled_scores": { - "r2": 0.670228765619469 - }, - "mean_score": 0.670228765619469 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "pancreas_alpha_1", - "submission_time": "2023-02-21 23:01:42.511", - "code_version": "0.1.3", - "resources": { - "duration_sec": 9880.0, - "cpu_pct": 1342.5, - "peak_memory_mb": 4900.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.0 - }, - "metric_values": { - "r2": 0.8248909658601526 - }, - "scaled_scores": { - "r2": 0.9004288578366658 - }, - "mean_score": 0.9004288578366658 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.251", - "code_version": "1.9.3", - "resources": { - "duration_sec": 319.0, - "cpu_pct": 65.6, - "peak_memory_mb": 146.2, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -0.10261698548173868 - }, - "scaled_scores": { - "r2": 0.529428618853124 - }, - "mean_score": 0.529428618853124 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.312", - "code_version": "0.7.0", - "resources": { - "duration_sec": 319.0, - "cpu_pct": 58.8, - "peak_memory_mb": 140.8, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -1.343145014034729 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.308", - "code_version": "1.1.3", - "resources": { - "duration_sec": 330.0, - "cpu_pct": 1143.7, - "peak_memory_mb": 845.3, - "disk_read_mb": 285.5, - "disk_write_mb": 4.5 - }, - "metric_values": { - "r2": -0.33336175043503596 - }, - "scaled_scores": { - "r2": 0.43095209965725434 - }, - "mean_score": 0.43095209965725434 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.536", - "code_version": "0.7.0", - "resources": { - "duration_sec": 448.0, - "cpu_pct": 16.7, - "peak_memory_mb": 211.6, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.483", - "code_version": "1.0.4", - "resources": { - "duration_sec": 469.0, - "cpu_pct": 358.4, - "peak_memory_mb": 1300.0, - "disk_read_mb": 298.8, - "disk_write_mb": 5.1 - }, - "metric_values": { - "r2": -1.7592798690350302 - }, - "scaled_scores": { - "r2": -0.1775967140351022 - }, - "mean_score": -0.1775967140351022 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.423", - "code_version": "1.1.3", - "resources": { - "duration_sec": 708.0, - "cpu_pct": 350.7, - "peak_memory_mb": 3700.0, - "disk_read_mb": 285.6, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -2.784139246751888 - }, - "scaled_scores": { - "r2": -0.614982949875505 - }, - "mean_score": -0.614982949875505 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.406", - "code_version": "4.3.0", - "resources": { - "duration_sec": 798.0, - "cpu_pct": 121.6, - "peak_memory_mb": 19300.0, - "disk_read_mb": 710.7, - "disk_write_mb": 339.2 - }, - "metric_values": { - "r2": -1.7182059926727573 - }, - "scaled_scores": { - "r2": -0.16006733530853903 - }, - "mean_score": -0.16006733530853903 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 17:59:33.624", - "code_version": "2.1.7", - "resources": { - "duration_sec": 1267.0, - "cpu_pct": 30.6, - "peak_memory_mb": 4300.0, - "disk_read_mb": 714.6, - "disk_write_mb": 5.1 - }, - "metric_values": { - "r2": 0.16885015200580444 - }, - "scaled_scores": { - "r2": 0.6452845030862967 - }, - "mean_score": 0.6452845030862967 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 18:38:33.119", - "code_version": "0.20.0", - "resources": { - "duration_sec": 3048.0, - "cpu_pct": 489.7, - "peak_memory_mb": 1400.0, - "disk_read_mb": 307.0, - "disk_write_mb": 4.8 - }, - "metric_values": { - "r2": 0.009428033679160725 - }, - "scaled_scores": { - "r2": 0.5772468368847796 - }, - "mean_score": 0.5772468368847796 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 19:52:22.086", - "code_version": "0.1.3", - "resources": { - "duration_sec": 10149.0, - "cpu_pct": 1492.4, - "peak_memory_mb": 1300.0, - "disk_read_mb": 310.0, - "disk_write_mb": 17.6 - }, - "metric_values": { - "r2": 0.43773548324671624 - }, - "scaled_scores": { - "r2": 0.7600385322353121 - }, - "mean_score": 0.7600385322353121 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 23:01:11.984", - "code_version": "0.20.0", - "resources": { - "duration_sec": 14780.0, - "cpu_pct": 2321.0, - "peak_memory_mb": 16100.0, - "disk_read_mb": 307.1, - "disk_write_mb": 7.8 - }, - "metric_values": { - "r2": 0.342256513351454 - }, - "scaled_scores": { - "r2": 0.7192903201855363 - }, - "mean_score": 0.7192903201855363 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 23:06:03.049", - "code_version": "0.1.3", - "resources": { - "duration_sec": 19539.0, - "cpu_pct": 1299.9, - "peak_memory_mb": 1300.0, - "disk_read_mb": 310.0, - "disk_write_mb": 16.0 - }, - "metric_values": { - "r2": 0.43144219144553786 - }, - "scaled_scores": { - "r2": 0.7573527011136858 - }, - "mean_score": 0.7573527011136858 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 23:08:03.022", - "code_version": "0.1.3", - "resources": { - "duration_sec": 20899.0, - "cpu_pct": 1544.6, - "peak_memory_mb": 5900.0, - "disk_read_mb": 310.0, - "disk_write_mb": 16.0 - }, - "metric_values": { - "r2": 0.39771880714818886 - }, - "scaled_scores": { - "r2": 0.7429603420853899 - }, - "mean_score": 0.7429603420853899 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 23:06:02.573", - "code_version": "0.1.3", - "resources": { - "duration_sec": 21339.0, - "cpu_pct": 1916.5, - "peak_memory_mb": 16500.0, - "disk_read_mb": 310.0, - "disk_write_mb": 51.3 - }, - "metric_values": { - "r2": 0.37266091882957325 - }, - "scaled_scores": { - "r2": 0.7322662159563939 - }, - "mean_score": 0.7322662159563939 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "tabula_muris_senis_alpha_1", - "submission_time": "2023-02-21 23:21:22.009", - "code_version": "0.1.3", - "resources": { - "duration_sec": 25460.0, - "cpu_pct": 1393.3, - "peak_memory_mb": 1300.0, - "disk_read_mb": 310.0, - "disk_write_mb": 15.9 - }, - "metric_values": { - "r2": 0.4443393582901012 - }, - "scaled_scores": { - "r2": 0.7628569130883237 - }, - "mean_score": 0.7628569130883237 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:33.043", - "code_version": "0.7.0", - "resources": { - "duration_sec": 339.0, - "cpu_pct": 30.5, - "peak_memory_mb": 635.0, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.749", - "code_version": "0.7.0", - "resources": { - "duration_sec": 359.0, - "cpu_pct": 20.7, - "peak_memory_mb": 224.9, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": -0.6788678218288058 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.757", - "code_version": "1.9.3", - "resources": { - "duration_sec": 429.0, - "cpu_pct": 14.4, - "peak_memory_mb": 237.0, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 0.8173625631217027 - }, - "scaled_scores": { - "r2": 0.8912139273243389 - }, - "mean_score": 0.8912139273243389 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.856", - "code_version": "1.1.3", - "resources": { - "duration_sec": 439.0, - "cpu_pct": 87.1, - "peak_memory_mb": 658.5, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": 0.29515643384923823 - }, - "scaled_scores": { - "r2": 0.5801673264647068 - }, - "mean_score": 0.5801673264647068 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.916", - "code_version": "1.1.3", - "resources": { - "duration_sec": 480.0, - "cpu_pct": 372.3, - "peak_memory_mb": 1500.0, - "disk_read_mb": 215.7, - "disk_write_mb": 4.099999 - }, - "metric_values": { - "r2": -0.009115963663603491 - }, - "scaled_scores": { - "r2": 0.39893066592677656 - }, - "mean_score": 0.39893066592677656 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.890", - "code_version": "4.3.0", - "resources": { - "duration_sec": 679.0, - "cpu_pct": 134.7, - "peak_memory_mb": 22200.0, - "disk_read_mb": 439.6, - "disk_write_mb": 138.0 - }, - "metric_values": { - "r2": -1.1273708605624777 - }, - "scaled_scores": { - "r2": -0.26714612842189894 - }, - "mean_score": -0.26714612842189894 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:32.981", - "code_version": "1.0.4", - "resources": { - "duration_sec": 699.0, - "cpu_pct": 190.6, - "peak_memory_mb": 1000.0, - "disk_read_mb": 229.0, - "disk_write_mb": 4.8 - }, - "metric_values": { - "r2": -1.026672422946978 - }, - "scaled_scores": { - "r2": -0.20716616078763453 - }, - "mean_score": -0.20716616078763453 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 17:59:33.087", - "code_version": "2.1.7", - "resources": { - "duration_sec": 1032.0, - "cpu_pct": 28.4, - "peak_memory_mb": 2400.0, - "disk_read_mb": 644.7, - "disk_write_mb": 4.7 - }, - "metric_values": { - "r2": 0.2850966455673833 - }, - "scaled_scores": { - "r2": 0.5741753191422384 - }, - "mean_score": 0.5741753191422384 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 18:37:31.764", - "code_version": "0.20.0", - "resources": { - "duration_sec": 1340.0, - "cpu_pct": 657.4, - "peak_memory_mb": 1300.0, - "disk_read_mb": 237.2, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": 0.15075650262675666 - }, - "scaled_scores": { - "r2": 0.49415702276778717 - }, - "mean_score": 0.49415702276778717 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:00:55.365", - "code_version": "0.1.3", - "resources": { - "duration_sec": 6178.0, - "cpu_pct": 1892.2, - "peak_memory_mb": 15900.0, - "disk_read_mb": 240.1, - "disk_write_mb": 47.5 - }, - "metric_values": { - "r2": 0.8819433113741667 - }, - "scaled_scores": { - "r2": 0.9296807723092618 - }, - "mean_score": 0.9296807723092618 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:00:59.415", - "code_version": "0.1.3", - "resources": { - "duration_sec": 6733.0, - "cpu_pct": 1242.4, - "peak_memory_mb": 1200.0, - "disk_read_mb": 240.1, - "disk_write_mb": 14.9 - }, - "metric_values": { - "r2": 0.8733171361506876 - }, - "scaled_scores": { - "r2": 0.9245426815606511 - }, - "mean_score": 0.9245426815606511 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:00:58.020", - "code_version": "0.1.3", - "resources": { - "duration_sec": 6904.0, - "cpu_pct": 1393.0, - "peak_memory_mb": 3200.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.1 - }, - "metric_values": { - "r2": 0.8755567099709268 - }, - "scaled_scores": { - "r2": 0.9258766602045444 - }, - "mean_score": 0.9258766602045444 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:04:21.791", - "code_version": "0.1.3", - "resources": { - "duration_sec": 11990.0, - "cpu_pct": 1369.0, - "peak_memory_mb": 1200.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.2 - }, - "metric_values": { - "r2": 0.8750255158101483 - }, - "scaled_scores": { - "r2": 0.9255602599770386 - }, - "mean_score": 0.9255602599770386 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:01:02.654", - "code_version": "0.20.0", - "resources": { - "duration_sec": 16729.0, - "cpu_pct": 2171.5, - "peak_memory_mb": 17100.0, - "disk_read_mb": 237.3, - "disk_write_mb": 7.4 - }, - "metric_values": { - "r2": 0.4246885929535422 - }, - "scaled_scores": { - "r2": 0.6573217977221304 - }, - "mean_score": 0.6573217977221304 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "pancreas_alpha_0_5", - "submission_time": "2023-02-21 23:16:32.009", - "code_version": "0.1.3", - "resources": { - "duration_sec": 21590.0, - "cpu_pct": 1345.2, - "peak_memory_mb": 3400.0, - "disk_read_mb": 240.1, - "disk_write_mb": 15.0 - }, - "metric_values": { - "r2": 0.872510918761717 - }, - "scaled_scores": { - "r2": 0.924062466633372 - }, - "mean_score": 0.924062466633372 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.575", - "code_version": "0.7.0", - "resources": { - "duration_sec": 310.0, - "cpu_pct": 41.8, - "peak_memory_mb": 844.3, - "disk_read_mb": 285.4, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.240", - "code_version": "0.7.0", - "resources": { - "duration_sec": 390.0, - "cpu_pct": 19.3, - "peak_memory_mb": 233.1, - "disk_read_mb": 285.4, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": -1.6997749044765091 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.219", - "code_version": "1.9.3", - "resources": { - "duration_sec": 420.0, - "cpu_pct": 28.3, - "peak_memory_mb": 844.2, - "disk_read_mb": 285.4, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": 0.21573107550895285 - }, - "scaled_scores": { - "r2": 0.7095058098396843 - }, - "mean_score": 0.7095058098396843 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.500", - "code_version": "1.0.4", - "resources": { - "duration_sec": 439.0, - "cpu_pct": 219.5, - "peak_memory_mb": 1400.0, - "disk_read_mb": 298.7, - "disk_write_mb": 5.0 - }, - "metric_values": { - "r2": -2.230206915224445 - }, - "scaled_scores": { - "r2": -0.1964726799513634 - }, - "mean_score": -0.1964726799513634 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.396", - "code_version": "1.1.3", - "resources": { - "duration_sec": 450.0, - "cpu_pct": 139.7, - "peak_memory_mb": 845.6, - "disk_read_mb": 285.4, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": 0.049867688942457904 - }, - "scaled_scores": { - "r2": 0.6480698040854727 - }, - "mean_score": 0.6480698040854727 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.443", - "code_version": "1.1.3", - "resources": { - "duration_sec": 669.0, - "cpu_pct": 274.4, - "peak_memory_mb": 3700.0, - "disk_read_mb": 285.5, - "disk_write_mb": 4.4 - }, - "metric_values": { - "r2": -1.5069802848034444 - }, - "scaled_scores": { - "r2": 0.07141136816754283 - }, - "mean_score": 0.07141136816754283 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:23.022", - "code_version": "4.3.0", - "resources": { - "duration_sec": 699.0, - "cpu_pct": 135.2, - "peak_memory_mb": 24900.0, - "disk_read_mb": 710.5, - "disk_write_mb": 338.9 - }, - "metric_values": { - "r2": -1.4540498145350127 - }, - "scaled_scores": { - "r2": 0.09101688053106151 - }, - "mean_score": 0.09101688053106151 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:01:22.701", - "code_version": "2.1.7", - "resources": { - "duration_sec": 987.0, - "cpu_pct": 41.4, - "peak_memory_mb": 4300.0, - "disk_read_mb": 714.1, - "disk_write_mb": 4.9 - }, - "metric_values": { - "r2": 0.22132611678913217 - }, - "scaled_scores": { - "r2": 0.7115782201250389 - }, - "mean_score": 0.7115782201250389 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 18:38:54.230", - "code_version": "0.20.0", - "resources": { - "duration_sec": 3807.0, - "cpu_pct": 424.2, - "peak_memory_mb": 1400.0, - "disk_read_mb": 306.9, - "disk_write_mb": 4.8 - }, - "metric_values": { - "r2": 0.00658134561921141 - }, - "scaled_scores": { - "r2": 0.6320364883999786 - }, - "mean_score": 0.6320364883999786 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 19:51:33.305", - "code_version": "0.1.3", - "resources": { - "duration_sec": 8338.0, - "cpu_pct": 1480.7, - "peak_memory_mb": 1300.0, - "disk_read_mb": 309.9, - "disk_write_mb": 17.4 - }, - "metric_values": { - "r2": 0.5703817274549663 - }, - "scaled_scores": { - "r2": 0.8408688547209316 - }, - "mean_score": 0.8408688547209316 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 23:01:42.179", - "code_version": "0.1.3", - "resources": { - "duration_sec": 9040.0, - "cpu_pct": 1241.7, - "peak_memory_mb": 1300.0, - "disk_read_mb": 309.9, - "disk_write_mb": 15.8 - }, - "metric_values": { - "r2": 0.5728543404075948 - }, - "scaled_scores": { - "r2": 0.841784713649959 - }, - "mean_score": 0.841784713649959 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 23:01:42.960", - "code_version": "0.1.3", - "resources": { - "duration_sec": 9709.0, - "cpu_pct": 1297.2, - "peak_memory_mb": 1300.0, - "disk_read_mb": 309.9, - "disk_write_mb": 15.8 - }, - "metric_values": { - "r2": 0.5731468767196805 - }, - "scaled_scores": { - "r2": 0.8418930694656979 - }, - "mean_score": 0.8418930694656979 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 23:01:42.736", - "code_version": "0.1.3", - "resources": { - "duration_sec": 11129.0, - "cpu_pct": 1549.1, - "peak_memory_mb": 6200.0, - "disk_read_mb": 309.9, - "disk_write_mb": 15.9 - }, - "metric_values": { - "r2": 0.5415333252062493 - }, - "scaled_scores": { - "r2": 0.8301833704604168 - }, - "mean_score": 0.8301833704604168 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 23:01:52.214", - "code_version": "0.1.3", - "resources": { - "duration_sec": 11930.0, - "cpu_pct": 1889.6, - "peak_memory_mb": 17600.0, - "disk_read_mb": 309.9, - "disk_write_mb": 51.2 - }, - "metric_values": { - "r2": 0.5365943537638295 - }, - "scaled_scores": { - "r2": 0.8283539692632169 - }, - "mean_score": 0.8283539692632169 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "tabula_muris_senis_alpha_0_5", - "submission_time": "2023-02-21 23:00:57.250", - "code_version": "0.20.0", - "resources": { - "duration_sec": 13145.0, - "cpu_pct": 2316.3, - "peak_memory_mb": 16399.999999, - "disk_read_mb": 307.0, - "disk_write_mb": 7.7 - }, - "metric_values": { - "r2": 0.4775678626963948 - }, - "scaled_scores": { - "r2": 0.8064904831742238 - }, - "mean_score": 0.8064904831742238 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.617", - "code_version": "0.7.0", - "resources": { - "duration_sec": 489.0, - "cpu_pct": 36.2, - "peak_memory_mb": 224.9, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -2.123637053724888 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.928", - "code_version": "0.7.0", - "resources": { - "duration_sec": 509.0, - "cpu_pct": 8.4, - "peak_memory_mb": 233.5, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.776", - "code_version": "1.0.4", - "resources": { - "duration_sec": 529.0, - "cpu_pct": 524.4, - "peak_memory_mb": 1300.0, - "disk_read_mb": 298.9, - "disk_write_mb": 5.1 - }, - "metric_values": { - "r2": -2.6330378865410045 - }, - "scaled_scores": { - "r2": -0.16307939240529365 - }, - "mean_score": -0.16307939240529365 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.654", - "code_version": "1.9.3", - "resources": { - "duration_sec": 569.0, - "cpu_pct": 17.0, - "peak_memory_mb": 845.8, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -0.5101386294823858 - }, - "scaled_scores": { - "r2": 0.5165447830497564 - }, - "mean_score": 0.5165447830497564 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.707", - "code_version": "1.1.3", - "resources": { - "duration_sec": 579.0, - "cpu_pct": 382.4, - "peak_memory_mb": 844.9, - "disk_read_mb": 285.5, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -0.3725477367867464 - }, - "scaled_scores": { - "r2": 0.5605930800603083 - }, - "mean_score": 0.5605930800603083 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.738", - "code_version": "1.1.3", - "resources": { - "duration_sec": 759.0, - "cpu_pct": 369.1, - "peak_memory_mb": 3700.0, - "disk_read_mb": 285.6, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": -2.772659959591405 - }, - "scaled_scores": { - "r2": -0.2077779507361674 - }, - "mean_score": -0.2077779507361674 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.745", - "code_version": "4.3.0", - "resources": { - "duration_sec": 923.0, - "cpu_pct": 136.9, - "peak_memory_mb": 26500.0, - "disk_read_mb": 710.8, - "disk_write_mb": 339.3 - }, - "metric_values": { - "r2": -1.9140587049769946 - }, - "scaled_scores": { - "r2": 0.06709433431069547 - }, - "mean_score": 0.06709433431069547 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.853", - "code_version": "2.1.7", - "resources": { - "duration_sec": 1138.0, - "cpu_pct": 39.8, - "peak_memory_mb": 4300.0, - "disk_read_mb": 714.3, - "disk_write_mb": 5.1 - }, - "metric_values": { - "r2": -0.14733452360153512 - }, - "scaled_scores": { - "r2": 0.6326927540338412 - }, - "mean_score": 0.6326927540338412 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 18:02:12.978", - "code_version": "0.20.0", - "resources": { - "duration_sec": 1258.0, - "cpu_pct": 729.8, - "peak_memory_mb": 1400.0, - "disk_read_mb": 307.1, - "disk_write_mb": 4.8 - }, - "metric_values": { - "r2": 0.012448158131061517 - }, - "scaled_scores": { - "r2": 0.6838455221001754 - }, - "mean_score": 0.6838455221001754 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:01:00.157", - "code_version": "0.1.3", - "resources": { - "duration_sec": 8942.0, - "cpu_pct": 1920.5, - "peak_memory_mb": 16800.0, - "disk_read_mb": 310.0, - "disk_write_mb": 51.3 - }, - "metric_values": { - "r2": 0.16819668130937404 - }, - "scaled_scores": { - "r2": 0.7337067961533132 - }, - "mean_score": 0.7337067961533132 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:01:43.999", - "code_version": "0.1.3", - "resources": { - "duration_sec": 10238.0, - "cpu_pct": 1263.7, - "peak_memory_mb": 1300.0, - "disk_read_mb": 310.0, - "disk_write_mb": 15.9 - }, - "metric_values": { - "r2": 0.26524130129571694 - }, - "scaled_scores": { - "r2": 0.7647746245588632 - }, - "mean_score": 0.7647746245588632 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:01:14.713", - "code_version": "0.1.3", - "resources": { - "duration_sec": 15177.0, - "cpu_pct": 1565.6, - "peak_memory_mb": 6000.0, - "disk_read_mb": 310.0, - "disk_write_mb": 16.1 - }, - "metric_values": { - "r2": 0.21475313989059847 - }, - "scaled_scores": { - "r2": 0.7486113634191249 - }, - "mean_score": 0.7486113634191249 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:05:22.783", - "code_version": "0.1.3", - "resources": { - "duration_sec": 18869.0, - "cpu_pct": 1315.0, - "peak_memory_mb": 1500.0, - "disk_read_mb": 310.0, - "disk_write_mb": 15.9 - }, - "metric_values": { - "r2": 0.26726636845573154 - }, - "scaled_scores": { - "r2": 0.7654229288033015 - }, - "mean_score": 0.7654229288033015 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:08:02.230", - "code_version": "0.1.3", - "resources": { - "duration_sec": 19360.0, - "cpu_pct": 1319.4, - "peak_memory_mb": 1600.0, - "disk_read_mb": 310.0, - "disk_write_mb": 16.0 - }, - "metric_values": { - "r2": 0.26463040796770465 - }, - "scaled_scores": { - "r2": 0.7645790533969435 - }, - "mean_score": 0.7645790533969435 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "tabula_muris_senis_alpha_5", - "submission_time": "2023-02-21 23:05:22.353", - "code_version": "0.20.0", - "resources": { - "duration_sec": 25819.0, - "cpu_pct": 2293.2, - "peak_memory_mb": 16100.0, - "disk_read_mb": 307.1, - "disk_write_mb": 7.8 - }, - "metric_values": { - "r2": 0.1825519677141374 - }, - "scaled_scores": { - "r2": 0.7383024921826086 - }, - "mean_score": 0.7383024921826086 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.599", - "code_version": "0.7.0", - "resources": { - "duration_sec": 460.0, - "cpu_pct": 11.7, - "peak_memory_mb": 225.4, - "disk_read_mb": 215.6, - "disk_write_mb": 4.0 - }, - "metric_values": { - "r2": -1.5048844077651864 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.606", - "code_version": "1.9.3", - "resources": { - "duration_sec": 460.0, - "cpu_pct": 10.6, - "peak_memory_mb": 226.7, - "disk_read_mb": 215.6, - "disk_write_mb": 4.0 - }, - "metric_values": { - "r2": 0.28550643716174523 - }, - "scaled_scores": { - "r2": 0.714759866513875 - }, - "mean_score": 0.714759866513875 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.780", - "code_version": "0.7.0", - "resources": { - "duration_sec": 460.0, - "cpu_pct": 11.9, - "peak_memory_mb": 225.6, - "disk_read_mb": 215.6, - "disk_write_mb": 4.0 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.733", - "code_version": "1.1.3", - "resources": { - "duration_sec": 470.0, - "cpu_pct": 112.1, - "peak_memory_mb": 658.7, - "disk_read_mb": 215.6, - "disk_write_mb": 4.0 - }, - "metric_values": { - "r2": -1.083444172106386 - }, - "scaled_scores": { - "r2": 0.16824737874223977 - }, - "mean_score": 0.16824737874223977 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.727", - "code_version": "1.1.3", - "resources": { - "duration_sec": 540.0, - "cpu_pct": 581.8, - "peak_memory_mb": 1400.0, - "disk_read_mb": 215.6, - "disk_write_mb": 4.0 - }, - "metric_values": { - "r2": -0.33816912836317026 - }, - "scaled_scores": { - "r2": 0.4657760956095131 - }, - "mean_score": 0.4657760956095131 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.761", - "code_version": "1.0.4", - "resources": { - "duration_sec": 591.0, - "cpu_pct": 491.3, - "peak_memory_mb": 1000.0, - "disk_read_mb": 229.0, - "disk_write_mb": 4.7 - }, - "metric_values": { - "r2": -1.8624860868216642 - }, - "scaled_scores": { - "r2": -0.14276174898446656 - }, - "mean_score": -0.14276174898446656 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:02:42.703", - "code_version": "4.3.0", - "resources": { - "duration_sec": 649.0, - "cpu_pct": 144.8, - "peak_memory_mb": 72000.0, - "disk_read_mb": 440.3, - "disk_write_mb": 137.9 - }, - "metric_values": { - "r2": -2.778652178337191 - }, - "scaled_scores": { - "r2": -0.5085135931316038 - }, - "mean_score": -0.5085135931316038 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:40:21.584", - "code_version": "0.20.0", - "resources": { - "duration_sec": 1460.0, - "cpu_pct": 588.1, - "peak_memory_mb": 1300.0, - "disk_read_mb": 237.1, - "disk_write_mb": 4.3 - }, - "metric_values": { - "r2": 0.17389604990595645 - }, - "scaled_scores": { - "r2": 0.6702027656313774 - }, - "mean_score": 0.6702027656313774 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 18:43:42.576", - "code_version": "2.1.7", - "resources": { - "duration_sec": 2619.0, - "cpu_pct": 26.0, - "peak_memory_mb": 2400.0, - "disk_read_mb": 644.6, - "disk_write_mb": 4.6 - }, - "metric_values": { - "r2": 0.20661257377402853 - }, - "scaled_scores": { - "r2": 0.6832638569003597 - }, - "mean_score": 0.6832638569003597 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:00:57.524", - "code_version": "0.1.3", - "resources": { - "duration_sec": 6605.0, - "cpu_pct": 1312.7, - "peak_memory_mb": 1900.0, - "disk_read_mb": 240.0, - "disk_write_mb": 15.9 - }, - "metric_values": { - "r2": 0.6763858442002704 - }, - "scaled_scores": { - "r2": 0.8708067506841753 - }, - "mean_score": 0.8708067506841753 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:01:13.035", - "code_version": "0.20.0", - "resources": { - "duration_sec": 12289.0, - "cpu_pct": 2164.3, - "peak_memory_mb": 17200.0, - "disk_read_mb": 237.2, - "disk_write_mb": 7.3 - }, - "metric_values": { - "r2": 0.29962619465676177 - }, - "scaled_scores": { - "r2": 0.7203967563644585 - }, - "mean_score": 0.7203967563644585 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:04:22.066", - "code_version": "0.1.3", - "resources": { - "duration_sec": 16090.0, - "cpu_pct": 1367.1, - "peak_memory_mb": 1200.0, - "disk_read_mb": 240.0, - "disk_write_mb": 15.0 - }, - "metric_values": { - "r2": 0.6728021897688164 - }, - "scaled_scores": { - "r2": 0.8693760840951923 - }, - "mean_score": 0.8693760840951923 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:05:13.136", - "code_version": "0.1.3", - "resources": { - "duration_sec": 17769.0, - "cpu_pct": 1502.0, - "peak_memory_mb": 3200.0, - "disk_read_mb": 240.0, - "disk_write_mb": 15.0 - }, - "metric_values": { - "r2": 0.6726500694644983 - }, - "scaled_scores": { - "r2": 0.8693153546244644 - }, - "mean_score": 0.8693153546244644 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:06:03.346", - "code_version": "0.1.3", - "resources": { - "duration_sec": 19219.0, - "cpu_pct": 1287.0, - "peak_memory_mb": 3500.0, - "disk_read_mb": 240.0, - "disk_write_mb": 14.9 - }, - "metric_values": { - "r2": 0.6656370580556353 - }, - "scaled_scores": { - "r2": 0.866515620078981 - }, - "mean_score": 0.866515620078981 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "pancreas_alpha_5", - "submission_time": "2023-02-21 23:18:32.401", - "code_version": "0.1.3", - "resources": { - "duration_sec": 25550.0, - "cpu_pct": 1904.8, - "peak_memory_mb": 17900.0, - "disk_read_mb": 240.0, - "disk_write_mb": 47.5 - }, - "metric_values": { - "r2": 0.6453329013682804 - }, - "scaled_scores": { - "r2": 0.8584097942674539 - }, - "mean_score": 0.8584097942674539 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nnls_scipy", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.655", - "code_version": "1.9.3", - "resources": { - "duration_sec": 530.0, - "cpu_pct": 72.3, - "peak_memory_mb": 1300.0, - "disk_read_mb": 472.2, - "disk_write_mb": 25.1 - }, - "metric_values": { - "r2": 0.3955919390431558 - }, - "scaled_scores": { - "r2": 0.5091300326149931 - }, - "mean_score": 0.5091300326149931 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "random_proportions", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.713", - "code_version": "0.7.0", - "resources": { - "duration_sec": 540.0, - "cpu_pct": 67.8, - "peak_memory_mb": 235.1, - "disk_read_mb": 472.2, - "disk_write_mb": 25.1 - }, - "metric_values": { - "r2": -0.23129973539975293 - }, - "scaled_scores": { - "r2": 0.0 - }, - "mean_score": 0.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmf", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.767", - "code_version": "1.1.3", - "resources": { - "duration_sec": 540.0, - "cpu_pct": 185.5, - "peak_memory_mb": 1300.0, - "disk_read_mb": 472.2, - "disk_write_mb": 25.1 - }, - "metric_values": { - "r2": 0.18038559654428302 - }, - "scaled_scores": { - "r2": 0.33435021555525507 - }, - "mean_score": 0.33435021555525507 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "nmfreg", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.880", - "code_version": "1.1.3", - "resources": { - "duration_sec": 644.0, - "cpu_pct": 336.6, - "peak_memory_mb": 2300.0, - "disk_read_mb": 472.2, - "disk_write_mb": 25.1 - }, - "metric_values": { - "r2": 0.5604023484563492 - }, - "scaled_scores": { - "r2": 0.6429807958978149 - }, - "mean_score": 0.6429807958978149 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "true_proportions", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.896", - "code_version": "0.7.0", - "resources": { - "duration_sec": 644.0, - "cpu_pct": 14.0, - "peak_memory_mb": 232.9, - "disk_read_mb": 472.2, - "disk_write_mb": 25.1 - }, - "metric_values": { - "r2": 1.0 - }, - "scaled_scores": { - "r2": 1.0 - }, - "mean_score": 1.0 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "seuratv3", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:42.829", - "code_version": "4.3.0", - "resources": { - "duration_sec": 939.0, - "cpu_pct": 117.6, - "peak_memory_mb": 68800.0, - "disk_read_mb": 1200.0, - "disk_write_mb": 784.9 - }, - "metric_values": { - "r2": -6.200264912090775 - }, - "scaled_scores": { - "r2": -4.847694679925471 - }, - "mean_score": -4.847694679925471 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "rctd", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:43.049", - "code_version": "2.1.7", - "resources": { - "duration_sec": 1039.0, - "cpu_pct": 50.0, - "peak_memory_mb": 4300.0, - "disk_read_mb": 900.8, - "disk_write_mb": 31.3 - }, - "metric_values": { - "r2": -0.09115811984833537 - }, - "scaled_scores": { - "r2": 0.11381600395286309 - }, - "mean_score": 0.11381600395286309 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "stereoscope", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:05:43.061", - "code_version": "0.20.0", - "resources": { - "duration_sec": 1990.0, - "cpu_pct": 186.3, - "peak_memory_mb": 1600.0, - "disk_read_mb": 493.6, - "disk_write_mb": 25.4 - }, - "metric_values": { - "r2": 0.18538189734684662 - }, - "scaled_scores": { - "r2": 0.33840796092701175 - }, - "mean_score": 0.33840796092701175 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "tangram", - "dataset_id": "destvi", - "submission_time": "2023-02-21 18:44:22.224", - "code_version": "1.0.4", - "resources": { - "duration_sec": 3349.0, - "cpu_pct": 475.6, - "peak_memory_mb": 3200.0, - "disk_read_mb": 485.4, - "disk_write_mb": 25.3 - }, - "metric_values": { - "r2": -3.4798774666342758 - }, - "scaled_scores": { - "r2": -2.638332193078756 - }, - "mean_score": -2.638332193078756 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20", - "dataset_id": "destvi", - "submission_time": "2023-02-21 23:14:32.681", - "code_version": "0.1.3", - "resources": { - "duration_sec": 22909.0, - "cpu_pct": 2072.0, - "peak_memory_mb": 5200.0, - "disk_read_mb": 496.4, - "disk_write_mb": 38.7 - }, - "metric_values": { - "r2": 0.891920786279696 - }, - "scaled_scores": { - "r2": 0.9122234736083856 - }, - "mean_score": 0.9122234736083856 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_200", - "dataset_id": "destvi", - "submission_time": "2023-02-21 23:15:03.305", - "code_version": "0.1.3", - "resources": { - "duration_sec": 23159.0, - "cpu_pct": 2039.5, - "peak_memory_mb": 5200.0, - "disk_read_mb": 496.4, - "disk_write_mb": 38.7 - }, - "metric_values": { - "r2": 0.8919090128569765 - }, - "scaled_scores": { - "r2": 0.91221391182389 - }, - "mean_score": 0.91221391182389 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_20_nb", - "dataset_id": "destvi", - "submission_time": "2023-02-21 23:15:01.890", - "code_version": "0.1.3", - "resources": { - "duration_sec": 24710.0, - "cpu_pct": 1887.7, - "peak_memory_mb": 5200.0, - "disk_read_mb": 496.4, - "disk_write_mb": 38.9 - }, - "metric_values": { - "r2": 0.8923773569843789 - }, - "scaled_scores": { - "r2": 0.9125942774764908 - }, - "mean_score": 0.9125942774764908 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_amortised_detection_alpha_20", - "dataset_id": "destvi", - "submission_time": "2023-02-21 23:08:51.873", - "code_version": "0.1.3", - "resources": { - "duration_sec": 26560.0, - "cpu_pct": 1909.0, - "peak_memory_mb": 41300.0, - "disk_read_mb": 496.4, - "disk_write_mb": 65.2 - }, - "metric_values": { - "r2": 0.8927061509087052 - }, - "scaled_scores": { - "r2": 0.9128613074407419 - }, - "mean_score": 0.9128613074407419 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "cell2location_detection_alpha_1", - "dataset_id": "destvi", - "submission_time": "2023-02-21 23:22:03.329", - "code_version": "0.1.3", - "resources": { - "duration_sec": 28349.0, - "cpu_pct": 2009.5, - "peak_memory_mb": 5300.0, - "disk_read_mb": 496.4, - "disk_write_mb": 38.7 - }, - "metric_values": { - "r2": 0.8919692943402945 - }, - "scaled_scores": { - "r2": 0.9122628694266449 - }, - "mean_score": 0.9122628694266449 - }, - { - "task_id": "spatial_decomposition", - "commit_sha": "65efdc87e3f4048b94b98c6f9fbfe10dae8d5ab0", - "method_id": "destvi", - "dataset_id": "destvi", - "submission_time": "2023-02-22 08:08:32.187", - "code_version": "0.20.0", - "resources": { - "duration_sec": 23700.0, - "cpu_pct": 2259.9, - "peak_memory_mb": 22200.0, - "disk_read_mb": 493.8, - "disk_write_mb": 28.4 - }, - "metric_values": { - "r2": 0.8903302043092818 - }, - "scaled_scores": { - "r2": 0.9109316825645927 - }, - "mean_score": 0.9109316825645927 - } -] \ No newline at end of file + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "cell2location", + "metric_values": { + "r2": 0.577 + }, + "scaled_scores": { + "r2": 0.7704 + }, + "mean_score": 0.7704, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3550, + "cpu_pct": 1759.5, + "peak_memory_mb": 16794, + "disk_read_mb": 777, + "disk_write_mb": 13 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "destvi", + "metric_values": { + "r2": 0.5475 + }, + "scaled_scores": { + "r2": 0.7543 + }, + "mean_score": 0.7543, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 4121, + "cpu_pct": 101.3, + "peak_memory_mb": 15770, + "disk_read_mb": 719, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "nmfreg", + "metric_values": { + "r2": -0.3863 + }, + "scaled_scores": { + "r2": 0.2474 + }, + "mean_score": 0.2474, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 455, + "cpu_pct": 110.2, + "peak_memory_mb": 8397, + "disk_read_mb": 675, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "nnls", + "metric_values": { + "r2": 0.3433 + }, + "scaled_scores": { + "r2": 0.6435 + }, + "mean_score": 0.6435, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 8.9, + "cpu_pct": 345.7, + "peak_memory_mb": 4711, + "disk_read_mb": 664, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.8421 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 4.9, + "cpu_pct": 163.7, + "peak_memory_mb": 3175, + "disk_read_mb": 665, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "rctd", + "metric_values": { + "r2": 0.5304 + }, + "scaled_scores": { + "r2": 0.745 + }, + "mean_score": 0.745, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 309, + "cpu_pct": 56.9, + "peak_memory_mb": 17204, + "disk_read_mb": 1024, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "seurat", + "metric_values": { + "r2": -2.5101 + }, + "scaled_scores": { + "r2": -0.9055 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 873, + "cpu_pct": 101, + "peak_memory_mb": 22119, + "disk_read_mb": 700, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0587 + }, + "scaled_scores": { + "r2": 0.489 + }, + "mean_score": 0.489, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 481, + "cpu_pct": 100.2, + "peak_memory_mb": 15360, + "disk_read_mb": 719, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "tangram", + "metric_values": { + "r2": -1.373 + }, + "scaled_scores": { + "r2": -0.2882 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 70, + "cpu_pct": 1132.7, + "peak_memory_mb": 9421, + "disk_read_mb": 730, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2.2, + "cpu_pct": 419.6, + "peak_memory_mb": 4199, + "disk_read_mb": 665, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/dkd", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.9833 + }, + "scaled_scores": { + "r2": -0.0766 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 21.8, + "cpu_pct": 1321, + "peak_memory_mb": 2765, + "disk_read_mb": 673, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "cell2location", + "metric_values": { + "r2": -0.0006 + }, + "scaled_scores": { + "r2": 0.3556 + }, + "mean_score": 0.3556, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3228, + "cpu_pct": 784.6, + "peak_memory_mb": 10855, + "disk_read_mb": 1639, + "disk_write_mb": 13 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "destvi", + "metric_values": { + "r2": 0.0814 + }, + "scaled_scores": { + "r2": 0.4084 + }, + "mean_score": 0.4084, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 16288, + "cpu_pct": 100.7, + "peak_memory_mb": 16896, + "disk_read_mb": 1536, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "nmfreg", + "metric_values": { + "r2": -0.7907 + }, + "scaled_scores": { + "r2": -0.1533 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 844, + "cpu_pct": 105, + "peak_memory_mb": 14644, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "nnls", + "metric_values": { + "r2": -0.4479 + }, + "scaled_scores": { + "r2": 0.0675 + }, + "mean_score": 0.0675, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 13, + "cpu_pct": 499.9, + "peak_memory_mb": 5632, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.5527 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5.7, + "cpu_pct": 93.3, + "peak_memory_mb": 2970, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "rctd", + "metric_values": { + "r2": 0.2005 + }, + "scaled_scores": { + "r2": 0.4851 + }, + "mean_score": 0.4851, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 728, + "cpu_pct": 69.2, + "peak_memory_mb": 59085, + "disk_read_mb": 1844, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "seurat", + "metric_values": { + "r2": -3.4424 + }, + "scaled_scores": { + "r2": -1.8611 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2903, + "cpu_pct": 99.9, + "peak_memory_mb": 76186, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0776 + }, + "scaled_scores": { + "r2": 0.4059 + }, + "mean_score": 0.4059, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2623, + "cpu_pct": 100.5, + "peak_memory_mb": 20480, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "tangram", + "metric_values": { + "r2": -1.1092 + }, + "scaled_scores": { + "r2": -0.3584 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 520, + "cpu_pct": 1190.8, + "peak_memory_mb": 17408, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 8.7, + "cpu_pct": 100.6, + "peak_memory_mb": 5018, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/gtex_v9", + "method_id": "vanillanmf", + "metric_values": { + "r2": -1.6403 + }, + "scaled_scores": { + "r2": -0.7005 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 76, + "cpu_pct": 592.2, + "peak_memory_mb": 5632, + "disk_read_mb": 1536, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "cell2location", + "metric_values": { + "r2": -0.1785 + }, + "scaled_scores": { + "r2": 0.2609 + }, + "mean_score": 0.2609, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3455, + "cpu_pct": 1588, + "peak_memory_mb": 24372, + "disk_read_mb": 8909, + "disk_write_mb": 13 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "destvi", + "metric_values": { + "r2": "NA" + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 143, + "duration_sec": 28801, + "cpu_pct": "NA", + "peak_memory_mb": "NA", + "disk_read_mb": "NA", + "disk_write_mb": "NA" + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "nmfreg", + "metric_values": { + "r2": -2.9522 + }, + "scaled_scores": { + "r2": -1.4786 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 7447, + "cpu_pct": 100.3, + "peak_memory_mb": 66970, + "disk_read_mb": 8807, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "nnls", + "metric_values": { + "r2": -0.9785 + }, + "scaled_scores": { + "r2": -0.2408 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 27.1, + "cpu_pct": 275.2, + "peak_memory_mb": 17306, + "disk_read_mb": 8704, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.5945 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 24, + "cpu_pct": 68.9, + "peak_memory_mb": 12288, + "disk_read_mb": 8704, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "rctd", + "metric_values": { + "r2": -0.1235 + }, + "scaled_scores": { + "r2": 0.2954 + }, + "mean_score": 0.2954, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 1132, + "cpu_pct": 82.8, + "peak_memory_mb": 174490, + "disk_read_mb": 9114, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "seurat", + "metric_values": { + "r2": -1.6325 + }, + "scaled_scores": { + "r2": -0.651 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 10671, + "cpu_pct": 100.2, + "peak_memory_mb": 306279, + "disk_read_mb": 8807, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0418 + }, + "scaled_scores": { + "r2": 0.3991 + }, + "mean_score": 0.3991, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 7138, + "cpu_pct": 100.1, + "peak_memory_mb": 23450, + "disk_read_mb": 8807, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "tangram", + "metric_values": { + "r2": -1.0983 + }, + "scaled_scores": { + "r2": -0.3159 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 1363, + "cpu_pct": 842, + "peak_memory_mb": 42599, + "disk_read_mb": 8807, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 16, + "cpu_pct": 95.2, + "peak_memory_mb": 12288, + "disk_read_mb": 8704, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hcla", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.1836 + }, + "scaled_scores": { + "r2": 0.2577 + }, + "mean_score": 0.2577, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 35.6, + "cpu_pct": 925.3, + "peak_memory_mb": 16692, + "disk_read_mb": 8807, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "cell2location", + "metric_values": { + "r2": 0.5583 + }, + "scaled_scores": { + "r2": 0.8529 + }, + "mean_score": 0.8529, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3902, + "cpu_pct": 1965.9, + "peak_memory_mb": 27648, + "disk_read_mb": 6452, + "disk_write_mb": 13 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "destvi", + "metric_values": { + "r2": "NA" + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 143, + "duration_sec": 28811, + "cpu_pct": "NA", + "peak_memory_mb": "NA", + "disk_read_mb": "NA", + "disk_write_mb": "NA" + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.3546 + }, + "scaled_scores": { + "r2": 0.2161 + }, + "mean_score": 0.2161, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5121, + "cpu_pct": 101, + "peak_memory_mb": 51098, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "nnls", + "metric_values": { + "r2": 0.1169 + }, + "scaled_scores": { + "r2": 0.706 + }, + "mean_score": 0.706, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 22.5, + "cpu_pct": 163, + "peak_memory_mb": 18740, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "random_proportions", + "metric_values": { + "r2": -2.0036 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 11.6, + "cpu_pct": 111.3, + "peak_memory_mb": 9216, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "rctd", + "metric_values": { + "r2": 0.5427 + }, + "scaled_scores": { + "r2": 0.8478 + }, + "mean_score": 0.8478, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 763, + "cpu_pct": 80.2, + "peak_memory_mb": 159949, + "disk_read_mb": 6759, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "seurat", + "metric_values": { + "r2": -1.594 + }, + "scaled_scores": { + "r2": 0.1364 + }, + "mean_score": 0.1364, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 8824, + "cpu_pct": 100.2, + "peak_memory_mb": 196404, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.1387 + }, + "scaled_scores": { + "r2": 0.7132 + }, + "mean_score": 0.7132, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 7269, + "cpu_pct": 100.1, + "peak_memory_mb": 21197, + "disk_read_mb": 6452, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "tangram", + "metric_values": { + "r2": -2.3183 + }, + "scaled_scores": { + "r2": -0.1048 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 727, + "cpu_pct": 1483.1, + "peak_memory_mb": 32052, + "disk_read_mb": 6452, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 12.4, + "cpu_pct": 113.1, + "peak_memory_mb": 9933, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/hypomap", + "method_id": "vanillanmf", + "metric_values": { + "r2": -1.0822 + }, + "scaled_scores": { + "r2": 0.3068 + }, + "mean_score": 0.3068, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 34.3, + "cpu_pct": 1669.1, + "peak_memory_mb": 23143, + "disk_read_mb": 6349, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "cell2location", + "metric_values": { + "r2": -0.0525 + }, + "scaled_scores": { + "r2": 0.2079 + }, + "mean_score": 0.2079, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3052, + "cpu_pct": 1932.5, + "peak_memory_mb": 20992, + "disk_read_mb": 5018, + "disk_write_mb": 11 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "destvi", + "metric_values": { + "r2": -0.9322 + }, + "scaled_scores": { + "r2": -0.4542 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 24795, + "cpu_pct": 101.3, + "peak_memory_mb": 24679, + "disk_read_mb": 4916, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.0756 + }, + "scaled_scores": { + "r2": -0.5621 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3441, + "cpu_pct": 100.9, + "peak_memory_mb": 40141, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "nnls", + "metric_values": { + "r2": -2.054 + }, + "scaled_scores": { + "r2": -1.2984 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 17.1, + "cpu_pct": 320.7, + "peak_memory_mb": 10036, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.3287 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 13, + "cpu_pct": 95, + "peak_memory_mb": 8397, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "rctd", + "metric_values": { + "r2": -0.7704 + }, + "scaled_scores": { + "r2": -0.3324 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 816, + "cpu_pct": 81.3, + "peak_memory_mb": 98816, + "disk_read_mb": 5325, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "seurat", + "metric_values": { + "r2": -2.8999 + }, + "scaled_scores": { + "r2": -1.9351 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5801, + "cpu_pct": 100.3, + "peak_memory_mb": 152884, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0196 + }, + "scaled_scores": { + "r2": 0.2621 + }, + "mean_score": 0.2621, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 4031, + "cpu_pct": 99.8, + "peak_memory_mb": 23860, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "tangram", + "metric_values": { + "r2": -0.8396 + }, + "scaled_scores": { + "r2": -0.3845 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 655, + "cpu_pct": 924.6, + "peak_memory_mb": 26010, + "disk_read_mb": 4916, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 8.5, + "cpu_pct": 147, + "peak_memory_mb": 8397, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/immune_cell_atlas", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.1929 + }, + "scaled_scores": { + "r2": 0.1022 + }, + "mean_score": 0.1022, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 25.1, + "cpu_pct": 937, + "peak_memory_mb": 10138, + "disk_read_mb": 4916, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "cell2location", + "metric_values": { + "r2": 0.1468 + }, + "scaled_scores": { + "r2": 0.5045 + }, + "mean_score": 0.5045, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3257, + "cpu_pct": 1457.4, + "peak_memory_mb": 22631, + "disk_read_mb": 6759, + "disk_write_mb": 13 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "destvi", + "metric_values": { + "r2": -0.3556 + }, + "scaled_scores": { + "r2": 0.2127 + }, + "mean_score": 0.2127, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 20789, + "cpu_pct": 101, + "peak_memory_mb": 26215, + "disk_read_mb": 6656, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "nmfreg", + "metric_values": { + "r2": -0.4976 + }, + "scaled_scores": { + "r2": 0.1302 + }, + "mean_score": 0.1302, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5057, + "cpu_pct": 100.8, + "peak_memory_mb": 53146, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "nnls", + "metric_values": { + "r2": -0.9455 + }, + "scaled_scores": { + "r2": -0.13 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 20.4, + "cpu_pct": 196.8, + "peak_memory_mb": 15975, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.7217 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 13.7, + "cpu_pct": 98.9, + "peak_memory_mb": 10138, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "rctd", + "metric_values": { + "r2": -0.4137 + }, + "scaled_scores": { + "r2": 0.1789 + }, + "mean_score": 0.1789, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 614, + "cpu_pct": 77.1, + "peak_memory_mb": 87655, + "disk_read_mb": 7066, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "seurat", + "metric_values": { + "r2": -5.9876 + }, + "scaled_scores": { + "r2": -3.0585 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5620, + "cpu_pct": 100.3, + "peak_memory_mb": 184320, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0408 + }, + "scaled_scores": { + "r2": 0.4429 + }, + "mean_score": 0.4429, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3205, + "cpu_pct": 100.8, + "peak_memory_mb": 32564, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "tangram", + "metric_values": { + "r2": -2.2135 + }, + "scaled_scores": { + "r2": -0.8664 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 444, + "cpu_pct": 977.8, + "peak_memory_mb": 33383, + "disk_read_mb": 6656, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 11.5, + "cpu_pct": 111.4, + "peak_memory_mb": 9524, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/mouse_pancreas_atlas", + "method_id": "vanillanmf", + "metric_values": { + "r2": 0.1789 + }, + "scaled_scores": { + "r2": 0.5231 + }, + "mean_score": 0.5231, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 22.8, + "cpu_pct": 302, + "peak_memory_mb": 18125, + "disk_read_mb": 6656, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "cell2location", + "metric_values": { + "r2": -5.0765 + }, + "scaled_scores": { + "r2": -3.4575 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 6661, + "cpu_pct": 1384.1, + "peak_memory_mb": 24372, + "disk_read_mb": 9831, + "disk_write_mb": 14 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "destvi", + "metric_values": { + "r2": "NA" + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 143, + "duration_sec": 28801, + "cpu_pct": "NA", + "peak_memory_mb": "NA", + "disk_read_mb": "NA", + "disk_write_mb": "NA" + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "nmfreg", + "metric_values": { + "r2": -3.3984 + }, + "scaled_scores": { + "r2": -2.2265 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 6617, + "cpu_pct": 100.8, + "peak_memory_mb": 76084, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "nnls", + "metric_values": { + "r2": -4.9846 + }, + "scaled_scores": { + "r2": -3.3901 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 42.7, + "cpu_pct": 1382, + "peak_memory_mb": 15872, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.3632 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 16.9, + "cpu_pct": 96, + "peak_memory_mb": 13210, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "rctd", + "metric_values": { + "r2": "NA" + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 1, + "duration_sec": 250, + "cpu_pct": "NA", + "peak_memory_mb": "NA", + "disk_read_mb": "NA", + "disk_write_mb": "NA" + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "seurat", + "metric_values": { + "r2": -3.4867 + }, + "scaled_scores": { + "r2": -2.2913 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 13647, + "cpu_pct": 100.1, + "peak_memory_mb": 267367, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "stereoscope", + "metric_values": { + "r2": -0.0208 + }, + "scaled_scores": { + "r2": 0.2512 + }, + "mean_score": 0.2512, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 17284, + "cpu_pct": 100.2, + "peak_memory_mb": 29082, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "tangram", + "metric_values": { + "r2": -1.3411 + }, + "scaled_scores": { + "r2": -0.7173 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2590, + "cpu_pct": 960.9, + "peak_memory_mb": 56423, + "disk_read_mb": 9728, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 16.1, + "cpu_pct": 96.4, + "peak_memory_mb": 13210, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.0813 + }, + "scaled_scores": { + "r2": 0.2068 + }, + "mean_score": 0.2068, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 38.5, + "cpu_pct": 953.5, + "peak_memory_mb": 15975, + "disk_read_mb": 9728, + "disk_write_mb": 3 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "cell2location", + "metric_values": { + "r2": -0.7173 + }, + "scaled_scores": { + "r2": -0.4653 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2744, + "cpu_pct": 1945.6, + "peak_memory_mb": 19354, + "disk_read_mb": 496, + "disk_write_mb": 11 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "destvi", + "metric_values": { + "r2": -0.5461 + }, + "scaled_scores": { + "r2": -0.3193 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 7149, + "cpu_pct": 112.9, + "peak_memory_mb": 28468, + "disk_read_mb": 438, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.9976 + }, + "scaled_scores": { + "r2": -1.5579 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 126, + "cpu_pct": 133, + "peak_memory_mb": 6247, + "disk_read_mb": 393, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "nnls", + "metric_values": { + "r2": -0.908 + }, + "scaled_scores": { + "r2": -0.6281 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 7.6, + "cpu_pct": 2372.4, + "peak_memory_mb": 4096, + "disk_read_mb": 383, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.1719 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 421.9, + "peak_memory_mb": 1741, + "disk_read_mb": 383, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "rctd", + "metric_values": { + "r2": -0.5507 + }, + "scaled_scores": { + "r2": -0.3232 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 935, + "cpu_pct": 29.3, + "peak_memory_mb": 22836, + "disk_read_mb": 784, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "seurat", + "metric_values": { + "r2": -2.3645 + }, + "scaled_scores": { + "r2": -1.871 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 1467, + "cpu_pct": 100, + "peak_memory_mb": 35021, + "disk_read_mb": 419, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0884 + }, + "scaled_scores": { + "r2": 0.2221 + }, + "mean_score": 0.2221, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 1060, + "cpu_pct": 101.5, + "peak_memory_mb": 18637, + "disk_read_mb": 438, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "tangram", + "metric_values": { + "r2": -0.6944 + }, + "scaled_scores": { + "r2": -0.4459 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 364, + "cpu_pct": 1540.1, + "peak_memory_mb": 13005, + "disk_read_mb": 449, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2.2, + "cpu_pct": 367.6, + "peak_memory_mb": 3892, + "disk_read_mb": 383, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/cengen", + "method_id": "vanillanmf", + "metric_values": { + "r2": 0.0452 + }, + "scaled_scores": { + "r2": 0.1853 + }, + "mean_score": 0.1853, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 14.2, + "cpu_pct": 1691.7, + "peak_memory_mb": 3482, + "disk_read_mb": 392, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "cell2location", + "metric_values": { + "r2": -0.0635 + }, + "scaled_scores": { + "r2": 0.4923 + }, + "mean_score": 0.4923, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2101, + "cpu_pct": 1939.5, + "peak_memory_mb": 16077, + "disk_read_mb": 530, + "disk_write_mb": 10 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "destvi", + "metric_values": { + "r2": -2.3364 + }, + "scaled_scores": { + "r2": -0.5927 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2616, + "cpu_pct": 101.8, + "peak_memory_mb": 20173, + "disk_read_mb": 472, + "disk_write_mb": 5 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.3268 + }, + "scaled_scores": { + "r2": -0.1107 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 252, + "cpu_pct": 117.4, + "peak_memory_mb": 6554, + "disk_read_mb": 427, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "nnls", + "metric_values": { + "r2": -2.5906 + }, + "scaled_scores": { + "r2": -0.714 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 21.1, + "cpu_pct": 134.4, + "peak_memory_mb": 77, + "disk_read_mb": 416, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "random_proportions", + "metric_values": { + "r2": -1.0948 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3.2, + "cpu_pct": 313, + "peak_memory_mb": 3892, + "disk_read_mb": 417, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "rctd", + "metric_values": { + "r2": -2.7278 + }, + "scaled_scores": { + "r2": -0.7795 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 196, + "cpu_pct": 50.3, + "peak_memory_mb": 9728, + "disk_read_mb": 817, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "seurat", + "metric_values": { + "r2": -1.9947 + }, + "scaled_scores": { + "r2": -0.4296 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 753, + "cpu_pct": 101.1, + "peak_memory_mb": 17306, + "disk_read_mb": 452, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0036 + }, + "scaled_scores": { + "r2": 0.5244 + }, + "mean_score": 0.5244, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 238, + "cpu_pct": 115.5, + "peak_memory_mb": 26215, + "disk_read_mb": 472, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "tangram", + "metric_values": { + "r2": -1.471 + }, + "scaled_scores": { + "r2": -0.1796 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 63, + "cpu_pct": 1452.4, + "peak_memory_mb": 9216, + "disk_read_mb": 482, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 424.1, + "peak_memory_mb": 1741, + "disk_read_mb": 417, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/immune_cells", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.2135 + }, + "scaled_scores": { + "r2": 0.4207 + }, + "mean_score": 0.4207, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5.2, + "cpu_pct": 1454.7, + "peak_memory_mb": 4301, + "disk_read_mb": 426, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "cell2location", + "metric_values": { + "r2": -1.6758 + }, + "scaled_scores": { + "r2": -0.2627 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2358, + "cpu_pct": 1543.3, + "peak_memory_mb": 20480, + "disk_read_mb": 561, + "disk_write_mb": 11 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "destvi", + "metric_values": { + "r2": -0.7201 + }, + "scaled_scores": { + "r2": 0.1883 + }, + "mean_score": 0.1883, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2205, + "cpu_pct": 100.7, + "peak_memory_mb": 15565, + "disk_read_mb": 503, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.1982 + }, + "scaled_scores": { + "r2": -0.0373 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 340, + "cpu_pct": 109.6, + "peak_memory_mb": 6144, + "disk_read_mb": 458, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "nnls", + "metric_values": { + "r2": -2.0492 + }, + "scaled_scores": { + "r2": -0.4389 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 6.7, + "cpu_pct": 328.8, + "peak_memory_mb": 3789, + "disk_read_mb": 448, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "random_proportions", + "metric_values": { + "r2": -1.1191 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 380.2, + "peak_memory_mb": 1434, + "disk_read_mb": 448, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "rctd", + "metric_values": { + "r2": -1.2913 + }, + "scaled_scores": { + "r2": -0.0813 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 180, + "cpu_pct": 47.3, + "peak_memory_mb": 9728, + "disk_read_mb": 848, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "seurat", + "metric_values": { + "r2": -2.208 + }, + "scaled_scores": { + "r2": -0.5138 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 544, + "cpu_pct": 101.9, + "peak_memory_mb": 13210, + "disk_read_mb": 484, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0469 + }, + "scaled_scores": { + "r2": 0.5502 + }, + "mean_score": 0.5502, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 159, + "cpu_pct": 99.8, + "peak_memory_mb": 18944, + "disk_read_mb": 503, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "tangram", + "metric_values": { + "r2": -1.6281 + }, + "scaled_scores": { + "r2": -0.2402 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 49.4, + "cpu_pct": 882.1, + "peak_memory_mb": 8090, + "disk_read_mb": 513, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 381.1, + "peak_memory_mb": 1434, + "disk_read_mb": 448, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/pancreas", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.86 + }, + "scaled_scores": { + "r2": 0.1223 + }, + "mean_score": 0.1223, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 5.7, + "cpu_pct": 1512.8, + "peak_memory_mb": 4506, + "disk_read_mb": 457, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "cell2location", + "metric_values": { + "r2": 0.0162 + }, + "scaled_scores": { + "r2": 0.43 + }, + "mean_score": 0.43, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3058, + "cpu_pct": 1814.9, + "peak_memory_mb": 16589, + "disk_read_mb": 515, + "disk_write_mb": 11 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "destvi", + "metric_values": { + "r2": -0.1616 + }, + "scaled_scores": { + "r2": 0.3269 + }, + "mean_score": 0.3269, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3179, + "cpu_pct": 104.3, + "peak_memory_mb": 27853, + "disk_read_mb": 457, + "disk_write_mb": 6 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "nmfreg", + "metric_values": { + "r2": -1.8065 + }, + "scaled_scores": { + "r2": -0.6262 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 259, + "cpu_pct": 176.8, + "peak_memory_mb": 8500, + "disk_read_mb": 412, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "nnls", + "metric_values": { + "r2": -1.2217 + }, + "scaled_scores": { + "r2": -0.2873 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 3.7, + "cpu_pct": 1302.9, + "peak_memory_mb": 4199, + "disk_read_mb": 401, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "random_proportions", + "metric_values": { + "r2": -0.7259 + }, + "scaled_scores": { + "r2": 0 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 462.3, + "peak_memory_mb": 1741, + "disk_read_mb": 403, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "rctd", + "metric_values": { + "r2": -0.2542 + }, + "scaled_scores": { + "r2": 0.2733 + }, + "mean_score": 0.2733, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 260, + "cpu_pct": 49.7, + "peak_memory_mb": 12596, + "disk_read_mb": 803, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "seurat", + "metric_values": { + "r2": -3.6839 + }, + "scaled_scores": { + "r2": -1.7139 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 602, + "cpu_pct": 102.6, + "peak_memory_mb": 18330, + "disk_read_mb": 438, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "stereoscope", + "metric_values": { + "r2": 0.0091 + }, + "scaled_scores": { + "r2": 0.4258 + }, + "mean_score": 0.4258, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 357, + "cpu_pct": 99.6, + "peak_memory_mb": 19968, + "disk_read_mb": 457, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "tangram", + "metric_values": { + "r2": -0.8411 + }, + "scaled_scores": { + "r2": -0.0668 + }, + "mean_score": 0, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 61, + "cpu_pct": 1342.6, + "peak_memory_mb": 9626, + "disk_read_mb": 467, + "disk_write_mb": 1 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "true_proportions", + "metric_values": { + "r2": 1 + }, + "scaled_scores": { + "r2": 1 + }, + "mean_score": 1, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 2, + "cpu_pct": 451.8, + "peak_memory_mb": 1741, + "disk_read_mb": 403, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "method_id": "vanillanmf", + "metric_values": { + "r2": -0.5034 + }, + "scaled_scores": { + "r2": 0.1289 + }, + "mean_score": 0.1289, + "normalization_id": "log_cp10k", + "resources": { + "exit_code": 0, + "duration_sec": 12.7, + "cpu_pct": 2409, + "peak_memory_mb": 4199, + "disk_read_mb": 411, + "disk_write_mb": 2 + }, + "task_id": "spatial_decomposition" + } +] diff --git a/results/spatial_decomposition/data/state.yaml b/results/spatial_decomposition/data/state.yaml new file mode 100644 index 000000000..abbb0fc14 --- /dev/null +++ b/results/spatial_decomposition/data/state.yaml @@ -0,0 +1,9 @@ +id: process +output_scores: !file results.json +output_method_info: !file method_info.json +output_metric_info: !file metric_info.json +output_dataset_info: !file dataset_info.json +output_task_info: !file task_info.json +output_qc: !file quality_control.json +output_metric_execution_info: !file metric_execution_info.json + diff --git a/results/spatial_decomposition/data/task_info.json b/results/spatial_decomposition/data/task_info.json index 8355f5e0c..e490bb948 100644 --- a/results/spatial_decomposition/data/task_info.json +++ b/results/spatial_decomposition/data/task_info.json @@ -1,8 +1,8 @@ { - "task_id": "spatial_decomposition", - "commit_sha": "c97decf07adb2e3050561d6fa9ae46132be07bef", - "task_name": "Spatial Decomposition", - "task_summary": "Calling cell-type compositions for spot-based spatial transcriptomics data", - "task_description": "\nSpatial decomposition (also often referred to as Spatial deconvolution) is\napplicable to spatial transcriptomics data where the transcription profile of\neach capture location (spot, voxel, bead, etc.) do not share a bijective\nrelationship with the cells in the tissue, i.e., multiple cells may contribute\nto the same capture location. The task of spatial decomposition then refers to\nestimating the composition of cell types/states that are present at each capture\nlocation. The cell type/states estimates are presented as proportion values,\nrepresenting the proportion of the cells at each capture location that belong to\na given cell type.\n\nWe distinguish between _reference-based_ decomposition and _de novo_\ndecomposition, where the former leverage external data (e.g., scRNA-seq or\nscNuc-seq) to guide the inference process, while the latter only work with the\nspatial data. We require that all datasets have an associated reference single\ncell data set, but methods are free to ignore this information.\n\n", - "repo": "openproblems-bio/openproblems" -} \ No newline at end of file + "task_id": "spatial_decomposition", + "commit_sha": null, + "task_name": "Spatial decomposition", + "task_summary": "Estimation of cell type proportions per spot in 2D space from spatial transcriptomic data coupled with corresponding single-cell data", + "task_description": "Spatial decomposition (also often referred to as Spatial deconvolution) is applicable to spatial transcriptomics data where the transcription profile of each capture location (spot, voxel, bead, etc.) do not share a bijective relationship with the cells in the tissue, i.e., multiple cells may contribute to the same capture location. The task of spatial decomposition then refers to estimating the composition of cell types/states that are present at each capture location. The cell type/states estimates are presented as proportion values, representing the proportion of the cells at each capture location that belong to a given cell type.\n\n\nWe distinguish between _reference-based_ decomposition and _de novo_ decomposition, where the former leverage external data (e.g., scRNA-seq or scNuc-seq) to guide the inference process, while the latter only work with the spatial data. We require that all datasets have an associated reference single cell data set, but methods are free to ignore this information. \nDue to the lack of real datasets with the necessary ground-truth, this task makes use of a simulated dataset generated by creating cell-aggregates by sampling from a Dirichlet distribution. The ground-truth dataset consists of the spatial expression matrix, XY coordinates of the spots, true cell-type proportions for each spot, and the reference single-cell data (from which cell aggregated were simulated).\n", + "repo": "openproblems-bio/openproblems-v2" +} From 9ea7647b8ae78475faee648995a927c290c4da61 Mon Sep 17 00:00:00 2001 From: Nirmayi Date: Fri, 22 Nov 2024 10:45:16 +0100 Subject: [PATCH 2/2] update results --- .../data/dataset_info.json | 137 +- .../data/method_info.json | 102 +- .../data/metric_execution_info.json | 986 ++++---- .../data/metric_info.json | 10 +- .../data/quality_control.json | 638 ++--- .../spatial_decomposition/data/results.json | 2129 +++++++---------- .../spatial_decomposition/data/task_info.json | 33 +- 7 files changed, 1686 insertions(+), 2349 deletions(-) diff --git a/results/spatial_decomposition/data/dataset_info.json b/results/spatial_decomposition/data/dataset_info.json index 113a646cb..530412e10 100644 --- a/results/spatial_decomposition/data/dataset_info.json +++ b/results/spatial_decomposition/data/dataset_info.json @@ -1,123 +1,102 @@ [ { - "task_id": "spatial_decomposition", + "dataset_id": "cellxgene_census/hypomap", + "dataset_name": "HypoMap", + "dataset_summary": "A unified single cell gene expression atlas of the murine hypothalamus", + "dataset_description": "The hypothalamus plays a key role in coordinating fundamental body functions. Despite recent progress in single-cell technologies, a unified catalogue and molecular characterization of the heterogeneous cell types and, specifically, neuronal subtypes in this brain region are still lacking. Here we present an integrated reference atlas “HypoMap” of the murine hypothalamus consisting of 384,925 cells, with the ability to incorporate new additional experiments. We validate HypoMap by comparing data collected from SmartSeq2 and bulk RNA sequencing of selected neuronal cell types with different degrees of cellular heterogeneity.", + "data_reference": "steuernagel2022hypomap", + "data_url": "https://cellxgene.cziscience.com/collections/d86517f0-fa7e-4266-b82e-a521350d6d36", + "date_created": "20-11-2024", + "file_size": 23918812 + }, + { + "dataset_id": "openproblems_v1/cengen", + "dataset_name": "CeNGEN", + "dataset_summary": "Complete Gene Expression Map of an Entire Nervous System", + "dataset_description": "100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics.", + "data_reference": "hammarlund2018cengen", + "data_url": "https://www.cengen.org", + "date_created": "20-11-2024", + "file_size": 14702268 + }, + { + "dataset_id": "openproblems_v1/zebrafish", + "dataset_name": "Zebrafish embryonic cells", + "dataset_summary": "Single-cell mRNA sequencing of zebrafish embryonic cells.", + "dataset_description": "90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene.", + "data_reference": "wagner2018single", + "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112294", + "date_created": "20-11-2024", + "file_size": 18701772 + }, + { + "dataset_id": "openproblems_v1/pancreas", + "dataset_name": "Human pancreas", + "dataset_summary": "Human pancreas cells dataset from the scIB benchmarks", + "dataset_description": "Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq).", + "data_reference": "luecken2022benchmarking", + "data_url": "https://theislab.github.io/scib-reproducibility/dataset_pancreas.html", + "date_created": "20-11-2024", + "file_size": 19238812 + }, + { "dataset_id": "cellxgene_census/gtex_v9", "dataset_name": "GTEX v9", "dataset_summary": "Single-nucleus cross-tissue molecular reference maps to decipher disease gene function", "dataset_description": "Understanding the function of genes and their regulation in tissue homeostasis and disease requires knowing the cellular context in which genes are expressed in tissues across the body. Single cell genomics allows the generation of detailed cellular atlases in human tissues, but most efforts are focused on single tissue types. Here, we establish a framework for profiling multiple tissues across the human body at single-cell resolution using single nucleus RNA-Seq (snRNA-seq), and apply it to 8 diverse, archived, frozen tissue types (three donors per tissue). We apply four snRNA-seq methods to each of 25 samples from 16 donors, generating a cross-tissue atlas of 209,126 nuclei profiles, and benchmark them vs. scRNA-seq of comparable fresh tissues. We use a conditional variational autoencoder (cVAE) to integrate an atlas across tissues, donors, and laboratory methods. We highlight shared and tissue-specific features of tissue-resident immune cells, identifying tissue-restricted and non-restricted resident myeloid populations. These include a cross-tissue conserved dichotomy between LYVE1- and HLA class II-expressing macrophages, and the broad presence of LAM-like macrophages across healthy tissues that is also observed in disease. For rare, monogenic muscle diseases, we identify cell types that likely underlie the neuromuscular, metabolic, and immune components of these diseases, and biological processes involved in their pathology. For common complex diseases and traits analyzed by GWAS, we identify the cell types and gene modules that potentially underlie disease mechanisms. The experimental and analytical frameworks we describe will enable the generation of large-scale studies of how cellular and molecular processes vary across individuals and populations.", "data_reference": "eraslan2022singlenucleus", "data_url": "https://cellxgene.cziscience.com/collections/a3ffde6c-7ad2-498a-903c-d58e732f7470", - "date_created": "28-06-2024", - "file_size": 3003208 - }, - { - "task_id": "spatial_decomposition", - "dataset_id": "cellxgene_census/dkd", - "dataset_name": "Diabetic Kidney Disease", - "dataset_summary": "Multimodal single cell sequencing implicates chromatin accessibility and genetic background in diabetic kidney disease progression", - "dataset_description": "Multimodal single cell sequencing is a powerful tool for interrogating cell-specific changes in transcription and chromatin accessibility. We performed single nucleus RNA (snRNA-seq) and assay for transposase accessible chromatin sequencing (snATAC-seq) on human kidney cortex from donors with and without diabetic kidney disease (DKD) to identify altered signaling pathways and transcription factors associated with DKD. Both snRNA-seq and snATAC-seq had an increased proportion of VCAM1+ injured proximal tubule cells (PT_VCAM1) in DKD samples. PT_VCAM1 has a pro-inflammatory expression signature and transcription factor motif enrichment implicated NFkB signaling. We used stratified linkage disequilibrium score regression to partition heritability of kidney-function-related traits using publicly-available GWAS summary statistics. Cell-specific PT_VCAM1 peaks were enriched for heritability of chronic kidney disease (CKD), suggesting that genetic background may regulate chromatin accessibility and DKD progression. snATAC-seq found cell-specific differentially accessible regions (DAR) throughout the nephron that change accessibility in DKD and these regions were enriched for glucocorticoid receptor (GR) motifs. Changes in chromatin accessibility were associated with decreased expression of insulin receptor, increased gluconeogenesis, and decreased expression of the GR cytosolic chaperone, FKBP5, in the diabetic proximal tubule. Cleavage under targets and release using nuclease (CUT&RUN) profiling of GR binding in bulk kidney cortex and an in vitro model of the proximal tubule (RPTEC) showed that DAR co-localize with GR binding sites. CRISPRi silencing of GR response elements (GRE) in the FKBP5 gene body reduced FKBP5 expression in RPTEC, suggesting that reduced FKBP5 chromatin accessibility in DKD may alter cellular response to GR. We developed an open-source tool for single cell allele specific analysis (SALSA) to model the effect of genetic background on gene expression. Heterozygous germline single nucleotide variants (SNV) in proximal tubule ATAC peaks were associated with allele-specific chromatin accessibility and differential expression of target genes within cis-coaccessibility networks. Partitioned heritability of proximal tubule ATAC peaks with a predicted allele-specific effect was enriched for eGFR, suggesting that genetic background may modify DKD progression in a cell-specific manner.", - "data_reference": "wilson2022multimodal", - "data_url": "https://cellxgene.cziscience.com/collections/b3e2c6e3-9b05-4da9-8f42-da38a664b45b", - "date_created": "28-06-2024", - "file_size": 2766040 + "date_created": "20-11-2024", + "file_size": 25202492 }, { - "task_id": "spatial_decomposition", "dataset_id": "openproblems_v1/immune_cells", "dataset_name": "Human immune", "dataset_summary": "Human immune cells dataset from the scIB benchmarks", "dataset_description": "Human immune cells from peripheral blood and bone marrow taken from 5 datasets comprising 10 batches across technologies (10X, Smart-seq2).", "data_reference": "luecken2022benchmarking", "data_url": "https://theislab.github.io/scib-reproducibility/dataset_immune_cell_hum.html", - "date_created": "28-06-2024", - "file_size": 1398520 - }, - { - "task_id": "spatial_decomposition", - "dataset_id": "cellxgene_census/hcla", - "dataset_name": "Human Lung Cell Atlas", - "dataset_summary": "An integrated cell atlas of the human lung in health and disease (core)", - "dataset_description": "The integrated Human Lung Cell Atlas (HLCA) represents the first large-scale, integrated single-cell reference atlas of the human lung. It consists of over 2 million cells from the respiratory tract of 486 individuals, and includes 49 different datasets. It is split into the HLCA core, and the extended or full HLCA. The HLCA core includes data of healthy lung tissue from 107 individuals, and includes manual cell type annotations based on consensus across 6 independent experts, as well as demographic, biological and technical metadata.", - "data_reference": "sikkema2023integrated", - "data_url": "https://cellxgene.cziscience.com/collections/6f6d381a-7701-4781-935c-db10d30de293", - "date_created": "28-06-2024", - "file_size": 2463000 - }, - { - "task_id": "spatial_decomposition", - "dataset_id": "openproblems_v1/pancreas", - "dataset_name": "Human pancreas", - "dataset_summary": "Human pancreas cells dataset from the scIB benchmarks", - "dataset_description": "Human pancreatic islet scRNA-seq data from 6 datasets across technologies (CEL-seq, CEL-seq2, Smart-seq2, inDrop, Fluidigm C1, and SMARTER-seq).", - "data_reference": "luecken2022benchmarking", - "data_url": "https://theislab.github.io/scib-reproducibility/dataset_pancreas.html", - "date_created": "28-06-2024", - "file_size": 1962344 + "date_created": "20-11-2024", + "file_size": 13412908 }, { - "task_id": "spatial_decomposition", "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "dataset_name": "Mouse Pancreatic Islet Atlas", "dataset_summary": "Mouse pancreatic islet scRNA-seq atlas across sexes, ages, and stress conditions including diabetes", "dataset_description": "To better understand pancreatic β-cell heterogeneity we generated a mouse pancreatic islet atlas capturing a wide range of biological conditions. The atlas contains scRNA-seq datasets of over 300,000 mouse pancreatic islet cells, of which more than 100,000 are β-cells, from nine datasets with 56 samples, including two previously unpublished datasets. The samples vary in sex, age (ranging from embryonic to aged), chemical stress, and disease status (including T1D NOD model development and two T2D models, mSTZ and db/db) together with different diabetes treatments. Additional information about data fields is available in anndata uns field 'field_descriptions' and on https://github.com/theislab/mm_pancreas_atlas_rep/blob/main/resources/cellxgene.md.", "data_reference": "hrovatin2023delineating", "data_url": "https://cellxgene.cziscience.com/collections/296237e2-393d-4e31-b590-b03f74ac5070", - "date_created": "28-06-2024", - "file_size": 2262488 - }, - { - "task_id": "spatial_decomposition", - "dataset_id": "cellxgene_census/hypomap", - "dataset_name": "HypoMap", - "dataset_summary": "A unified single cell gene expression atlas of the murine hypothalamus", - "dataset_description": "The hypothalamus plays a key role in coordinating fundamental body functions. Despite recent progress in single-cell technologies, a unified catalogue and molecular characterization of the heterogeneous cell types and, specifically, neuronal subtypes in this brain region are still lacking. Here we present an integrated reference atlas “HypoMap” of the murine hypothalamus consisting of 384,925 cells, with the ability to incorporate new additional experiments. We validate HypoMap by comparing data collected from SmartSeq2 and bulk RNA sequencing of selected neuronal cell types with different degrees of cellular heterogeneity.", - "data_reference": "steuernagel2022hypomap", - "data_url": "https://cellxgene.cziscience.com/collections/d86517f0-fa7e-4266-b82e-a521350d6d36", - "date_created": "28-06-2024", - "file_size": 3652072 + "date_created": "20-11-2024", + "file_size": 14454444 }, { - "task_id": "spatial_decomposition", - "dataset_id": "openproblems_v1/cengen", - "dataset_name": "CeNGEN", - "dataset_summary": "Complete Gene Expression Map of an Entire Nervous System", - "dataset_description": "100k FACS-isolated C. elegans neurons from 17 experiments sequenced on 10x Genomics.", - "data_reference": "hammarlund2018cengen", - "data_url": "https://www.cengen.org", - "date_created": "28-06-2024", - "file_size": 1944360 + "dataset_id": "cellxgene_census/dkd", + "dataset_name": "Diabetic Kidney Disease", + "dataset_summary": "Multimodal single cell sequencing implicates chromatin accessibility and genetic background in diabetic kidney disease progression", + "dataset_description": "Multimodal single cell sequencing is a powerful tool for interrogating cell-specific changes in transcription and chromatin accessibility. We performed single nucleus RNA (snRNA-seq) and assay for transposase accessible chromatin sequencing (snATAC-seq) on human kidney cortex from donors with and without diabetic kidney disease (DKD) to identify altered signaling pathways and transcription factors associated with DKD. Both snRNA-seq and snATAC-seq had an increased proportion of VCAM1+ injured proximal tubule cells (PT_VCAM1) in DKD samples. PT_VCAM1 has a pro-inflammatory expression signature and transcription factor motif enrichment implicated NFkB signaling. We used stratified linkage disequilibrium score regression to partition heritability of kidney-function-related traits using publicly-available GWAS summary statistics. Cell-specific PT_VCAM1 peaks were enriched for heritability of chronic kidney disease (CKD), suggesting that genetic background may regulate chromatin accessibility and DKD progression. snATAC-seq found cell-specific differentially accessible regions (DAR) throughout the nephron that change accessibility in DKD and these regions were enriched for glucocorticoid receptor (GR) motifs. Changes in chromatin accessibility were associated with decreased expression of insulin receptor, increased gluconeogenesis, and decreased expression of the GR cytosolic chaperone, FKBP5, in the diabetic proximal tubule. Cleavage under targets and release using nuclease (CUT&RUN) profiling of GR binding in bulk kidney cortex and an in vitro model of the proximal tubule (RPTEC) showed that DAR co-localize with GR binding sites. CRISPRi silencing of GR response elements (GRE) in the FKBP5 gene body reduced FKBP5 expression in RPTEC, suggesting that reduced FKBP5 chromatin accessibility in DKD may alter cellular response to GR. We developed an open-source tool for single cell allele specific analysis (SALSA) to model the effect of genetic background on gene expression. Heterozygous germline single nucleotide variants (SNV) in proximal tubule ATAC peaks were associated with allele-specific chromatin accessibility and differential expression of target genes within cis-coaccessibility networks. Partitioned heritability of proximal tubule ATAC peaks with a predicted allele-specific effect was enriched for eGFR, suggesting that genetic background may modify DKD progression in a cell-specific manner.", + "data_reference": "wilson2022multimodal", + "data_url": "https://cellxgene.cziscience.com/collections/b3e2c6e3-9b05-4da9-8f42-da38a664b45b", + "date_created": "20-11-2024", + "file_size": 23644620 }, { - "task_id": "spatial_decomposition", "dataset_id": "cellxgene_census/immune_cell_atlas", "dataset_name": "Immune Cell Atlas", "dataset_summary": "Cross-tissue immune cell analysis reveals tissue-specific features in humans", "dataset_description": "Despite their crucial role in health and disease, our knowledge of immune cells within human tissues remains limited. We surveyed the immune compartment of 16 tissues from 12 adult donors by single-cell RNA sequencing and VDJ sequencing generating a dataset of ~360,000 cells. To systematically resolve immune cell heterogeneity across tissues, we developed CellTypist, a machine learning tool for rapid and precise cell type annotation. Using this approach, combined with detailed curation, we determined the tissue distribution of finely phenotyped immune cell types, revealing hitherto unappreciated tissue-specific features and clonal architecture of T and B cells. Our multitissue approach lays the foundation for identifying highly resolved immune cell types by leveraging a common reference dataset, tissue-integrated expression analysis, and antigen receptor sequencing.", "data_reference": "dominguez2022crosstissue", "data_url": "https://cellxgene.cziscience.com/collections/62ef75e4-cbea-454e-a0ce-998ec40223d3", - "date_created": "28-06-2024", - "file_size": 2506312 - }, - { - "task_id": "spatial_decomposition", - "dataset_id": "openproblems_v1/zebrafish", - "dataset_name": "Zebrafish embryonic cells", - "dataset_summary": "Single-cell mRNA sequencing of zebrafish embryonic cells.", - "dataset_description": "90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene.", - "data_reference": "wagner2018single", - "data_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112294", - "date_created": "28-06-2024", - "file_size": 2553912 + "date_created": "20-11-2024", + "file_size": 17758524 }, { - "task_id": "spatial_decomposition", "dataset_id": "cellxgene_census/tabula_sapiens", "dataset_name": "Tabula Sapiens", "dataset_summary": "A multiple-organ, single-cell transcriptomic atlas of humans", "dataset_description": "Tabula Sapiens is a benchmark, first-draft human cell atlas of nearly 500,000 cells from 24 organs of 15 normal human subjects. This work is the product of the Tabula Sapiens Consortium. Taking the organs from the same individual controls for genetic background, age, environment, and epigenetic effects and allows detailed analysis and comparison of cell types that are shared between tissues. Our work creates a detailed portrait of cell types as well as their distribution and variation in gene expression across tissues and within the endothelial, epithelial, stromal and immune compartments.", "data_reference": "consortium2022tabula", "data_url": "https://cellxgene.cziscience.com/collections/e5f58829-1a66-40b5-a624-9046778e74f5", - "date_created": "28-06-2024", - "file_size": 3719656 + "date_created": "20-11-2024", + "file_size": 18060124 } ] diff --git a/results/spatial_decomposition/data/method_info.json b/results/spatial_decomposition/data/method_info.json index edcbf5af4..5773b189e 100644 --- a/results/spatial_decomposition/data/method_info.json +++ b/results/spatial_decomposition/data/method_info.json @@ -1,6 +1,6 @@ [ { - "task_id": "spatial_decomposition", + "task_id": "control_methods", "method_id": "random_proportions", "method_name": "Random Proportions", "method_summary": "Negative control method that randomly assigns celltype proportions from a Dirichlet distribution.", @@ -8,12 +8,12 @@ "is_baseline": true, "paper_reference": null, "code_url": null, - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/control_methods/random_proportions/config.vsh.yaml", + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/control_methods/random_proportions/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "control_methods", "method_id": "true_proportions", "method_name": "True Proportions", "method_summary": "Positive control method that assigns celltype proportions from the ground truth.", @@ -21,125 +21,125 @@ "is_baseline": true, "paper_reference": null, "code_url": null, - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/control_methods/true_proportions/config.vsh.yaml", + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/control_methods/true_proportions/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "cell2location", "method_name": "Cell2Location", "method_summary": "Cell2location uses a Bayesian model to resolve cell types in spatial transcriptomic data and create comprehensive cellular maps of diverse tissues.", "method_description": "Cell2location is a decomposition method based on Negative Binomial regression that is able to account for batch effects in estimating the single-cell gene expression signature used for the spatial decomposition step. \nNote that when batch information is unavailable for this task, we can use either a hard-coded reference, or a negative-binomial learned reference without batch labels. The parameter alpha refers to the detection efficiency prior.\n", "is_baseline": false, - "paper_reference": "kleshchevnikov2022cell2location", - "code_url": "https://github.com/BayraktarLab/cell2location", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/cell2location/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/cell2location/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "destvi", "method_name": "DestVI", "method_summary": "DestVI is a probabilistic method for multi-resolution analysis for spatial transcriptomics that explicitly models continuous variation within cell types", "method_description": "Deconvolution of Spatial Transcriptomics profiles using Variational Inference (DestVI) is a spatial decomposition method that leverages a conditional generative model of spatial transcriptomics down to the sub-cell-type variation level, which is then used to decompose the cell-type proportions determining the spatial organization of a tissue.\n", "is_baseline": false, - "paper_reference": "lopez2022destvi", - "code_url": "https://github.com/scverse/scvi-tools", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/destvi/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/destvi/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "nmfreg", "method_name": "NMFreg", "method_summary": "NMFreg reconstructs gene expression as a weighted combination of cell type signatures defined by scRNA-seq.", "method_description": "Non-Negative Matrix Factorization regression (NMFreg) is a decomposition method that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It was originally developed for Slide-seq data. This is a re-implementation from https://github.com/tudaga/NMFreg_tutorial.\n", "is_baseline": false, - "paper_reference": "rodriques2019slide", - "code_url": "https://github.com/tudaga/NMFreg_tutorial/tree/master?tab=readme-ov-file", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/nmfreg/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/nmfreg/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "nnls", "method_name": "NNLS", "method_summary": "NNLS is a decomposition method based on Non-Negative Least Square Regression.", "method_description": "NonNegative Least Squares (NNLS), is a convex optimization problem with convex constraints. It was used by the AutoGeneS method to infer cellular proporrtions by solvong a multi-objective optimization problem.\n", "is_baseline": false, - "paper_reference": "aliee2021autogenes", - "code_url": "https://github.com/scipy/scipy", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/nnls/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/nnls/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "rctd", "method_name": "RCTD", "method_summary": "RCTD learns cell type profiles from scRNA-seq to decompose cell type mixtures while correcting for differences across sequencing technologies.", "method_description": "RCTD (Robust Cell Type Decomposition) is a decomposition method that uses signatures learnt from single-cell data to decompose spatial expression of tissues. It is able to use a platform effect normalization step, which normalizes the scRNA-seq cell type profiles to match the platform effects of the spatial transcriptomics dataset.\n", "is_baseline": false, - "paper_reference": "cable2021robust", - "code_url": "https://github.com/dmcable/spacexr", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/rctd/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/rctd/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "seurat", "method_name": "Seurat", "method_summary": "Seurat method that is based on Canonical Correlation Analysis (CCA).", "method_description": "This method applies the 'anchor'-based integration workflow introduced in Seurat v3, that enables the probabilistic transfer of annotations from a reference to a query set. First, mutual nearest neighbors (anchors) are identified from the reference scRNA-seq and query spatial datasets. Then, annotations are transfered from the single cell reference data to the sptial data along with prediction scores for each spot.\n", "is_baseline": false, - "paper_reference": "stuart2019comprehensive", - "code_url": "https://github.com/satijalab/seurat", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/seurat/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/seurat/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "stereoscope", "method_name": "Stereoscope", "method_summary": "Stereoscope is a decomposition method based on Negative Binomial regression.", "method_description": "Stereoscope is a decomposition method based on Negative Binomial regression. It is similar in scope and implementation to cell2location but less flexible to incorporate additional covariates such as batch effects and other type of experimental design annotations.\n", "is_baseline": false, - "paper_reference": "andersson2020single", - "code_url": "https://github.com/scverse/scvi-tools", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/stereoscope/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/stereoscope/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "tangram", "method_name": "Tangram", "method_summary": "Tanagram maps single-cell gene expression data onto spatial gene expression data by fitting gene expression on shared genes", "method_description": "Tangram is a method to map gene expression signatures from scRNA-seq data to spatial data. It performs the cell type mapping by learning a similarity matrix between single-cell and spatial locations based on gene expression profiles.\n", "is_baseline": false, - "paper_reference": "biancalani2021deep", - "code_url": "https://github.com/broadinstitute/Tangram", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/tangram/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/tangram/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" }, { - "task_id": "spatial_decomposition", + "task_id": "methods", "method_id": "vanillanmf", "method_name": "NMF", "method_summary": "NMF reconstructs gene expression as a weighted combination of cell type signatures defined by scRNA-seq.", "method_description": "NMF is a decomposition method based on Non-negative Matrix Factorization (NMF) that reconstructs expression of each spatial location as a weighted combination of cell-type signatures defined by scRNA-seq. It is a simpler baseline than NMFreg as it only performs the NMF step based on mean expression signatures of cell types, returning the weights loading of the NMF as (normalized) cell type proportions, without the regression step.\n", "is_baseline": false, - "paper_reference": "cichocki2009fast", - "code_url": "https://github.com/scikit-learn/scikit-learn/blob/92c9b1866/sklearn/decomposition/", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/methods/vanillanmf/config.vsh.yaml", + "paper_reference": null, + "code_url": null, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/methods/vanillanmf/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc" + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac" } ] diff --git a/results/spatial_decomposition/data/metric_execution_info.json b/results/spatial_decomposition/data/metric_execution_info.json index 79ba11489..ac6772432 100644 --- a/results/spatial_decomposition/data/metric_execution_info.json +++ b/results/spatial_decomposition/data/metric_execution_info.json @@ -6,10 +6,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 459.5, - "peak_memory_mb": 3482, - "disk_read_mb": 33, + "duration_sec": 2.4, + "cpu_pct": 387.2, + "peak_memory_mb": 4199, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -20,10 +20,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.8, - "cpu_pct": 279.6, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 4, + "cpu_pct": 266.1, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -34,10 +34,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 250.6, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 8.2, + "cpu_pct": 189.8, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -48,10 +48,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 207, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.3, + "cpu_pct": 392.8, + "peak_memory_mb": 4301, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -62,10 +62,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 337.7, - "peak_memory_mb": 3482, - "disk_read_mb": 32, + "duration_sec": 3.9, + "cpu_pct": 289, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -76,10 +76,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 306, + "duration_sec": 8.5, + "cpu_pct": 185.5, "peak_memory_mb": 5530, - "disk_read_mb": 32, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -90,10 +90,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 322, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 4.2, + "cpu_pct": 316.9, + "peak_memory_mb": 5530, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -104,10 +104,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 4, - "cpu_pct": 326.1, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 4.1, + "cpu_pct": 340.7, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -118,10 +118,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 321.1, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 413.7, + "peak_memory_mb": 4301, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -132,10 +132,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.2, - "cpu_pct": 171.6, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 3.9, + "cpu_pct": 289.8, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -146,10 +146,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 306.2, - "peak_memory_mb": 3482, - "disk_read_mb": 32, + "duration_sec": 3.6, + "cpu_pct": 316.1, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -160,10 +160,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 333, - "peak_memory_mb": 3482, - "disk_read_mb": 33, + "duration_sec": 3.1, + "cpu_pct": 440.7, + "peak_memory_mb": 5530, + "disk_read_mb": 59, "disk_write_mb": 1 } }, @@ -174,10 +174,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 82, - "cpu_pct": 16.7, - "peak_memory_mb": 5530, - "disk_read_mb": 33, + "duration_sec": 2.5, + "cpu_pct": 459.4, + "peak_memory_mb": 5632, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -188,10 +188,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 384.3, - "peak_memory_mb": 2765, - "disk_read_mb": 33, + "duration_sec": 2.8, + "cpu_pct": 328, + "peak_memory_mb": 4199, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -202,10 +202,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 395.5, - "peak_memory_mb": 3584, - "disk_read_mb": 33, + "duration_sec": 2.9, + "cpu_pct": 467.9, + "peak_memory_mb": 5632, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -216,10 +216,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 327.3, - "peak_memory_mb": 3482, - "disk_read_mb": 33, + "duration_sec": 12.5, + "cpu_pct": 126.8, + "peak_memory_mb": 5632, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -230,10 +230,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.9, - "cpu_pct": 291.2, - "peak_memory_mb": 2868, - "disk_read_mb": 33, + "duration_sec": 2.5, + "cpu_pct": 448.5, + "peak_memory_mb": 5632, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -244,10 +244,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.2, - "cpu_pct": 355, - "peak_memory_mb": 2868, - "disk_read_mb": 33, + "duration_sec": 2.3, + "cpu_pct": 401.3, + "peak_memory_mb": 4301, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -258,10 +258,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 302.3, - "peak_memory_mb": 2868, - "disk_read_mb": 33, + "duration_sec": 3, + "cpu_pct": 406.3, + "peak_memory_mb": 5530, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -272,10 +272,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 6.6, - "cpu_pct": 169.5, + "duration_sec": 3.2, + "cpu_pct": 491.2, "peak_memory_mb": 5632, - "disk_read_mb": 32, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -286,10 +286,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 336, - "peak_memory_mb": 3482, - "disk_read_mb": 33, + "duration_sec": 3.1, + "cpu_pct": 469, + "peak_memory_mb": 5530, + "disk_read_mb": 58, "disk_write_mb": 1 } }, @@ -300,164 +300,38 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 330.9, - "peak_memory_mb": 3482, - "disk_read_mb": 33, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "cell2location", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.1, - "cpu_pct": 428.7, - "peak_memory_mb": 3482, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "nmfreg", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 297.7, - "peak_memory_mb": 2868, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "nnls", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 5.3, - "cpu_pct": 174.4, + "duration_sec": 12.1, + "cpu_pct": 135.9, "peak_memory_mb": 5632, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "random_proportions", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 328.4, - "peak_memory_mb": 3482, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "rctd", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 232.3, - "peak_memory_mb": 2868, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "seurat", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.8, - "cpu_pct": 291.3, - "peak_memory_mb": 2868, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "stereoscope", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 1.9, - "cpu_pct": 231.9, - "peak_memory_mb": 1434, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "tangram", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 327.5, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "disk_read_mb": 58, "disk_write_mb": 1 } }, { - "dataset_id": "cellxgene_census/hcla", + "dataset_id": "cellxgene_census/hypomap", "normalization_id": "log_cp10k", - "method_id": "true_proportions", + "method_id": "cell2location", "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 7.9, - "cpu_pct": 156.7, + "duration_sec": 3.2, + "cpu_pct": 480.6, "peak_memory_mb": 5530, - "disk_read_mb": 32, - "disk_write_mb": 1 - } - }, - { - "dataset_id": "cellxgene_census/hcla", - "normalization_id": "log_cp10k", - "method_id": "vanillanmf", - "metric_id": "r2", - "resources": { - "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 207.6, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "disk_read_mb": 58, "disk_write_mb": 1 } }, { "dataset_id": "cellxgene_census/hypomap", "normalization_id": "log_cp10k", - "method_id": "cell2location", + "method_id": "destvi", "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 289.7, + "duration_sec": 2.4, + "cpu_pct": 287.7, "peak_memory_mb": 2868, - "disk_read_mb": 34, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -468,10 +342,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.1, - "cpu_pct": 361.2, + "duration_sec": 2.5, + "cpu_pct": 281.4, "peak_memory_mb": 2868, - "disk_read_mb": 34, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -482,10 +356,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 369.3, - "peak_memory_mb": 3482, - "disk_read_mb": 34, + "duration_sec": 2.7, + "cpu_pct": 450.6, + "peak_memory_mb": 5632, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -496,10 +370,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 12.7, - "cpu_pct": 124.4, - "peak_memory_mb": 2765, - "disk_read_mb": 34, + "duration_sec": 3.8, + "cpu_pct": 299.9, + "peak_memory_mb": 5632, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -510,10 +384,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 259.2, - "peak_memory_mb": 2868, - "disk_read_mb": 34, + "duration_sec": 2.3, + "cpu_pct": 387.8, + "peak_memory_mb": 4301, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -524,10 +398,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 26.3, - "cpu_pct": 56.9, - "peak_memory_mb": 2765, - "disk_read_mb": 34, + "duration_sec": 2.3, + "cpu_pct": 294.4, + "peak_memory_mb": 2868, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -538,10 +412,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 221.6, - "peak_memory_mb": 1434, - "disk_read_mb": 34, + "duration_sec": 2.3, + "cpu_pct": 420.1, + "peak_memory_mb": 4301, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -552,10 +426,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 281.6, - "peak_memory_mb": 2868, - "disk_read_mb": 33, + "duration_sec": 2.3, + "cpu_pct": 567.9, + "peak_memory_mb": 5632, + "disk_read_mb": 56, "disk_write_mb": 1 } }, @@ -566,10 +440,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.7, - "cpu_pct": 374.4, - "peak_memory_mb": 5530, - "disk_read_mb": 34, + "duration_sec": 4.5, + "cpu_pct": 320, + "peak_memory_mb": 5632, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -580,10 +454,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 392.8, - "peak_memory_mb": 3584, - "disk_read_mb": 34, + "duration_sec": 3.6, + "cpu_pct": 324.6, + "peak_memory_mb": 5632, + "disk_read_mb": 57, "disk_write_mb": 1 } }, @@ -594,10 +468,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 390.3, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 3.3, + "cpu_pct": 399.8, + "peak_memory_mb": 5632, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -608,10 +482,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.1, - "cpu_pct": 367.6, - "peak_memory_mb": 1536, - "disk_read_mb": 32, + "duration_sec": 2.5, + "cpu_pct": 304.1, + "peak_memory_mb": 2868, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -622,10 +496,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 338.9, - "peak_memory_mb": 3482, - "disk_read_mb": 32, + "duration_sec": 2.2, + "cpu_pct": 311.1, + "peak_memory_mb": 2970, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -636,10 +510,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 716.8, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 10.3, + "cpu_pct": 153.3, + "peak_memory_mb": 5632, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -650,10 +524,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 8, - "cpu_pct": 156.5, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 389.8, + "peak_memory_mb": 4199, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -664,10 +538,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.1, - "cpu_pct": 169.3, - "peak_memory_mb": 1536, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 376, + "peak_memory_mb": 4199, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -678,10 +552,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.3, - "cpu_pct": 454.7, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.3, + "cpu_pct": 299.2, + "peak_memory_mb": 2868, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -693,9 +567,9 @@ "resources": { "exit_code": 0, "duration_sec": 2.2, - "cpu_pct": 356.6, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "cpu_pct": 499.6, + "peak_memory_mb": 5632, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -706,10 +580,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 322.1, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.3, + "cpu_pct": 392, + "peak_memory_mb": 4301, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -720,10 +594,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 1.9, - "cpu_pct": 727.7, + "duration_sec": 3.1, + "cpu_pct": 461.9, "peak_memory_mb": 5530, - "disk_read_mb": 32, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -734,10 +608,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.5, - "cpu_pct": 580.1, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 548.7, + "peak_memory_mb": 5632, + "disk_read_mb": 49, "disk_write_mb": 1 } }, @@ -748,10 +622,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 289.2, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 4.9, + "cpu_pct": 317.4, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -762,10 +636,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 1.9, - "cpu_pct": 700.1, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.2, + "cpu_pct": 309.7, + "peak_memory_mb": 2970, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -776,10 +650,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 297.3, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 331.5, + "peak_memory_mb": 4301, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -790,10 +664,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.8, - "cpu_pct": 385.3, + "duration_sec": 4.2, + "cpu_pct": 344.4, "peak_memory_mb": 5530, - "disk_read_mb": 32, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -804,10 +678,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5, - "cpu_pct": 305.7, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.5, + "cpu_pct": 481.7, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -818,10 +692,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 327.5, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 11.1, + "cpu_pct": 135.4, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -832,10 +706,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 327.4, + "duration_sec": 2.3, + "cpu_pct": 293.4, "peak_memory_mb": 2868, - "disk_read_mb": 32, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -846,10 +720,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.5, - "cpu_pct": 310.1, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.8, + "cpu_pct": 522.7, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -860,10 +734,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.3, - "cpu_pct": 332.9, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 2.4, + "cpu_pct": 404.1, + "peak_memory_mb": 4199, + "disk_read_mb": 45, "disk_write_mb": 1 } }, @@ -874,10 +748,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.9, - "cpu_pct": 356, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 7.8, + "cpu_pct": 202.3, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -888,10 +762,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 279.5, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.5, + "cpu_pct": 485.4, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -902,10 +776,24 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 290.4, - "peak_memory_mb": 2868, - "disk_read_mb": 34, + "duration_sec": 4.4, + "cpu_pct": 192.4, + "peak_memory_mb": 5632, + "disk_read_mb": 52, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "destvi", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.6, + "cpu_pct": 530.3, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -916,10 +804,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.3, - "cpu_pct": 339.5, + "duration_sec": 2.6, + "cpu_pct": 273.4, "peak_memory_mb": 2868, - "disk_read_mb": 34, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -930,10 +818,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 12.7, - "cpu_pct": 107.8, - "peak_memory_mb": 2765, - "disk_read_mb": 34, + "duration_sec": 10.4, + "cpu_pct": 155.7, + "peak_memory_mb": 5632, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -944,24 +832,38 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 317.5, - "peak_memory_mb": 5530, - "disk_read_mb": 34, + "duration_sec": 3.4, + "cpu_pct": 411.2, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "normalization_id": "log_cp10k", - "method_id": "seurat", + "method_id": "rctd", "metric_id": "r2", "resources": { "exit_code": 0, "duration_sec": 2.3, - "cpu_pct": 337.7, - "peak_memory_mb": 2868, - "disk_read_mb": 34, + "cpu_pct": 330.1, + "peak_memory_mb": 4301, + "disk_read_mb": 51, + "disk_write_mb": 1 + } + }, + { + "dataset_id": "cellxgene_census/tabula_sapiens", + "normalization_id": "log_cp10k", + "method_id": "seurat", + "metric_id": "r2", + "resources": { + "exit_code": 0, + "duration_sec": 2.5, + "cpu_pct": 429, + "peak_memory_mb": 5632, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -972,10 +874,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.9, - "cpu_pct": 289.4, - "peak_memory_mb": 2868, - "disk_read_mb": 34, + "duration_sec": 2.2, + "cpu_pct": 316.1, + "peak_memory_mb": 2970, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -986,10 +888,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 301.6, + "duration_sec": 2.4, + "cpu_pct": 302, "peak_memory_mb": 2868, - "disk_read_mb": 33, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -1000,10 +902,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 304.7, + "duration_sec": 4.2, + "cpu_pct": 351, "peak_memory_mb": 5530, - "disk_read_mb": 34, + "disk_read_mb": 50, "disk_write_mb": 1 } }, @@ -1014,10 +916,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 289.2, - "peak_memory_mb": 5530, - "disk_read_mb": 34, + "duration_sec": 10.2, + "cpu_pct": 148.6, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1028,10 +930,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 322.6, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 2.3, + "cpu_pct": 556, + "peak_memory_mb": 5632, + "disk_read_mb": 47, "disk_write_mb": 1 } }, @@ -1042,10 +944,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.1, - "cpu_pct": 202.5, - "peak_memory_mb": 1434, - "disk_read_mb": 31, + "duration_sec": 2.5, + "cpu_pct": 284.5, + "peak_memory_mb": 2868, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1056,10 +958,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 279.4, - "peak_memory_mb": 5530, - "disk_read_mb": 31, + "duration_sec": 4.3, + "cpu_pct": 348, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1071,9 +973,9 @@ "resources": { "exit_code": 0, "duration_sec": 3.8, - "cpu_pct": 361.6, - "peak_memory_mb": 5530, - "disk_read_mb": 31, + "cpu_pct": 293.9, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1084,10 +986,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.3, - "cpu_pct": 224.7, + "duration_sec": 7.2, + "cpu_pct": 219.2, "peak_memory_mb": 5530, - "disk_read_mb": 31, + "disk_read_mb": 47, "disk_write_mb": 1 } }, @@ -1098,10 +1000,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 319.7, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 2.2, + "cpu_pct": 403.3, + "peak_memory_mb": 4301, + "disk_read_mb": 47, "disk_write_mb": 1 } }, @@ -1112,10 +1014,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 327.4, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 4.4, + "cpu_pct": 351.2, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1126,10 +1028,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.1, - "cpu_pct": 220.1, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 2.5, + "cpu_pct": 487.4, + "peak_memory_mb": 5632, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1140,10 +1042,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 4, - "cpu_pct": 333.8, - "peak_memory_mb": 5530, - "disk_read_mb": 31, + "duration_sec": 4.1, + "cpu_pct": 229.1, + "peak_memory_mb": 4199, + "disk_read_mb": 47, "disk_write_mb": 1 } }, @@ -1154,10 +1056,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 8, - "cpu_pct": 121.6, - "peak_memory_mb": 5530, - "disk_read_mb": 31, + "duration_sec": 2.3, + "cpu_pct": 413.8, + "peak_memory_mb": 4301, + "disk_read_mb": 46, "disk_write_mb": 1 } }, @@ -1168,10 +1070,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 299.2, - "peak_memory_mb": 5530, - "disk_read_mb": 31, + "duration_sec": 2.6, + "cpu_pct": 490.5, + "peak_memory_mb": 5632, + "disk_read_mb": 47, "disk_write_mb": 1 } }, @@ -1182,10 +1084,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 282.9, - "peak_memory_mb": 2868, - "disk_read_mb": 30, + "duration_sec": 3.4, + "cpu_pct": 298.4, + "peak_memory_mb": 5632, + "disk_read_mb": 45, "disk_write_mb": 1 } }, @@ -1196,10 +1098,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 258.2, - "peak_memory_mb": 2868, - "disk_read_mb": 30, + "duration_sec": 2.5, + "cpu_pct": 264.5, + "peak_memory_mb": 4199, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1210,10 +1112,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 278.2, - "peak_memory_mb": 5530, - "disk_read_mb": 30, + "duration_sec": 11, + "cpu_pct": 133.6, + "peak_memory_mb": 5632, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1224,10 +1126,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 248.3, - "peak_memory_mb": 5530, - "disk_read_mb": 30, + "duration_sec": 2.3, + "cpu_pct": 402.2, + "peak_memory_mb": 4301, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1238,10 +1140,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.7, - "cpu_pct": 355.2, + "duration_sec": 4.1, + "cpu_pct": 346.5, "peak_memory_mb": 5530, - "disk_read_mb": 30, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1252,10 +1154,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 244.4, - "peak_memory_mb": 5530, - "disk_read_mb": 30, + "duration_sec": 4.8, + "cpu_pct": 295.7, + "peak_memory_mb": 5632, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1266,10 +1168,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 173.9, - "peak_memory_mb": 1536, - "disk_read_mb": 30, + "duration_sec": 2.3, + "cpu_pct": 425.4, + "peak_memory_mb": 4301, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1280,10 +1182,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.1, - "cpu_pct": 372.5, - "peak_memory_mb": 2765, - "disk_read_mb": 30, + "duration_sec": 4.2, + "cpu_pct": 325, + "peak_memory_mb": 5530, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1294,10 +1196,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 267.1, - "peak_memory_mb": 5530, - "disk_read_mb": 30, + "duration_sec": 3.8, + "cpu_pct": 335.1, + "peak_memory_mb": 5632, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1308,10 +1210,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 242.5, + "duration_sec": 4.1, + "cpu_pct": 378.4, "peak_memory_mb": 5530, - "disk_read_mb": 30, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1322,10 +1224,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 12.6, - "cpu_pct": 104.9, - "peak_memory_mb": 2765, - "disk_read_mb": 30, + "duration_sec": 2.3, + "cpu_pct": 512.7, + "peak_memory_mb": 5632, + "disk_read_mb": 44, "disk_write_mb": 1 } }, @@ -1336,10 +1238,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.5, - "cpu_pct": 328.1, - "peak_memory_mb": 3482, - "disk_read_mb": 31, + "duration_sec": 2.4, + "cpu_pct": 509.9, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1350,10 +1252,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 1.8, - "cpu_pct": 240.2, - "peak_memory_mb": 1434, - "disk_read_mb": 31, + "duration_sec": 2.3, + "cpu_pct": 516.5, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1364,10 +1266,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 327.4, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 2.3, + "cpu_pct": 421.3, + "peak_memory_mb": 4301, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1378,10 +1280,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.9, - "cpu_pct": 290.8, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 12.2, + "cpu_pct": 132.9, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1392,10 +1294,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 302.3, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 12.1, + "cpu_pct": 124.4, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1406,10 +1308,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.1, - "cpu_pct": 173, - "peak_memory_mb": 1536, - "disk_read_mb": 31, + "duration_sec": 12.2, + "cpu_pct": 136, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1420,10 +1322,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 322.8, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 12.3, + "cpu_pct": 127.6, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1434,10 +1336,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.5, - "cpu_pct": 310.4, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "duration_sec": 3, + "cpu_pct": 491.7, + "peak_memory_mb": 5530, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1448,10 +1350,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.1, - "cpu_pct": 169.2, - "peak_memory_mb": 1536, - "disk_read_mb": 31, + "duration_sec": 7.2, + "cpu_pct": 227.2, + "peak_memory_mb": 5530, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1463,9 +1365,9 @@ "resources": { "exit_code": 0, "duration_sec": 2.3, - "cpu_pct": 330.2, - "peak_memory_mb": 2868, - "disk_read_mb": 31, + "cpu_pct": 516.3, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1476,10 +1378,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 387.8, - "peak_memory_mb": 2765, - "disk_read_mb": 31, + "duration_sec": 2.4, + "cpu_pct": 505.5, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1490,10 +1392,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.6, - "cpu_pct": 366.3, - "peak_memory_mb": 3482, - "disk_read_mb": 32, + "duration_sec": 2.2, + "cpu_pct": 396.3, + "peak_memory_mb": 4301, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1504,10 +1406,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3.4, - "cpu_pct": 229.8, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 2.2, + "cpu_pct": 313, + "peak_memory_mb": 2970, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1518,10 +1420,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.7, - "cpu_pct": 324.5, - "peak_memory_mb": 3482, - "disk_read_mb": 32, + "duration_sec": 4.2, + "cpu_pct": 309.2, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1532,10 +1434,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 6.6, - "cpu_pct": 183.6, + "duration_sec": 4.2, + "cpu_pct": 191.7, "peak_memory_mb": 5632, - "disk_read_mb": 32, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1546,10 +1448,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.1, - "cpu_pct": 319.2, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.3, + "cpu_pct": 442.3, + "peak_memory_mb": 4301, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1560,10 +1462,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 3, - "cpu_pct": 176.1, - "peak_memory_mb": 1536, - "disk_read_mb": 32, + "duration_sec": 2.4, + "cpu_pct": 544.4, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1574,10 +1476,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.4, - "cpu_pct": 317.5, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 3, + "cpu_pct": 429.6, + "peak_memory_mb": 5530, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1588,10 +1490,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.2, - "cpu_pct": 354.5, - "peak_memory_mb": 2868, - "disk_read_mb": 32, + "duration_sec": 3.1, + "cpu_pct": 462.7, + "peak_memory_mb": 5530, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1602,10 +1504,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 2.9, - "cpu_pct": 436.6, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.5, + "cpu_pct": 488, + "peak_memory_mb": 5632, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1616,10 +1518,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 6.6, - "cpu_pct": 150.6, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.5, + "cpu_pct": 395.1, + "peak_memory_mb": 4199, + "disk_read_mb": 51, "disk_write_mb": 1 } }, @@ -1630,10 +1532,10 @@ "metric_id": "r2", "resources": { "exit_code": 0, - "duration_sec": 5.2, - "cpu_pct": 280, - "peak_memory_mb": 5530, - "disk_read_mb": 32, + "duration_sec": 2.3, + "cpu_pct": 416.4, + "peak_memory_mb": 4301, + "disk_read_mb": 51, "disk_write_mb": 1 } } diff --git a/results/spatial_decomposition/data/metric_info.json b/results/spatial_decomposition/data/metric_info.json index 8a2176676..8455d81dc 100644 --- a/results/spatial_decomposition/data/metric_info.json +++ b/results/spatial_decomposition/data/metric_info.json @@ -1,14 +1,16 @@ [ { - "task_id": "spatial_decomposition", + "task_id": "metrics", "metric_id": "r2", "metric_name": "R2", "metric_summary": "R2 represents the proportion of variance in the true proportions which is explained by the predicted proportions.", "metric_description": "R2, or the “coefficient of determination”, reports the fraction of the true proportion values' variance that can be explained by the predicted proportion values. The best score, and upper bound, is 1.0. There is no fixed lower bound for the metric. The uniform/non-weighted average across all cell types/states is used to summarise performance. By default, cases resulting in a score of NaN (perfect predictions) or -Inf (imperfect predictions) are replaced with 1.0 (perfect predictions) or 0.0 (imperfect predictions) respectively.\n", - "paper_reference": "miles2005rsquared", - "implementation_url": "https://github.com/openproblems-bio/openproblems-v2/blob/44694e82e86ee3d89737ae9474d54c5f0a29b6fc/src/tasks/spatial_decomposition/metrics/r2/config.vsh.yaml", + "paper_reference": { + "doi": "10.1002/0470013192.bsa526" + }, + "implementation_url": "https://github.com/openproblems-bio/task_spatial_decomposition/blob/9f32dec1f8fe366abd433021fe0d2e0cab492aac/src/metrics/r2/config.vsh.yaml", "code_version": null, - "commit_sha": "44694e82e86ee3d89737ae9474d54c5f0a29b6fc", + "commit_sha": "9f32dec1f8fe366abd433021fe0d2e0cab492aac", "maximize": true } ] diff --git a/results/spatial_decomposition/data/quality_control.json b/results/spatial_decomposition/data/quality_control.json index 4af4f0b96..4b0c50b1e 100644 --- a/results/spatial_decomposition/data/quality_control.json +++ b/results/spatial_decomposition/data/quality_control.json @@ -1,922 +1,692 @@ [ { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Task info", "name": "Pct 'task_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing([task_info], field)", - "message": "Task metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" + "message": "Task metadata field 'task_id' should be defined\n Task id: task_spatial_decomposition\n Field: task_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Task info", "name": "Pct 'task_name' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing([task_info], field)", - "message": "Task metadata field 'task_name' should be defined\n Task id: spatial_decomposition\n Field: task_name\n" + "message": "Task metadata field 'task_name' should be defined\n Task id: task_spatial_decomposition\n Field: task_name\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Task info", "name": "Pct 'task_summary' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing([task_info], field)", - "message": "Task metadata field 'task_summary' should be defined\n Task id: spatial_decomposition\n Field: task_summary\n" + "message": "Task metadata field 'task_summary' should be defined\n Task id: task_spatial_decomposition\n Field: task_summary\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Task info", "name": "Pct 'task_description' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing([task_info], field)", - "message": "Task metadata field 'task_description' should be defined\n Task id: spatial_decomposition\n Field: task_description\n" + "message": "Task metadata field 'task_description' should be defined\n Task id: task_spatial_decomposition\n Field: task_description\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'task_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" + "message": "Method metadata field 'task_id' should be defined\n Task id: task_spatial_decomposition\n Field: task_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'commit_sha' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'commit_sha' should be defined\n Task id: spatial_decomposition\n Field: commit_sha\n" + "message": "Method metadata field 'commit_sha' should be defined\n Task id: task_spatial_decomposition\n Field: commit_sha\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'method_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'method_id' should be defined\n Task id: spatial_decomposition\n Field: method_id\n" + "message": "Method metadata field 'method_id' should be defined\n Task id: task_spatial_decomposition\n Field: method_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'method_name' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'method_name' should be defined\n Task id: spatial_decomposition\n Field: method_name\n" + "message": "Method metadata field 'method_name' should be defined\n Task id: task_spatial_decomposition\n Field: method_name\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'method_summary' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'method_summary' should be defined\n Task id: spatial_decomposition\n Field: method_summary\n" + "message": "Method metadata field 'method_summary' should be defined\n Task id: task_spatial_decomposition\n Field: method_summary\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'paper_reference' missing", - "value": 0.0, - "severity": 0, - "severity_value": 0.0, + "value": 0.8181818181818182, + "severity": 2, + "severity_value": 3.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'paper_reference' should be defined\n Task id: spatial_decomposition\n Field: paper_reference\n" + "message": "Method metadata field 'paper_reference' should be defined\n Task id: task_spatial_decomposition\n Field: paper_reference\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Method info", "name": "Pct 'is_baseline' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(method_info, field)", - "message": "Method metadata field 'is_baseline' should be defined\n Task id: spatial_decomposition\n Field: is_baseline\n" + "message": "Method metadata field 'is_baseline' should be defined\n Task id: task_spatial_decomposition\n Field: is_baseline\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'task_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" + "message": "Metric metadata field 'task_id' should be defined\n Task id: task_spatial_decomposition\n Field: task_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'commit_sha' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'commit_sha' should be defined\n Task id: spatial_decomposition\n Field: commit_sha\n" + "message": "Metric metadata field 'commit_sha' should be defined\n Task id: task_spatial_decomposition\n Field: commit_sha\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'metric_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'metric_id' should be defined\n Task id: spatial_decomposition\n Field: metric_id\n" + "message": "Metric metadata field 'metric_id' should be defined\n Task id: task_spatial_decomposition\n Field: metric_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'metric_name' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'metric_name' should be defined\n Task id: spatial_decomposition\n Field: metric_name\n" + "message": "Metric metadata field 'metric_name' should be defined\n Task id: task_spatial_decomposition\n Field: metric_name\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'metric_summary' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'metric_summary' should be defined\n Task id: spatial_decomposition\n Field: metric_summary\n" + "message": "Metric metadata field 'metric_summary' should be defined\n Task id: task_spatial_decomposition\n Field: metric_summary\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'paper_reference' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'paper_reference' should be defined\n Task id: spatial_decomposition\n Field: paper_reference\n" + "message": "Metric metadata field 'paper_reference' should be defined\n Task id: task_spatial_decomposition\n Field: paper_reference\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Metric info", "name": "Pct 'maximize' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(metric_info, field)", - "message": "Metric metadata field 'maximize' should be defined\n Task id: spatial_decomposition\n Field: maximize\n" + "message": "Metric metadata field 'maximize' should be defined\n Task id: task_spatial_decomposition\n Field: maximize\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'task_id' missing", - "value": 0.0, - "severity": 0, - "severity_value": 0.0, + "value": 1.0, + "severity": 2, + "severity_value": 3.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'task_id' should be defined\n Task id: spatial_decomposition\n Field: task_id\n" + "message": "Dataset metadata field 'task_id' should be defined\n Task id: task_spatial_decomposition\n Field: task_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'dataset_id' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'dataset_id' should be defined\n Task id: spatial_decomposition\n Field: dataset_id\n" + "message": "Dataset metadata field 'dataset_id' should be defined\n Task id: task_spatial_decomposition\n Field: dataset_id\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'dataset_name' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'dataset_name' should be defined\n Task id: spatial_decomposition\n Field: dataset_name\n" + "message": "Dataset metadata field 'dataset_name' should be defined\n Task id: task_spatial_decomposition\n Field: dataset_name\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'dataset_summary' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'dataset_summary' should be defined\n Task id: spatial_decomposition\n Field: dataset_summary\n" + "message": "Dataset metadata field 'dataset_summary' should be defined\n Task id: task_spatial_decomposition\n Field: dataset_summary\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'data_reference' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'data_reference' should be defined\n Task id: spatial_decomposition\n Field: data_reference\n" + "message": "Dataset metadata field 'data_reference' should be defined\n Task id: task_spatial_decomposition\n Field: data_reference\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Dataset info", "name": "Pct 'data_url' missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "percent_missing(dataset_info, field)", - "message": "Dataset metadata field 'data_url' should be defined\n Task id: spatial_decomposition\n Field: data_url\n" + "message": "Dataset metadata field 'data_url' should be defined\n Task id: task_spatial_decomposition\n Field: data_url\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw data", "name": "Number of results", - "value": 121, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "len(results) == len(method_info) * len(metric_info) * len(dataset_info)", - "message": "Number of results should be equal to #methods × #metrics × #datasets.\n Task id: spatial_decomposition\n Number of results: 121\n Number of methods: 11\n Number of metrics: 1\n Number of datasets: 33\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Metric 'r2' %missing", - "value": 0.6776859504132231, - "severity": 3, - "severity_value": 6.776859504132231, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n Metric id: r2\n Percentage missing: 68%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'random_proportions' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: random_proportions\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'true_proportions' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: true_proportions\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'cell2location' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: cell2location\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'destvi' %missing", - "value": 0.7575757575757576, - "severity": 3, - "severity_value": 7.575757575757575, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: destvi\n Percentage missing: 76%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'nmfreg' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nmfreg\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'nnls' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: nnls\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'rctd' %missing", - "value": 0.696969696969697, - "severity": 3, - "severity_value": 6.96969696969697, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: rctd\n Percentage missing: 70%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'seurat' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: seurat\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'stereoscope' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: stereoscope\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'tangram' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: tangram\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Method 'vanillanmf' %missing", - "value": 0.6666666666666667, - "severity": 3, - "severity_value": 6.666666666666667, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n method id: vanillanmf\n Percentage missing: 67%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/gtex_v9' %missing", - "value": 0.0, - "severity": 0, - "severity_value": 0.0, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/dkd' %missing", - "value": 0.0, + "value": 110, "severity": 0, "severity_value": 0.0, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" + "code": "len(results) == len(method_info) * len(metric_info) * len(dataset_info)", + "message": "Number of results should be equal to #methods × #metrics × #datasets.\n Task id: task_spatial_decomposition\n Number of results: 110\n Number of methods: 11\n Number of metrics: 1\n Number of datasets: 10\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/dkd' %missing", + "name": "Metric 'r2' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n Metric id: r2\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/cengen' %missing", + "name": "Method 'random_proportions' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: random_proportions\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/zebrafish' %missing", + "name": "Method 'true_proportions' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: true_proportions\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/immune_cells' %missing", + "name": "Method 'cell2location' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: cell2location\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/cengen' %missing", + "name": "Method 'destvi' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/hcla' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: destvi\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/immune_cells' %missing", + "name": "Method 'nmfreg' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", - "value": 0.18181818181818177, - "severity": 1, - "severity_value": 1.8181818181818177, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: nmfreg\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/zebrafish' %missing", + "name": "Method 'nnls' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", - "value": 0.18181818181818177, - "severity": 1, - "severity_value": 1.8181818181818177, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: nnls\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/pancreas' %missing", + "name": "Method 'rctd' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: rctd\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", + "name": "Method 'seurat' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/hypomap' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/hypomap' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: seurat\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/pancreas' %missing", + "name": "Method 'stereoscope' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: stereoscope\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/cengen' %missing", + "name": "Method 'tangram' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: tangram\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", + "name": "Method 'vanillanmf' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n method id: vanillanmf\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/hcla' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/gtex_v9' %missing", + "name": "Dataset 'cellxgene_census/hypomap' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/immune_cells' %missing", + "name": "Dataset 'openproblems_v1/cengen' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: openproblems_v1/cengen\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", + "name": "Dataset 'openproblems_v1/zebrafish' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", "name": "Dataset 'openproblems_v1/pancreas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: openproblems_v1/pancreas\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", "name": "Dataset 'cellxgene_census/gtex_v9' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/gtex_v9\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", + "name": "Dataset 'openproblems_v1/immune_cells' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/hypomap' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hypomap\n Percentage missing: 9%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: openproblems_v1/immune_cells\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'cellxgene_census/mouse_pancreas_atlas' %missing", + "name": "Dataset 'cellxgene_census/dkd' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/mouse_pancreas_atlas\n Percentage missing: 0%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/hcla' %missing", - "value": 0.09090909090909094, - "severity": 0, - "severity_value": 0.9090909090909094, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/hcla\n Percentage missing: 9%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", - "name": "Dataset 'openproblems_v1/zebrafish' %missing", + "name": "Dataset 'cellxgene_census/immune_cell_atlas' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: openproblems_v1/zebrafish\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/immune_cell_atlas\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Raw results", "name": "Dataset 'cellxgene_census/tabula_sapiens' %missing", - "value": 0.18181818181818177, - "severity": 1, - "severity_value": 1.8181818181818177, - "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 18%\n" - }, - { - "task_id": "spatial_decomposition", - "category": "Raw results", - "name": "Dataset 'cellxgene_census/dkd' %missing", "value": 0.0, "severity": 0, "severity_value": 0.0, "code": "pct_missing <= .1", - "message": "Percentage of missing results should be less than 10%.\n Task id: spatial_decomposition\n dataset id: cellxgene_census/dkd\n Percentage missing: 0%\n" + "message": "Percentage of missing results should be less than 10%.\n Task id: task_spatial_decomposition\n dataset id: cellxgene_census/tabula_sapiens\n Percentage missing: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score random_proportions r2", "value": 0, "severity": 0, "severity_value": -0.0, "code": "worst_score >= -1", - "message": "Method random_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Worst score: 0%\n" + "message": "Method random_proportions performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Worst score: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score random_proportions r2", "value": 0, "severity": 0, "severity_value": 0.0, "code": "best_score <= 2", - "message": "Method random_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Best score: 0%\n" + "message": "Method random_proportions performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: random_proportions\n Metric id: r2\n Best score: 0%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score true_proportions r2", "value": 1, "severity": 0, "severity_value": -1.0, "code": "worst_score >= -1", - "message": "Method true_proportions performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Worst score: 1%\n" + "message": "Method true_proportions performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Worst score: 1%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score true_proportions r2", "value": 1, "severity": 0, "severity_value": 0.5, "code": "best_score <= 2", - "message": "Method true_proportions performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Best score: 1%\n" + "message": "Method true_proportions performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: true_proportions\n Metric id: r2\n Best score: 1%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score cell2location r2", - "value": -3.4575, + "value": -3.3126, "severity": 3, - "severity_value": 3.4575, + "severity_value": 3.3126, "code": "worst_score >= -1", - "message": "Method cell2location performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Worst score: -3.4575%\n" + "message": "Method cell2location performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Worst score: -3.3126%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score cell2location r2", - "value": 0.8529, + "value": 0.8624, "severity": 0, - "severity_value": 0.42645, + "severity_value": 0.4312, "code": "best_score <= 2", - "message": "Method cell2location performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Best score: 0.8529%\n" + "message": "Method cell2location performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: cell2location\n Metric id: r2\n Best score: 0.8624%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score destvi r2", - "value": -0.5927, - "severity": 0, - "severity_value": 0.5927, + "value": -1.1763, + "severity": 1, + "severity_value": 1.1763, "code": "worst_score >= -1", - "message": "Method destvi performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Worst score: -0.5927%\n" + "message": "Method destvi performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: destvi\n Metric id: r2\n Worst score: -1.1763%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score destvi r2", - "value": 0.7543, + "value": 0.8507, "severity": 0, - "severity_value": 0.37715, + "severity_value": 0.42535, "code": "best_score <= 2", - "message": "Method destvi performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: destvi\n Metric id: r2\n Best score: 0.7543%\n" + "message": "Method destvi performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: destvi\n Metric id: r2\n Best score: 0.8507%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score nmfreg r2", - "value": -2.2265, - "severity": 2, - "severity_value": 2.2265, + "value": -1.8296, + "severity": 1, + "severity_value": 1.8296, "code": "worst_score >= -1", - "message": "Method nmfreg performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Worst score: -2.2265%\n" + "message": "Method nmfreg performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Worst score: -1.8296%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score nmfreg r2", - "value": 0.2474, + "value": 0.3319, "severity": 0, - "severity_value": 0.1237, + "severity_value": 0.16595, "code": "best_score <= 2", - "message": "Method nmfreg performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Best score: 0.2474%\n" + "message": "Method nmfreg performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: nmfreg\n Metric id: r2\n Best score: 0.3319%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score nnls r2", - "value": -3.3901, - "severity": 3, - "severity_value": 3.3901, + "value": -2.8586, + "severity": 2, + "severity_value": 2.8586, "code": "worst_score >= -1", - "message": "Method nnls performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: nnls\n Metric id: r2\n Worst score: -3.3901%\n" + "message": "Method nnls performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: nnls\n Metric id: r2\n Worst score: -2.8586%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score nnls r2", - "value": 0.706, + "value": 0.7482, "severity": 0, - "severity_value": 0.353, + "severity_value": 0.3741, "code": "best_score <= 2", - "message": "Method nnls performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: nnls\n Metric id: r2\n Best score: 0.706%\n" + "message": "Method nnls performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: nnls\n Metric id: r2\n Best score: 0.7482%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score rctd r2", - "value": -0.7795, - "severity": 0, - "severity_value": 0.7795, + "value": -2.5379, + "severity": 2, + "severity_value": 2.5379, "code": "worst_score >= -1", - "message": "Method rctd performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Worst score: -0.7795%\n" + "message": "Method rctd performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: rctd\n Metric id: r2\n Worst score: -2.5379%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score rctd r2", - "value": 0.8478, + "value": 0.8622, "severity": 0, - "severity_value": 0.4239, + "severity_value": 0.4311, "code": "best_score <= 2", - "message": "Method rctd performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: rctd\n Metric id: r2\n Best score: 0.8478%\n" + "message": "Method rctd performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: rctd\n Metric id: r2\n Best score: 0.8622%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score seurat r2", - "value": -3.0585, + "value": -3.1724, "severity": 3, - "severity_value": 3.0585, + "severity_value": 3.1724, "code": "worst_score >= -1", - "message": "Method seurat performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: seurat\n Metric id: r2\n Worst score: -3.0585%\n" + "message": "Method seurat performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: seurat\n Metric id: r2\n Worst score: -3.1724%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score seurat r2", - "value": 0.1364, + "value": -0.2107, "severity": 0, - "severity_value": 0.0682, + "severity_value": -0.10535, "code": "best_score <= 2", - "message": "Method seurat performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: seurat\n Metric id: r2\n Best score: 0.1364%\n" + "message": "Method seurat performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: seurat\n Metric id: r2\n Best score: -0.2107%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score stereoscope r2", - "value": 0.2221, + "value": -0.037, "severity": 0, - "severity_value": -0.2221, + "severity_value": 0.037, "code": "worst_score >= -1", - "message": "Method stereoscope performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Worst score: 0.2221%\n" + "message": "Method stereoscope performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Worst score: -0.037%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score stereoscope r2", - "value": 0.7132, + "value": 0.8493, "severity": 0, - "severity_value": 0.3566, + "severity_value": 0.42465, "code": "best_score <= 2", - "message": "Method stereoscope performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Best score: 0.7132%\n" + "message": "Method stereoscope performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: stereoscope\n Metric id: r2\n Best score: 0.8493%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score tangram r2", - "value": -0.8664, + "value": -0.7971, "severity": 0, - "severity_value": 0.8664, + "severity_value": 0.7971, "code": "worst_score >= -1", - "message": "Method tangram performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Worst score: -0.8664%\n" + "message": "Method tangram performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: tangram\n Metric id: r2\n Worst score: -0.7971%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score tangram r2", - "value": -0.0668, + "value": -0.1703, "severity": 0, - "severity_value": -0.0334, + "severity_value": -0.08515, "code": "best_score <= 2", - "message": "Method tangram performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: tangram\n Metric id: r2\n Best score: -0.0668%\n" + "message": "Method tangram performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: tangram\n Metric id: r2\n Best score: -0.1703%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Worst score vanillanmf r2", - "value": -0.7005, + "value": 0.2092, "severity": 0, - "severity_value": 0.7005, + "severity_value": -0.2092, "code": "worst_score >= -1", - "message": "Method vanillanmf performs much worse than baselines.\n Task id: spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Worst score: -0.7005%\n" + "message": "Method vanillanmf performs much worse than baselines.\n Task id: task_spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Worst score: 0.2092%\n" }, { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "category": "Scaling", "name": "Best score vanillanmf r2", - "value": 0.5231, + "value": 0.7631, "severity": 0, - "severity_value": 0.26155, + "severity_value": 0.38155, "code": "best_score <= 2", - "message": "Method vanillanmf performs a lot better than baselines.\n Task id: spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Best score: 0.5231%\n" + "message": "Method vanillanmf performs a lot better than baselines.\n Task id: task_spatial_decomposition\n Method id: vanillanmf\n Metric id: r2\n Best score: 0.7631%\n" } ] \ No newline at end of file diff --git a/results/spatial_decomposition/data/results.json b/results/spatial_decomposition/data/results.json index 30adea7e0..30aca9f14 100644 --- a/results/spatial_decomposition/data/results.json +++ b/results/spatial_decomposition/data/results.json @@ -3,91 +3,87 @@ "dataset_id": "cellxgene_census/dkd", "method_id": "cell2location", "metric_values": { - "r2": 0.577 + "r2": 0.5477 }, "scaled_scores": { - "r2": 0.7704 + "r2": 0.7611 }, - "mean_score": 0.7704, + "mean_score": 0.7611, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3550, - "cpu_pct": 1759.5, - "peak_memory_mb": 16794, - "disk_read_mb": 777, - "disk_write_mb": 13 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3368, + "cpu_pct": 99.8, + "peak_memory_mb": 17408, + "disk_read_mb": 1024, + "disk_write_mb": 18 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "destvi", "metric_values": { - "r2": 0.5475 + "r2": 0.5013 }, "scaled_scores": { - "r2": 0.7543 + "r2": 0.7366 }, - "mean_score": 0.7543, + "mean_score": 0.7366, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 4121, - "cpu_pct": 101.3, - "peak_memory_mb": 15770, - "disk_read_mb": 719, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6317, + "cpu_pct": 110.3, + "peak_memory_mb": 18944, + "disk_read_mb": 1024, + "disk_write_mb": 10 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "nmfreg", "metric_values": { - "r2": -0.3863 + "r2": -0.2648 }, "scaled_scores": { - "r2": 0.2474 + "r2": 0.3319 }, - "mean_score": 0.2474, + "mean_score": 0.3319, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 455, - "cpu_pct": 110.2, - "peak_memory_mb": 8397, - "disk_read_mb": 675, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 973, + "cpu_pct": 347.2, + "peak_memory_mb": 11776, + "disk_read_mb": 1014, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "nnls", "metric_values": { - "r2": 0.3433 + "r2": 0.3508 }, "scaled_scores": { - "r2": 0.6435 + "r2": 0.657 }, - "mean_score": 0.6435, + "mean_score": 0.657, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 8.9, - "cpu_pct": 345.7, - "peak_memory_mb": 4711, - "disk_read_mb": 664, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 12, + "cpu_pct": 2227.7, + "peak_memory_mb": 7373, + "disk_read_mb": 1003, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "random_proportions", "metric_values": { - "r2": -0.8421 + "r2": -0.8931 }, "scaled_scores": { "r2": 0 @@ -96,97 +92,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 4.9, - "cpu_pct": 163.7, - "peak_memory_mb": 3175, - "disk_read_mb": 665, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 4.8, + "cpu_pct": 243, + "peak_memory_mb": 6554, + "disk_read_mb": 1002, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "rctd", "metric_values": { - "r2": 0.5304 + "r2": 0.4768 }, "scaled_scores": { - "r2": 0.745 + "r2": 0.7236 }, - "mean_score": 0.745, + "mean_score": 0.7236, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 309, - "cpu_pct": 56.9, - "peak_memory_mb": 17204, - "disk_read_mb": 1024, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 684, + "cpu_pct": 57.6, + "peak_memory_mb": 18228, + "disk_read_mb": 1434, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "seurat", "metric_values": { - "r2": -2.5101 + "r2": -4.3057 }, "scaled_scores": { - "r2": -0.9055 + "r2": -1.8027 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 873, - "cpu_pct": 101, - "peak_memory_mb": 22119, - "disk_read_mb": 700, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 1192, + "cpu_pct": 101.4, + "peak_memory_mb": 24474, + "disk_read_mb": 1024, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "stereoscope", "metric_values": { - "r2": 0.0587 + "r2": 0.4946 }, "scaled_scores": { - "r2": 0.489 + "r2": 0.733 }, - "mean_score": 0.489, + "mean_score": 0.733, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 481, - "cpu_pct": 100.2, - "peak_memory_mb": 15360, - "disk_read_mb": 719, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 542, + "cpu_pct": 106.1, + "peak_memory_mb": 18228, + "disk_read_mb": 1024, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "tangram", "metric_values": { - "r2": -1.373 + "r2": -1.6465 }, "scaled_scores": { - "r2": -0.2882 + "r2": -0.398 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 70, - "cpu_pct": 1132.7, - "peak_memory_mb": 9421, - "disk_read_mb": 730, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 846, + "cpu_pct": 2085.1, + "peak_memory_mb": 17408, + "disk_read_mb": 1024, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/dkd", @@ -201,124 +192,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2.2, - "cpu_pct": 419.6, - "peak_memory_mb": 4199, - "disk_read_mb": 665, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6.7, + "cpu_pct": 217.2, + "peak_memory_mb": 6554, + "disk_read_mb": 1024, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/dkd", "method_id": "vanillanmf", "metric_values": { - "r2": -0.9833 + "r2": 0.1686 }, "scaled_scores": { - "r2": -0.0766 + "r2": 0.5608 }, - "mean_score": 0, + "mean_score": 0.5608, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 21.8, - "cpu_pct": 1321, - "peak_memory_mb": 2765, - "disk_read_mb": 673, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 23.8, + "cpu_pct": 2445.1, + "peak_memory_mb": 7578, + "disk_read_mb": 1012, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "cell2location", "metric_values": { - "r2": -0.0006 + "r2": -0.0118 }, "scaled_scores": { - "r2": 0.3556 + "r2": 0.3439 }, - "mean_score": 0.3556, + "mean_score": 0.3439, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3228, - "cpu_pct": 784.6, - "peak_memory_mb": 10855, - "disk_read_mb": 1639, - "disk_write_mb": 13 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3461, + "cpu_pct": 99.8, + "peak_memory_mb": 21095, + "disk_read_mb": 2356, + "disk_write_mb": 18 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "destvi", "metric_values": { - "r2": 0.0814 + "r2": 0.1168 }, "scaled_scores": { - "r2": 0.4084 + "r2": 0.4273 }, - "mean_score": 0.4084, + "mean_score": 0.4273, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 16288, - "cpu_pct": 100.7, - "peak_memory_mb": 16896, - "disk_read_mb": 1536, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 19389, + "cpu_pct": 103.8, + "peak_memory_mb": 23655, + "disk_read_mb": 2356, + "disk_write_mb": 10 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "nmfreg", "metric_values": { - "r2": -0.7907 + "r2": -0.6618 }, "scaled_scores": { - "r2": -0.1533 + "r2": -0.0776 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 844, - "cpu_pct": 105, - "peak_memory_mb": 14644, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2455, + "cpu_pct": 171.5, + "peak_memory_mb": 19559, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "nnls", "metric_values": { - "r2": -0.4479 + "r2": -0.3636 }, "scaled_scores": { - "r2": 0.0675 + "r2": 0.1158 }, - "mean_score": 0.0675, + "mean_score": 0.1158, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 13, - "cpu_pct": 499.9, - "peak_memory_mb": 5632, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 28.5, + "cpu_pct": 3490.5, + "peak_memory_mb": 8602, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "random_proportions", "metric_values": { - "r2": -0.5527 + "r2": -0.5422 }, "scaled_scores": { "r2": 0 @@ -327,97 +312,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5.7, - "cpu_pct": 93.3, - "peak_memory_mb": 2970, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6.6, + "cpu_pct": 152.5, + "peak_memory_mb": 7783, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "rctd", "metric_values": { - "r2": 0.2005 + "r2": 0.2041 }, "scaled_scores": { - "r2": 0.4851 + "r2": 0.4839 }, - "mean_score": 0.4851, + "mean_score": 0.4839, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 728, - "cpu_pct": 69.2, - "peak_memory_mb": 59085, - "disk_read_mb": 1844, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 1311, + "cpu_pct": 27, + "peak_memory_mb": 62772, + "disk_read_mb": 2663, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "seurat", "metric_values": { - "r2": -3.4424 + "r2": -4.3898 }, "scaled_scores": { - "r2": -1.8611 + "r2": -2.4949 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2903, - "cpu_pct": 99.9, - "peak_memory_mb": 76186, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3488, + "cpu_pct": 100.5, + "peak_memory_mb": 78951, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "stereoscope", "metric_values": { - "r2": 0.0776 + "r2": 0.4011 }, "scaled_scores": { - "r2": 0.4059 + "r2": 0.6116 }, - "mean_score": 0.4059, + "mean_score": 0.6116, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2623, - "cpu_pct": 100.5, - "peak_memory_mb": 20480, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 1865, + "cpu_pct": 101.1, + "peak_memory_mb": 18944, + "disk_read_mb": 2356, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "tangram", "metric_values": { - "r2": -1.1092 + "r2": -1.1312 }, "scaled_scores": { - "r2": -0.3584 + "r2": -0.3819 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 520, - "cpu_pct": 1190.8, - "peak_memory_mb": 17408, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2518, + "cpu_pct": 2336.1, + "peak_memory_mb": 27956, + "disk_read_mb": 2356, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", @@ -432,355 +412,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 8.7, - "cpu_pct": 100.6, - "peak_memory_mb": 5018, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8.1, + "cpu_pct": 161.4, + "peak_memory_mb": 7885, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/gtex_v9", "method_id": "vanillanmf", "metric_values": { - "r2": -1.6403 + "r2": 0.116 }, "scaled_scores": { - "r2": -0.7005 + "r2": 0.4268 }, - "mean_score": 0, + "mean_score": 0.4268, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 76, - "cpu_pct": 592.2, - "peak_memory_mb": 5632, - "disk_read_mb": 1536, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "cell2location", - "metric_values": { - "r2": -0.1785 - }, - "scaled_scores": { - "r2": 0.2609 - }, - "mean_score": 0.2609, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 3455, - "cpu_pct": 1588, - "peak_memory_mb": 24372, - "disk_read_mb": 8909, - "disk_write_mb": 13 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "destvi", - "metric_values": { - "r2": "NA" - }, - "scaled_scores": { - "r2": 0 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 143, - "duration_sec": 28801, - "cpu_pct": "NA", - "peak_memory_mb": "NA", - "disk_read_mb": "NA", - "disk_write_mb": "NA" - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "nmfreg", - "metric_values": { - "r2": -2.9522 - }, - "scaled_scores": { - "r2": -1.4786 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 7447, - "cpu_pct": 100.3, - "peak_memory_mb": 66970, - "disk_read_mb": 8807, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "nnls", - "metric_values": { - "r2": -0.9785 - }, - "scaled_scores": { - "r2": -0.2408 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 27.1, - "cpu_pct": 275.2, - "peak_memory_mb": 17306, - "disk_read_mb": 8704, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "random_proportions", - "metric_values": { - "r2": -0.5945 - }, - "scaled_scores": { - "r2": 0 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 24, - "cpu_pct": 68.9, - "peak_memory_mb": 12288, - "disk_read_mb": 8704, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "rctd", - "metric_values": { - "r2": -0.1235 - }, - "scaled_scores": { - "r2": 0.2954 - }, - "mean_score": 0.2954, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 1132, - "cpu_pct": 82.8, - "peak_memory_mb": 174490, - "disk_read_mb": 9114, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "seurat", - "metric_values": { - "r2": -1.6325 - }, - "scaled_scores": { - "r2": -0.651 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 10671, - "cpu_pct": 100.2, - "peak_memory_mb": 306279, - "disk_read_mb": 8807, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "stereoscope", - "metric_values": { - "r2": 0.0418 - }, - "scaled_scores": { - "r2": 0.3991 - }, - "mean_score": 0.3991, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 7138, - "cpu_pct": 100.1, - "peak_memory_mb": 23450, - "disk_read_mb": 8807, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "tangram", - "metric_values": { - "r2": -1.0983 - }, - "scaled_scores": { - "r2": -0.3159 - }, - "mean_score": 0, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 1363, - "cpu_pct": 842, - "peak_memory_mb": 42599, - "disk_read_mb": 8807, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "true_proportions", - "metric_values": { - "r2": 1 - }, - "scaled_scores": { - "r2": 1 - }, - "mean_score": 1, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 16, - "cpu_pct": 95.2, - "peak_memory_mb": 12288, - "disk_read_mb": 8704, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" - }, - { - "dataset_id": "cellxgene_census/hcla", - "method_id": "vanillanmf", - "metric_values": { - "r2": -0.1836 - }, - "scaled_scores": { - "r2": 0.2577 - }, - "mean_score": 0.2577, - "normalization_id": "log_cp10k", - "resources": { - "exit_code": 0, - "duration_sec": 35.6, - "cpu_pct": 925.3, - "peak_memory_mb": 16692, - "disk_read_mb": 8807, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 27, + "cpu_pct": 2377.1, + "peak_memory_mb": 8807, + "disk_read_mb": 2253, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "cell2location", "metric_values": { - "r2": 0.5583 + "r2": 0.5426 }, "scaled_scores": { - "r2": 0.8529 + "r2": 0.8624 }, - "mean_score": 0.8529, + "mean_score": 0.8624, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3902, - "cpu_pct": 1965.9, - "peak_memory_mb": 27648, - "disk_read_mb": 6452, - "disk_write_mb": 13 - }, - "task_id": "spatial_decomposition" + "duration_sec": 4773, + "cpu_pct": 100, + "peak_memory_mb": 39629, + "disk_read_mb": 9626, + "disk_write_mb": 18 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "destvi", "metric_values": { - "r2": "NA" + "r2": 0.5038 }, "scaled_scores": { - "r2": 0 + "r2": 0.8507 }, - "mean_score": 0, + "mean_score": 0.8507, "normalization_id": "log_cp10k", "resources": { - "exit_code": 143, - "duration_sec": 28811, - "cpu_pct": "NA", - "peak_memory_mb": "NA", - "disk_read_mb": "NA", - "disk_write_mb": "NA" - }, - "task_id": "spatial_decomposition" + "exit_code": 0, + "duration_sec": 32660, + "cpu_pct": 101.2, + "peak_memory_mb": 30208, + "disk_read_mb": 9626, + "disk_write_mb": 11 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "nmfreg", "metric_values": { - "r2": -1.3546 + "r2": -1.4988 }, "scaled_scores": { - "r2": 0.2161 + "r2": 0.2484 }, - "mean_score": 0.2161, + "mean_score": 0.2484, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5121, - "cpu_pct": 101, - "peak_memory_mb": 51098, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 11062, + "cpu_pct": 109.2, + "peak_memory_mb": 65741, + "disk_read_mb": 9524, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "nnls", "metric_values": { - "r2": 0.1169 + "r2": 0.1629 }, "scaled_scores": { - "r2": 0.706 + "r2": 0.7482 }, - "mean_score": 0.706, + "mean_score": 0.7482, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 22.5, - "cpu_pct": 163, - "peak_memory_mb": 18740, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 35.5, + "cpu_pct": 1461.6, + "peak_memory_mb": 34919, + "disk_read_mb": 9524, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "random_proportions", "metric_values": { - "r2": -2.0036 + "r2": -2.3244 }, "scaled_scores": { "r2": 0 @@ -789,97 +532,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 11.6, - "cpu_pct": 111.3, - "peak_memory_mb": 9216, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8.9, + "cpu_pct": 151.2, + "peak_memory_mb": 13824, + "disk_read_mb": 9524, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "rctd", "metric_values": { - "r2": 0.5427 + "r2": 0.5418 }, "scaled_scores": { - "r2": 0.8478 + "r2": 0.8622 }, - "mean_score": 0.8478, + "mean_score": 0.8622, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 763, - "cpu_pct": 80.2, - "peak_memory_mb": 159949, - "disk_read_mb": 6759, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 1168, + "cpu_pct": 75.1, + "peak_memory_mb": 163533, + "disk_read_mb": 9933, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "seurat", "metric_values": { - "r2": -1.594 + "r2": -3.0248 }, "scaled_scores": { - "r2": 0.1364 + "r2": -0.2107 }, - "mean_score": 0.1364, + "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 8824, + "duration_sec": 8375, "cpu_pct": 100.2, - "peak_memory_mb": 196404, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "peak_memory_mb": 198247, + "disk_read_mb": 9626, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "stereoscope", "metric_values": { - "r2": 0.1387 + "r2": 0.4991 }, "scaled_scores": { - "r2": 0.7132 + "r2": 0.8493 }, - "mean_score": 0.7132, + "mean_score": 0.8493, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 7269, - "cpu_pct": 100.1, - "peak_memory_mb": 21197, - "disk_read_mb": 6452, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 4372, + "cpu_pct": 100.4, + "peak_memory_mb": 25805, + "disk_read_mb": 9626, + "disk_write_mb": 7 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "tangram", "metric_values": { - "r2": -2.3183 + "r2": -2.8906 }, "scaled_scores": { - "r2": -0.1048 + "r2": -0.1703 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 727, - "cpu_pct": 1483.1, - "peak_memory_mb": 32052, - "disk_read_mb": 6452, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6651, + "cpu_pct": 2145.8, + "peak_memory_mb": 51610, + "disk_read_mb": 9626, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", @@ -894,124 +632,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 12.4, - "cpu_pct": 113.1, - "peak_memory_mb": 9933, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 11.7, + "cpu_pct": 162.9, + "peak_memory_mb": 15156, + "disk_read_mb": 9524, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/hypomap", "method_id": "vanillanmf", "metric_values": { - "r2": -1.0822 + "r2": 0.2123 }, "scaled_scores": { - "r2": 0.3068 + "r2": 0.7631 }, - "mean_score": 0.3068, + "mean_score": 0.7631, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 34.3, - "cpu_pct": 1669.1, - "peak_memory_mb": 23143, - "disk_read_mb": 6349, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 44.8, + "cpu_pct": 1692.5, + "peak_memory_mb": 34919, + "disk_read_mb": 9524, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "cell2location", "metric_values": { - "r2": -0.0525 + "r2": -0.0761 }, "scaled_scores": { - "r2": 0.2079 + "r2": 0.1927 }, - "mean_score": 0.2079, + "mean_score": 0.1927, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3052, - "cpu_pct": 1932.5, - "peak_memory_mb": 20992, - "disk_read_mb": 5018, - "disk_write_mb": 11 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3552, + "cpu_pct": 99.7, + "peak_memory_mb": 26112, + "disk_read_mb": 7373, + "disk_write_mb": 17 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "destvi", "metric_values": { - "r2": -0.9322 + "r2": -0.7598 }, "scaled_scores": { - "r2": -0.4542 + "r2": -0.3202 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 24795, - "cpu_pct": 101.3, - "peak_memory_mb": 24679, - "disk_read_mb": 4916, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 24467, + "cpu_pct": 101.2, + "peak_memory_mb": 24064, + "disk_read_mb": 7373, + "disk_write_mb": 9 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "nmfreg", "metric_values": { - "r2": -1.0756 + "r2": -0.8248 }, "scaled_scores": { - "r2": -0.5621 + "r2": -0.369 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3441, - "cpu_pct": 100.9, - "peak_memory_mb": 40141, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8674, + "cpu_pct": 130.4, + "peak_memory_mb": 51917, + "disk_read_mb": 7373, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "nnls", "metric_values": { - "r2": -2.054 + "r2": -1.6263 }, "scaled_scores": { - "r2": -1.2984 + "r2": -0.9702 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 17.1, - "cpu_pct": 320.7, - "peak_memory_mb": 10036, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 44.7, + "cpu_pct": 2381.6, + "peak_memory_mb": 15258, + "disk_read_mb": 7373, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "random_proportions", "metric_values": { - "r2": -0.3287 + "r2": -0.333 }, "scaled_scores": { "r2": 0 @@ -1020,97 +752,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 13, - "cpu_pct": 95, - "peak_memory_mb": 8397, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6.1, + "cpu_pct": 165.5, + "peak_memory_mb": 12903, + "disk_read_mb": 7373, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "rctd", "metric_values": { - "r2": -0.7704 + "r2": -0.7286 }, "scaled_scores": { - "r2": -0.3324 + "r2": -0.2968 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 816, - "cpu_pct": 81.3, - "peak_memory_mb": 98816, - "disk_read_mb": 5325, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 1377, + "cpu_pct": 64.3, + "peak_memory_mb": 103220, + "disk_read_mb": 7783, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "seurat", "metric_values": { - "r2": -2.8999 + "r2": -4.5616 }, "scaled_scores": { - "r2": -1.9351 + "r2": -3.1724 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5801, + "duration_sec": 6126, "cpu_pct": 100.3, - "peak_memory_mb": 152884, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "peak_memory_mb": 157184, + "disk_read_mb": 7373, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "stereoscope", "metric_values": { - "r2": 0.0196 + "r2": 0.07 }, "scaled_scores": { - "r2": 0.2621 + "r2": 0.3023 }, - "mean_score": 0.2621, + "mean_score": 0.3023, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 4031, - "cpu_pct": 99.8, - "peak_memory_mb": 23860, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3060, + "cpu_pct": 100.5, + "peak_memory_mb": 24064, + "disk_read_mb": 7373, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "tangram", "metric_values": { - "r2": -0.8396 + "r2": -0.8496 }, "scaled_scores": { - "r2": -0.3845 + "r2": -0.3875 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 655, - "cpu_pct": 924.6, - "peak_memory_mb": 26010, - "disk_read_mb": 4916, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 7168, + "cpu_pct": 3020.8, + "peak_memory_mb": 46080, + "disk_read_mb": 7373, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", @@ -1125,124 +852,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 8.5, - "cpu_pct": 147, - "peak_memory_mb": 8397, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8.1, + "cpu_pct": 186.5, + "peak_memory_mb": 12903, + "disk_read_mb": 7373, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/immune_cell_atlas", "method_id": "vanillanmf", "metric_values": { - "r2": -0.1929 + "r2": 0.0469 }, "scaled_scores": { - "r2": 0.1022 + "r2": 0.285 }, - "mean_score": 0.1022, + "mean_score": 0.285, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 25.1, - "cpu_pct": 937, - "peak_memory_mb": 10138, - "disk_read_mb": 4916, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 29.4, + "cpu_pct": 1282.4, + "peak_memory_mb": 15360, + "disk_read_mb": 7373, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "cell2location", "metric_values": { - "r2": 0.1468 + "r2": 0.1889 }, "scaled_scores": { - "r2": 0.5045 + "r2": 0.5519 }, - "mean_score": 0.5045, + "mean_score": 0.5519, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3257, - "cpu_pct": 1457.4, - "peak_memory_mb": 22631, - "disk_read_mb": 6759, - "disk_write_mb": 13 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3571, + "cpu_pct": 99.7, + "peak_memory_mb": 33178, + "disk_read_mb": 10036, + "disk_write_mb": 16 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "destvi", "metric_values": { - "r2": -0.3556 + "r2": -0.2948 }, "scaled_scores": { - "r2": 0.2127 + "r2": 0.2846 }, - "mean_score": 0.2127, + "mean_score": 0.2846, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 20789, - "cpu_pct": 101, - "peak_memory_mb": 26215, - "disk_read_mb": 6656, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 19176, + "cpu_pct": 102.4, + "peak_memory_mb": 30004, + "disk_read_mb": 10036, + "disk_write_mb": 8 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "nmfreg", "metric_values": { - "r2": -0.4976 + "r2": -0.426 }, "scaled_scores": { - "r2": 0.1302 + "r2": 0.2121 }, - "mean_score": 0.1302, + "mean_score": 0.2121, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5057, - "cpu_pct": 100.8, - "peak_memory_mb": 53146, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 10209, + "cpu_pct": 110.4, + "peak_memory_mb": 68404, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "nnls", "metric_values": { - "r2": -0.9455 + "r2": -0.5531 }, "scaled_scores": { - "r2": -0.13 + "r2": 0.1419 }, - "mean_score": 0, + "mean_score": 0.1419, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 20.4, - "cpu_pct": 196.8, - "peak_memory_mb": 15975, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 18.1, + "cpu_pct": 445.9, + "peak_memory_mb": 25703, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "random_proportions", "metric_values": { - "r2": -0.7217 + "r2": -0.81 }, "scaled_scores": { "r2": 0 @@ -1251,97 +972,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 13.7, - "cpu_pct": 98.9, - "peak_memory_mb": 10138, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 12.3, + "cpu_pct": 156.7, + "peak_memory_mb": 15565, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "rctd", "metric_values": { - "r2": -0.4137 + "r2": -0.3459 }, "scaled_scores": { - "r2": 0.1789 + "r2": 0.2564 }, - "mean_score": 0.1789, + "mean_score": 0.2564, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 614, - "cpu_pct": 77.1, - "peak_memory_mb": 87655, - "disk_read_mb": 7066, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 946, + "cpu_pct": 72.4, + "peak_memory_mb": 93184, + "disk_read_mb": 10343, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "seurat", "metric_values": { - "r2": -5.9876 + "r2": -2.7328 }, "scaled_scores": { - "r2": -3.0585 + "r2": -1.0624 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5620, + "duration_sec": 5778, "cpu_pct": 100.3, - "peak_memory_mb": 184320, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "peak_memory_mb": 161280, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "stereoscope", "metric_values": { - "r2": 0.0408 + "r2": 0.3296 }, "scaled_scores": { - "r2": 0.4429 + "r2": 0.6296 }, - "mean_score": 0.4429, + "mean_score": 0.6296, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3205, - "cpu_pct": 100.8, - "peak_memory_mb": 32564, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2730, + "cpu_pct": 100.7, + "peak_memory_mb": 25703, + "disk_read_mb": 10036, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "tangram", "metric_values": { - "r2": -2.2135 + "r2": -1.6435 }, "scaled_scores": { - "r2": -0.8664 + "r2": -0.4605 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 444, - "cpu_pct": 977.8, - "peak_memory_mb": 33383, - "disk_read_mb": 6656, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 5016, + "cpu_pct": 3305.2, + "peak_memory_mb": 55604, + "disk_read_mb": 10036, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", @@ -1356,124 +1072,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 11.5, - "cpu_pct": 111.4, - "peak_memory_mb": 9524, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8.9, + "cpu_pct": 118.1, + "peak_memory_mb": 12903, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/mouse_pancreas_atlas", "method_id": "vanillanmf", "metric_values": { - "r2": 0.1789 + "r2": 0.1196 }, "scaled_scores": { - "r2": 0.5231 + "r2": 0.5136 }, - "mean_score": 0.5231, + "mean_score": 0.5136, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 22.8, - "cpu_pct": 302, - "peak_memory_mb": 18125, - "disk_read_mb": 6656, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 31.9, + "cpu_pct": 1054.8, + "peak_memory_mb": 28468, + "disk_read_mb": 9933, + "disk_write_mb": 4 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "cell2location", "metric_values": { - "r2": -5.0765 + "r2": -4.6432 }, "scaled_scores": { - "r2": -3.4575 + "r2": -3.3126 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 6661, - "cpu_pct": 1384.1, - "peak_memory_mb": 24372, - "disk_read_mb": 9831, - "disk_write_mb": 14 - }, - "task_id": "spatial_decomposition" + "duration_sec": 5707, + "cpu_pct": 100, + "peak_memory_mb": 37991, + "disk_read_mb": 14644, + "disk_write_mb": 18 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "destvi", "metric_values": { - "r2": "NA" + "r2": -1.1979 }, "scaled_scores": { - "r2": 0 + "r2": -0.6797 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { - "exit_code": 143, - "duration_sec": 28801, - "cpu_pct": "NA", - "peak_memory_mb": "NA", - "disk_read_mb": "NA", - "disk_write_mb": "NA" - }, - "task_id": "spatial_decomposition" + "exit_code": 0, + "duration_sec": 73886, + "cpu_pct": 101.7, + "peak_memory_mb": 44340, + "disk_read_mb": 14644, + "disk_write_mb": 10 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "nmfreg", "metric_values": { - "r2": -3.3984 + "r2": -2.7027 }, "scaled_scores": { - "r2": -2.2265 + "r2": -1.8296 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 6617, - "cpu_pct": 100.8, - "peak_memory_mb": 76084, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 14021, + "cpu_pct": 110.1, + "peak_memory_mb": 97485, + "disk_read_mb": 14541, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "nnls", "metric_values": { - "r2": -4.9846 + "r2": -4.0492 }, "scaled_scores": { - "r2": -3.3901 + "r2": -2.8586 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 42.7, - "cpu_pct": 1382, - "peak_memory_mb": 15872, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 85, + "cpu_pct": 4530.9, + "peak_memory_mb": 24064, + "disk_read_mb": 14541, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "random_proportions", "metric_values": { - "r2": -0.3632 + "r2": -0.3086 }, "scaled_scores": { "r2": 0 @@ -1482,97 +1192,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 16.9, - "cpu_pct": 96, - "peak_memory_mb": 13210, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8.5, + "cpu_pct": 161.5, + "peak_memory_mb": 20173, + "disk_read_mb": 14541, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "rctd", "metric_values": { - "r2": "NA" + "r2": -3.6296 }, "scaled_scores": { - "r2": 0 + "r2": -2.5379 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { - "exit_code": 1, - "duration_sec": 250, - "cpu_pct": "NA", - "peak_memory_mb": "NA", - "disk_read_mb": "NA", - "disk_write_mb": "NA" - }, - "task_id": "spatial_decomposition" + "exit_code": 0, + "duration_sec": 4210, + "cpu_pct": 65.9, + "peak_memory_mb": 284263, + "disk_read_mb": 14951, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "seurat", "metric_values": { - "r2": -3.4867 + "r2": -4.1736 }, "scaled_scores": { - "r2": -2.2913 + "r2": -2.9536 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 13647, + "duration_sec": 13780, "cpu_pct": 100.1, - "peak_memory_mb": 267367, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "peak_memory_mb": 272077, + "disk_read_mb": 14541, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "stereoscope", "metric_values": { - "r2": -0.0208 + "r2": -0.357 }, "scaled_scores": { - "r2": 0.2512 + "r2": -0.037 }, - "mean_score": 0.2512, + "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 17284, - "cpu_pct": 100.2, - "peak_memory_mb": 29082, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 9179, + "cpu_pct": 100.4, + "peak_memory_mb": 33588, + "disk_read_mb": 14644, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "tangram", "metric_values": { - "r2": -1.3411 + "r2": -1.3517 }, "scaled_scores": { - "r2": -0.7173 + "r2": -0.7971 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2590, - "cpu_pct": 960.9, - "peak_memory_mb": 56423, - "disk_read_mb": 9728, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 7679, + "cpu_pct": 1312.5, + "peak_memory_mb": 72500, + "disk_read_mb": 14644, + "disk_write_mb": 6 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", @@ -1587,124 +1292,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 16.1, - "cpu_pct": 96.4, - "peak_memory_mb": 13210, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 10.2, + "cpu_pct": 115.5, + "peak_memory_mb": 17511, + "disk_read_mb": 14541, + "disk_write_mb": 5 + } }, { "dataset_id": "cellxgene_census/tabula_sapiens", "method_id": "vanillanmf", "metric_values": { - "r2": -0.0813 + "r2": 0.0136 }, "scaled_scores": { - "r2": 0.2068 + "r2": 0.2462 }, - "mean_score": 0.2068, + "mean_score": 0.2462, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 38.5, - "cpu_pct": 953.5, - "peak_memory_mb": 15975, - "disk_read_mb": 9728, - "disk_write_mb": 3 - }, - "task_id": "spatial_decomposition" + "duration_sec": 117, + "cpu_pct": 1971, + "peak_memory_mb": 24167, + "disk_read_mb": 14541, + "disk_write_mb": 6 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "cell2location", "metric_values": { - "r2": -0.7173 + "r2": -0.5529 }, "scaled_scores": { - "r2": -0.4653 + "r2": -0.3238 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2744, - "cpu_pct": 1945.6, - "peak_memory_mb": 19354, - "disk_read_mb": 496, - "disk_write_mb": 11 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2901, + "cpu_pct": 99.6, + "peak_memory_mb": 21300, + "disk_read_mb": 641, + "disk_write_mb": 15 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "destvi", "metric_values": { - "r2": -0.5461 + "r2": -0.1919 }, "scaled_scores": { - "r2": -0.3193 + "r2": -0.0161 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 7149, - "cpu_pct": 112.9, - "peak_memory_mb": 28468, - "disk_read_mb": 438, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 19218, + "cpu_pct": 102.1, + "peak_memory_mb": 19866, + "disk_read_mb": 637, + "disk_write_mb": 9 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "nmfreg", "metric_values": { - "r2": -1.9976 + "r2": -1.794 }, "scaled_scores": { - "r2": -1.5579 + "r2": -1.3819 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 126, - "cpu_pct": 133, - "peak_memory_mb": 6247, - "disk_read_mb": 393, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 329, + "cpu_pct": 468.6, + "peak_memory_mb": 9012, + "disk_read_mb": 581, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "nnls", "metric_values": { - "r2": -0.908 + "r2": -0.7215 }, "scaled_scores": { - "r2": -0.6281 + "r2": -0.4676 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 7.6, - "cpu_pct": 2372.4, - "peak_memory_mb": 4096, - "disk_read_mb": 383, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 247, + "cpu_pct": 3511, + "peak_memory_mb": 6247, + "disk_read_mb": 570, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "random_proportions", "metric_values": { - "r2": -0.1719 + "r2": -0.173 }, "scaled_scores": { "r2": 0 @@ -1713,97 +1412,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 421.9, - "peak_memory_mb": 1741, - "disk_read_mb": 383, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 5.2, + "cpu_pct": 162.3, + "peak_memory_mb": 4199, + "disk_read_mb": 569, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "rctd", "metric_values": { - "r2": -0.5507 + "r2": -0.3095 }, "scaled_scores": { - "r2": -0.3232 + "r2": -0.1163 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 935, - "cpu_pct": 29.3, - "peak_memory_mb": 22836, - "disk_read_mb": 784, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 8962, + "cpu_pct": 6.9, + "peak_memory_mb": 25191, + "disk_read_mb": 973, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "seurat", "metric_values": { - "r2": -2.3645 + "r2": -3.5128 }, "scaled_scores": { - "r2": -1.871 + "r2": -2.8472 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 1467, - "cpu_pct": 100, - "peak_memory_mb": 35021, - "disk_read_mb": 419, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2212, + "cpu_pct": 100.4, + "peak_memory_mb": 37581, + "disk_read_mb": 607, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "stereoscope", "metric_values": { - "r2": 0.0884 + "r2": 0.2483 }, "scaled_scores": { - "r2": 0.2221 + "r2": 0.3591 }, - "mean_score": 0.2221, + "mean_score": 0.3591, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 1060, - "cpu_pct": 101.5, - "peak_memory_mb": 18637, - "disk_read_mb": 438, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 837, + "cpu_pct": 102.2, + "peak_memory_mb": 17306, + "disk_read_mb": 637, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "tangram", "metric_values": { - "r2": -0.6944 + "r2": -0.7656 }, "scaled_scores": { - "r2": -0.4459 + "r2": -0.5051 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 364, - "cpu_pct": 1540.1, - "peak_memory_mb": 13005, - "disk_read_mb": 449, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3420, + "cpu_pct": 3652.6, + "peak_memory_mb": 23450, + "disk_read_mb": 641, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/cengen", @@ -1818,124 +1512,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2.2, - "cpu_pct": 367.6, - "peak_memory_mb": 3892, - "disk_read_mb": 383, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2.3, + "cpu_pct": 361.8, + "peak_memory_mb": 6144, + "disk_read_mb": 583, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/cengen", "method_id": "vanillanmf", "metric_values": { - "r2": 0.0452 + "r2": 0.0724 }, "scaled_scores": { - "r2": 0.1853 + "r2": 0.2092 }, - "mean_score": 0.1853, + "mean_score": 0.2092, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 14.2, - "cpu_pct": 1691.7, - "peak_memory_mb": 3482, - "disk_read_mb": 392, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 12.9, + "cpu_pct": 3628, + "peak_memory_mb": 6964, + "disk_read_mb": 580, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "cell2location", "metric_values": { - "r2": -0.0635 + "r2": -0.4828 }, "scaled_scores": { - "r2": 0.4923 + "r2": 0.269 }, - "mean_score": 0.4923, + "mean_score": 0.269, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2101, - "cpu_pct": 1939.5, - "peak_memory_mb": 16077, - "disk_read_mb": 530, - "disk_write_mb": 10 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2581, + "cpu_pct": 99.6, + "peak_memory_mb": 15975, + "disk_read_mb": 695, + "disk_write_mb": 13 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "destvi", "metric_values": { - "r2": -2.3364 + "r2": -3.415 }, "scaled_scores": { - "r2": -0.5927 + "r2": -1.1763 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2616, - "cpu_pct": 101.8, - "peak_memory_mb": 20173, - "disk_read_mb": 472, - "disk_write_mb": 5 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3928, + "cpu_pct": 101.1, + "peak_memory_mb": 16077, + "disk_read_mb": 691, + "disk_write_mb": 8 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "nmfreg", "metric_values": { - "r2": -1.3268 + "r2": -1.1123 }, "scaled_scores": { - "r2": -0.1107 + "r2": -0.0412 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 252, - "cpu_pct": 117.4, - "peak_memory_mb": 6554, - "disk_read_mb": 427, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 585, + "cpu_pct": 207.4, + "peak_memory_mb": 9421, + "disk_read_mb": 635, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "nnls", "metric_values": { - "r2": -2.5906 + "r2": -2.7262 }, "scaled_scores": { - "r2": -0.714 + "r2": -0.8368 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 21.1, - "cpu_pct": 134.4, - "peak_memory_mb": 77, - "disk_read_mb": 416, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 14.1, + "cpu_pct": 2228, + "peak_memory_mb": 6656, + "disk_read_mb": 624, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "random_proportions", "metric_values": { - "r2": -1.0948 + "r2": -1.0286 }, "scaled_scores": { "r2": 0 @@ -1944,97 +1632,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3.2, - "cpu_pct": 313, - "peak_memory_mb": 3892, - "disk_read_mb": 417, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2.9, + "cpu_pct": 432.7, + "peak_memory_mb": 6144, + "disk_read_mb": 623, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "rctd", "metric_values": { - "r2": -2.7278 + "r2": -3.6914 }, "scaled_scores": { - "r2": -0.7795 + "r2": -1.3126 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 196, - "cpu_pct": 50.3, - "peak_memory_mb": 9728, - "disk_read_mb": 817, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 596, + "cpu_pct": 58.8, + "peak_memory_mb": 12084, + "disk_read_mb": 1024, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "seurat", "metric_values": { - "r2": -1.9947 + "r2": -4.97 }, "scaled_scores": { - "r2": -0.4296 + "r2": -1.9429 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 753, - "cpu_pct": 101.1, - "peak_memory_mb": 17306, - "disk_read_mb": 452, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 518, + "cpu_pct": 101.9, + "peak_memory_mb": 19149, + "disk_read_mb": 660, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "stereoscope", "metric_values": { - "r2": 0.0036 + "r2": -0.5802 }, "scaled_scores": { - "r2": 0.5244 + "r2": 0.221 }, - "mean_score": 0.5244, + "mean_score": 0.221, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 238, - "cpu_pct": 115.5, - "peak_memory_mb": 26215, - "disk_read_mb": 472, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 324, + "cpu_pct": 103.9, + "peak_memory_mb": 14644, + "disk_read_mb": 691, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "tangram", "metric_values": { - "r2": -1.471 + "r2": -1.6185 }, "scaled_scores": { - "r2": -0.1796 + "r2": -0.2908 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 63, - "cpu_pct": 1452.4, - "peak_memory_mb": 9216, - "disk_read_mb": 482, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 517, + "cpu_pct": 2031.1, + "peak_memory_mb": 15975, + "disk_read_mb": 695, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/immune_cells", @@ -2049,124 +1732,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 424.1, - "peak_memory_mb": 1741, - "disk_read_mb": 417, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 4.6, + "cpu_pct": 160.6, + "peak_memory_mb": 3482, + "disk_read_mb": 636, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/immune_cells", "method_id": "vanillanmf", "metric_values": { - "r2": -0.2135 + "r2": -0.1062 }, "scaled_scores": { - "r2": 0.4207 + "r2": 0.4547 }, - "mean_score": 0.4207, + "mean_score": 0.4547, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5.2, - "cpu_pct": 1454.7, - "peak_memory_mb": 4301, - "disk_read_mb": 426, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 21.8, + "cpu_pct": 2689.9, + "peak_memory_mb": 6759, + "disk_read_mb": 633, + "disk_write_mb": 3 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "cell2location", "metric_values": { - "r2": -1.6758 + "r2": -1.5081 }, "scaled_scores": { - "r2": -0.2627 + "r2": -0.1819 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2358, - "cpu_pct": 1543.3, - "peak_memory_mb": 20480, - "disk_read_mb": 561, - "disk_write_mb": 11 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2928, + "cpu_pct": 99.7, + "peak_memory_mb": 16384, + "disk_read_mb": 747, + "disk_write_mb": 14 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "destvi", "metric_values": { - "r2": -0.7201 + "r2": -0.4357 }, "scaled_scores": { - "r2": 0.1883 + "r2": 0.3234 }, - "mean_score": 0.1883, + "mean_score": 0.3234, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2205, - "cpu_pct": 100.7, - "peak_memory_mb": 15565, - "disk_read_mb": 503, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3786, + "cpu_pct": 101.3, + "peak_memory_mb": 18125, + "disk_read_mb": 743, + "disk_write_mb": 9 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "nmfreg", "metric_values": { - "r2": -1.1982 + "r2": -1.4856 }, "scaled_scores": { - "r2": -0.0373 + "r2": -0.1713 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 340, - "cpu_pct": 109.6, - "peak_memory_mb": 6144, - "disk_read_mb": 458, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 708, + "cpu_pct": 534, + "peak_memory_mb": 9728, + "disk_read_mb": 687, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "nnls", "metric_values": { - "r2": -2.0492 + "r2": -2.0061 }, "scaled_scores": { - "r2": -0.4389 + "r2": -0.4166 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 6.7, - "cpu_pct": 328.8, - "peak_memory_mb": 3789, - "disk_read_mb": 448, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 6.2, + "cpu_pct": 2127.4, + "peak_memory_mb": 6964, + "disk_read_mb": 676, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "random_proportions", "metric_values": { - "r2": -1.1191 + "r2": -1.1221 }, "scaled_scores": { "r2": 0 @@ -2175,97 +1852,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 380.2, - "peak_memory_mb": 1434, - "disk_read_mb": 448, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3.8, + "cpu_pct": 226.3, + "peak_memory_mb": 6247, + "disk_read_mb": 675, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "rctd", "metric_values": { - "r2": -1.2913 + "r2": -1.3697 }, "scaled_scores": { - "r2": -0.0813 + "r2": -0.1167 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 180, - "cpu_pct": 47.3, - "peak_memory_mb": 9728, - "disk_read_mb": 848, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 397, + "cpu_pct": 58.1, + "peak_memory_mb": 12800, + "disk_read_mb": 1127, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "seurat", "metric_values": { - "r2": -2.208 + "r2": -3.5576 }, "scaled_scores": { - "r2": -0.5138 + "r2": -1.1477 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 544, + "duration_sec": 732, "cpu_pct": 101.9, - "peak_memory_mb": 13210, - "disk_read_mb": 484, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "peak_memory_mb": 15463, + "disk_read_mb": 713, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "stereoscope", "metric_values": { - "r2": 0.0469 + "r2": -0.3236 }, "scaled_scores": { - "r2": 0.5502 + "r2": 0.3763 }, - "mean_score": 0.5502, + "mean_score": 0.3763, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 159, - "cpu_pct": 99.8, - "peak_memory_mb": 18944, - "disk_read_mb": 503, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 246, + "cpu_pct": 98.9, + "peak_memory_mb": 16180, + "disk_read_mb": 743, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "tangram", "metric_values": { - "r2": -1.6281 + "r2": -2.0109 }, "scaled_scores": { - "r2": -0.2402 + "r2": -0.4188 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 49.4, - "cpu_pct": 882.1, - "peak_memory_mb": 8090, - "disk_read_mb": 513, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 156, + "cpu_pct": 2656.5, + "peak_memory_mb": 16077, + "disk_read_mb": 747, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/pancreas", @@ -2280,124 +1952,118 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 381.1, - "peak_memory_mb": 1434, - "disk_read_mb": 448, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2.1, + "cpu_pct": 592.9, + "peak_memory_mb": 2765, + "disk_read_mb": 693, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/pancreas", "method_id": "vanillanmf", "metric_values": { - "r2": -0.86 + "r2": 0.0768 }, "scaled_scores": { - "r2": 0.1223 + "r2": 0.565 }, - "mean_score": 0.1223, + "mean_score": 0.565, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 5.7, - "cpu_pct": 1512.8, - "peak_memory_mb": 4506, - "disk_read_mb": 457, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 19.9, + "cpu_pct": 2753.6, + "peak_memory_mb": 6964, + "disk_read_mb": 686, + "disk_write_mb": 4 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "cell2location", "metric_values": { - "r2": 0.0162 + "r2": -0.0843 }, "scaled_scores": { - "r2": 0.43 + "r2": 0.2797 }, - "mean_score": 0.43, + "mean_score": 0.2797, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3058, - "cpu_pct": 1814.9, - "peak_memory_mb": 16589, - "disk_read_mb": 515, - "disk_write_mb": 11 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3247, + "cpu_pct": 99.9, + "peak_memory_mb": 16896, + "disk_read_mb": 676, + "disk_write_mb": 16 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "destvi", "metric_values": { - "r2": -0.1616 + "r2": -0.0323 }, "scaled_scores": { - "r2": 0.3269 + "r2": 0.3143 }, - "mean_score": 0.3269, + "mean_score": 0.3143, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3179, - "cpu_pct": 104.3, - "peak_memory_mb": 27853, - "disk_read_mb": 457, - "disk_write_mb": 6 - }, - "task_id": "spatial_decomposition" + "duration_sec": 5994, + "cpu_pct": 100.9, + "peak_memory_mb": 16589, + "disk_read_mb": 672, + "disk_write_mb": 9 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "nmfreg", "metric_values": { - "r2": -1.8065 + "r2": -1.5356 }, "scaled_scores": { - "r2": -0.6262 + "r2": -0.6844 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 259, - "cpu_pct": 176.8, - "peak_memory_mb": 8500, - "disk_read_mb": 412, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 314, + "cpu_pct": 760.9, + "peak_memory_mb": 9216, + "disk_read_mb": 616, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "nnls", "metric_values": { - "r2": -1.2217 + "r2": -0.9402 }, "scaled_scores": { - "r2": -0.2873 + "r2": -0.2888 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 3.7, - "cpu_pct": 1302.9, - "peak_memory_mb": 4199, - "disk_read_mb": 401, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 19.5, + "cpu_pct": 1980.5, + "peak_memory_mb": 6452, + "disk_read_mb": 605, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "random_proportions", "metric_values": { - "r2": -0.7259 + "r2": -0.5054 }, "scaled_scores": { "r2": 0 @@ -2406,97 +2072,92 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 462.3, - "peak_memory_mb": 1741, - "disk_read_mb": 403, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 3.3, + "cpu_pct": 467.7, + "peak_memory_mb": 5940, + "disk_read_mb": 604, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "rctd", "metric_values": { - "r2": -0.2542 + "r2": -0.3375 }, "scaled_scores": { - "r2": 0.2733 + "r2": 0.1115 }, - "mean_score": 0.2733, + "mean_score": 0.1115, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 260, - "cpu_pct": 49.7, - "peak_memory_mb": 12596, - "disk_read_mb": 803, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 776, + "cpu_pct": 51.5, + "peak_memory_mb": 12903, + "disk_read_mb": 1007, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "seurat", "metric_values": { - "r2": -3.6839 + "r2": -3.7479 }, "scaled_scores": { - "r2": -1.7139 + "r2": -2.154 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 602, - "cpu_pct": 102.6, - "peak_memory_mb": 18330, - "disk_read_mb": 438, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 956, + "cpu_pct": 102.2, + "peak_memory_mb": 18432, + "disk_read_mb": 641, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "stereoscope", "metric_values": { - "r2": 0.0091 + "r2": 0.1949 }, "scaled_scores": { - "r2": 0.4258 + "r2": 0.4652 }, - "mean_score": 0.4258, + "mean_score": 0.4652, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 357, - "cpu_pct": 99.6, - "peak_memory_mb": 19968, - "disk_read_mb": 457, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 320, + "cpu_pct": 100.5, + "peak_memory_mb": 18228, + "disk_read_mb": 672, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "tangram", "metric_values": { - "r2": -0.8411 + "r2": -1.1635 }, "scaled_scores": { - "r2": -0.0668 + "r2": -0.4372 }, "mean_score": 0, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 61, - "cpu_pct": 1342.6, - "peak_memory_mb": 9626, - "disk_read_mb": 467, - "disk_write_mb": 1 - }, - "task_id": "spatial_decomposition" + "duration_sec": 633, + "cpu_pct": 2699.6, + "peak_memory_mb": 18228, + "disk_read_mb": 676, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", @@ -2511,33 +2172,31 @@ "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 2, - "cpu_pct": 451.8, - "peak_memory_mb": 1741, - "disk_read_mb": 403, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 2.7, + "cpu_pct": 496.3, + "peak_memory_mb": 6144, + "disk_read_mb": 621, + "disk_write_mb": 5 + } }, { "dataset_id": "openproblems_v1/zebrafish", "method_id": "vanillanmf", "metric_values": { - "r2": -0.5034 + "r2": 0.0572 }, "scaled_scores": { - "r2": 0.1289 + "r2": 0.3737 }, - "mean_score": 0.1289, + "mean_score": 0.3737, "normalization_id": "log_cp10k", "resources": { "exit_code": 0, - "duration_sec": 12.7, - "cpu_pct": 2409, - "peak_memory_mb": 4199, - "disk_read_mb": 411, - "disk_write_mb": 2 - }, - "task_id": "spatial_decomposition" + "duration_sec": 25.7, + "cpu_pct": 1782.9, + "peak_memory_mb": 7066, + "disk_read_mb": 614, + "disk_write_mb": 5 + } } ] diff --git a/results/spatial_decomposition/data/task_info.json b/results/spatial_decomposition/data/task_info.json index e490bb948..7ba1d523c 100644 --- a/results/spatial_decomposition/data/task_info.json +++ b/results/spatial_decomposition/data/task_info.json @@ -1,8 +1,33 @@ { - "task_id": "spatial_decomposition", + "task_id": "task_spatial_decomposition", "commit_sha": null, - "task_name": "Spatial decomposition", + "task_name": "Spatial Decomposition", "task_summary": "Estimation of cell type proportions per spot in 2D space from spatial transcriptomic data coupled with corresponding single-cell data", - "task_description": "Spatial decomposition (also often referred to as Spatial deconvolution) is applicable to spatial transcriptomics data where the transcription profile of each capture location (spot, voxel, bead, etc.) do not share a bijective relationship with the cells in the tissue, i.e., multiple cells may contribute to the same capture location. The task of spatial decomposition then refers to estimating the composition of cell types/states that are present at each capture location. The cell type/states estimates are presented as proportion values, representing the proportion of the cells at each capture location that belong to a given cell type.\n\n\nWe distinguish between _reference-based_ decomposition and _de novo_ decomposition, where the former leverage external data (e.g., scRNA-seq or scNuc-seq) to guide the inference process, while the latter only work with the spatial data. We require that all datasets have an associated reference single cell data set, but methods are free to ignore this information. \nDue to the lack of real datasets with the necessary ground-truth, this task makes use of a simulated dataset generated by creating cell-aggregates by sampling from a Dirichlet distribution. The ground-truth dataset consists of the spatial expression matrix, XY coordinates of the spots, true cell-type proportions for each spot, and the reference single-cell data (from which cell aggregated were simulated).\n", - "repo": "openproblems-bio/openproblems-v2" + "task_description": "Spatial decomposition (also often referred to as Spatial deconvolution) is applicable to spatial transcriptomics data where the transcription profile of each capture location (spot, voxel, bead, etc.) do not share a bijective relationship with the cells in the tissue, i.e., multiple cells may contribute to the same capture location. The task of spatial decomposition then refers to estimating the composition of cell types/states that are present at each capture location. The cell type/states estimates are presented as proportion values, representing the proportion of the cells at each capture location that belong to a given cell type.\n\nWe distinguish between _reference-based_ decomposition and _de novo_ decomposition, where the former leverage external data (e.g., scRNA-seq or scNuc-seq) to guide the inference process, while the latter only work with the spatial data. We require that all datasets have an associated reference single cell data set, but methods are free to ignore this information. \n\nDue to the lack of real datasets with the necessary ground-truth, this task makes use of a simulated dataset generated by creating cell-aggregates by sampling from a Dirichlet distribution. The ground-truth dataset consists of the spatial expression matrix, XY coordinates of the spots, true cell-type proportions for each spot, and the reference single-cell data (from which cell aggregated were simulated).\n", + "repo": "openproblems-bio/task_spatial_decomposition", + "authors": [ + { + "name": "Giovanni Palla", + "roles": ["author", "maintainer"], + "info": { + "github": "giovp" + } + }, + { + "name": "Scott Gigante", + "roles": "author", + "info": { + "github": "scottgigante", + "orcid": "0000-0002-4544-2764" + } + }, + { + "name": "Sai Nirmayi Yasa", + "roles": "contributor", + "info": { + "github": "sainirmayi", + "orcid": "0009-0003-6319-9803" + } + } + ] }