Create bidcell.py

scripts/create_test_resources/2023_10x_mouse_brain_xenium_rep1.sh

@@ -8,8 +8,8 @@ cd "$REPO_ROOT"
 
 set -e
 
-if [ ! -d temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium ]; then
-  mkdir -p temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium
+if [ ! -d temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium_rep1 ]; then
+  mkdir -p temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium_rep1
 fi
 if [ ! -f temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium_rep1/Xenium_V1_FF_Mouse_Brain_MultiSection_1_outs.zip ]; then
   wget -O temp/datasets/10x_xenium/2023_10x_mouse_brain_xenium_rep1/Xenium_V1_FF_Mouse_Brain_MultiSection_1_outs.zip \
@@ -29,9 +29,9 @@ param_list:
     dataset_description: Demonstration of gene expression profiling for fresh frozen mouse brain on the Xenium platform using the pre-designed Mouse Brain Gene Expression Panel (v1).
     dataset_organism: mus_musculus
     crop_region_min_x: 10000
-    crop_region_max_x: 12000
+    crop_region_max_x: 11000
     crop_region_min_y: 10000
-    crop_region_max_y: 12000
+    crop_region_max_y: 11000
 
 publish_dir: resources_test/common
 output_dataset: '\$id/dataset.zarr'

scripts/create_test_resources/test_pipeline.sh

@@ -12,6 +12,13 @@ mkdir -p $OUT_DIR
 
 # run dataset preprocessor
 viash run src/data_processors/process_dataset/config.vsh.yaml -- \
+  --dataset_id mouse_brain_combined \
+  --dataset_name "Test data mouse brain combined 2023 tenx Xenium replicate 1 2023 Yao scRNAseq" \
+  --dataset_url "https://www.10xgenomics.com/datasets/fresh-frozen-mouse-brain-replicates-1-standard;https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE246717" \
+  --dataset_reference "https://www.10xgenomics.com/datasets/fresh-frozen-mouse-brain-replicates-1-standard;10.1038/s41586-023-06812-z" \
+  --dataset_summary "Demonstration of gene expression profiling for fresh frozen mouse brain on the Xenium platform using the pre-designed Mouse Brain Gene Expression Panel (v1);A high-resolution scRNAseq atlas of cell types in the whole mouse brain" \
+  --dataset_description "Demonstration of gene expression profiling for fresh frozen mouse brain on the Xenium platform using the pre-designed Mouse Brain Gene Expression Panel (v1). Replicate results demonstrate the high reproducibility of data generated by the platform. 10x Genomics obtained tissue from a C57BL/6 mouse from Charles River Laboratories. Three adjacent 10µm sections were placed on the same slide. Tissues were prepared following the demonstrated protocols Xenium In Situ for Fresh Frozen Tissues - Tissue Preparation Guide (CG000579) and Xenium In Situ for Fresh Frozen Tissues - Fixation & Permeabilization (CG000581).;See dataset_reference for more information. Note that we only took the 10xv2 data from the dataset." \
+  --dataset_organism "mus_musculus" \
   --input_sc $SC_DIR/dataset.h5ad \
   --input_sp $SP_DIR/dataset.zarr \
   --output_sc $OUT_DIR/scrnaseq_reference.h5ad \

src/datasets/loaders/tenx_xenium/config.vsh.yaml

@@ -67,4 +67,4 @@ runners:
   - type: executable
   - type: nextflow
     directives:
-      label: [highmem, midcpu, midtime]
+      label: [midmem, midcpu, midtime]

src/datasets/workflows/process_tenx_xenium/config.vsh.yaml

@@ -82,4 +82,4 @@ dependencies:
 runners:
   - type: nextflow
     directives:
-      label: [highcpu, highmem, hightime]
+      label: [highcpu, midmem, hightime]

src/datasets/workflows/process_wu_human_breast_cancer_sc/config.vsh.yaml

@@ -88,8 +88,10 @@ dependencies:
     repository: openproblems
   - name: datasets/processors/knn
     repository: openproblems
-  - name: h5ad/extract_uns_metadata
-    repository: core
+  - name: utils/extract_uns_metadata
+    repository: openproblems
+#  - name: h5ad/extract_uns_metadata
+#    repository: core
 
 runners:
   - type: nextflow