wf fixed

README.md

@@ -71,7 +71,8 @@ flowchart TB
 
 Chromatin accessibility data
 
-Example file: `resources_test/grn_benchmark/inference_datasets//op_atac.h5ad`
+Example file:
+`resources_test/grn_benchmark/inference_data//op_atac.h5ad`
 
 Format:
 
@@ -120,7 +121,7 @@ Arguments:
 
 File indicating the inferred GRN.
 
-Example file: `resources/grn_models/op/collectri.h5ad`
+Example file: `resources_test/grn_models/op/collectri.h5ad`
 
 Format:
 
@@ -139,7 +140,7 @@ Data structure:
 |:---|:---|:---|
 | `uns["dataset_id"]` | `string` | A unique identifier for the dataset. |
 | `uns["method_id"]` | `string` | A unique identifier for the inference method. |
-| `uns["prediction"]` | `DataFrame` | Inferred GRNs in the format of source, target, weight. |
+| `uns["prediction"]` | `object` | Inferred GRNs in the format of source, target, weight. |
 
 </div>
 
@@ -245,7 +246,8 @@ Data structure:
 
 Perturbation dataset for benchmarking.
 
-Example file: `resources_test/grn_benchmark/evaluation_data//op.h5ad`
+Example file:
+`resources_test/grn_benchmark/evaluation_data/op_bulk.h5ad`
 
 Format:
 
@@ -275,7 +277,8 @@ Data structure:
 
 RNA expression data.
 
-Example file: `resources_test/grn_benchmark/inference_datasets//op_rna.h5ad`
+Example file:
+`resources_test/grn_benchmark/inference_data/op_rna.h5ad`
 
 Format:
 

_viash.yaml

@@ -59,7 +59,7 @@ info:
 
     ```bash
     viash run src/control_methods/pearson_corr/config.vsh.yaml -- \
-              --rna resources/grn_benchmark/inference_datasets/norman_rna.h5ad --prediction output/net.h5ad
+              --rna resources/grn_benchmark/inference_data/norman_rna.h5ad --prediction output/net.h5ad
     ```
 
     ## Evaluate a GRN

scripts/add_a_method.sh

@@ -27,7 +27,7 @@ viash run src/methods/$method_id/config.vsh.yaml -- \
 
 # run the inference using the method for op dataset using only RNA data. Add more aurguments if needed.
 viash run src/methods/$method_id/config.vsh.yaml -- \
-  --rna "resources/grn_benchmark/inference_datasets/op_rna.h5ad" \
+  --rna "resources/grn_benchmark/inference_data/op_rna.h5ad" \
   --prediction "output/prediction.h5ad"
 
 # run evaluation metrics

scripts/download_resources.sh

@@ -4,4 +4,4 @@ set -e
 
 # common/scripts/sync_resources
 
-aws s3 sync  s3://openproblems-data/resources/grn/grn_benchmark resources/grn_benchmark --delete --no-sign-request
+aws s3 sync  s3://openproblems-data/resources/grn/grn_benchmark resources/grn_benchmark --delete --no-sign-request

scripts/run_benchmark_all.sh

@@ -22,8 +22,8 @@ param_list:
     metric_ids: $metric_ids
     method_ids: $method_ids
     evaluation_data: ${resources_dir}/evaluation_data/${dataset}.h5ad
-    rna: ${resources_dir}/inference_datasets/${dataset}_rna.h5ad
-    atac: ${resources_dir}/inference_datasets/${dataset}_atac.h5ad
+    rna: ${resources_dir}/inference_data/${dataset}_rna.h5ad
+    atac: ${resources_dir}/inference_data/${dataset}_atac.h5ad
     reg_type: $reg_type
     subsample: $subsample
     num_workers: $num_workers

scripts/run_grn_evaluation.sh

@@ -57,15 +57,16 @@ append_entry() {
   cat >> $param_file << HERE
   - id: ${reg_type}_${1}
     metric_ids: ${metric_ids}
-    evaluation_data: ${resources_dir}/evaluation_data/${dataset}.h5ad
-    evaluation_data_sc: ${resources_dir}/evaluation_data/${dataset}_sc_counts.h5ad
+    evaluation_data: ${resources_dir}/grn_benchmark/evaluation_data/${dataset}.h5ad
+    evaluation_data_sc: ${resources_dir}/grn_benchmark/evaluation_data/${dataset}_sc.h5ad
     reg_type: $reg_type
     method_id: $1
+    dataset_id: $dataset
     num_workers: $num_workers
-    tf_all: ${resources_dir}/prior/tf_all.csv
-    regulators_consensus: ${resources_dir}/prior/regulators_consensus_${dataset}.json
-    ws_consensus: ${resources_dir}/prior/ws_consensus_${dataset}.json
-    ws_distance_background: ${resources_dir}/prior/ws_distance_background_${dataset}.json
+    tf_all: ${resources_dir}/grn_benchmark/prior/tf_all.csv
+    regulators_consensus: ${resources_dir}/grn_benchmark/prior/regulators_consensus_${dataset}.json
+    ws_consensus: ${resources_dir}/grn_benchmark/prior/ws_consensus_${dataset}.csv
+    ws_distance_background: ${resources_dir}/grn_benchmark/prior/ws_distance_background_${dataset}.csv
     prediction: ${grn_models_folder}/${dataset}/$1.h5ad
     layer: "X_norm"
 HERE

src/api/file_atac_h5ad.yaml

@@ -1,5 +1,5 @@
 type: file
-example: resources_test/grn_benchmark/inference_datasets//op_atac.h5ad
+example: resources_test/grn_benchmark/inference_data//op_atac.h5ad
 label:  chromatin accessibility data
 summary: "Chromatin accessibility data"
 info:

src/api/file_rna_h5ad.yaml

@@ -1,5 +1,5 @@
 type: file
-example: resources_test/grn_benchmark/inference_datasets/op_rna.h5ad
+example: resources_test/grn_benchmark/inference_data/op_rna.h5ad
 label: gene expression data
 summary: "RNA expression data."
 info:

src/helper.py

@@ -40,7 +40,7 @@ def analyse_meta_cells(task_grn_inference_dir):
 
 
     par = {
-        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
         "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
         'layer': 'X_norm',
@@ -123,7 +123,7 @@ def analyse_imputation(task_grn_inference_dir):
 
 
     par = {
-        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+        'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
         "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
         'layer': 'X_norm',
@@ -204,7 +204,7 @@ def analyse_imputation(task_grn_inference_dir):
 def analyse_corr_vs_tfmasked_corr(task_grn_inference_dir):
     for i_run, dataset in enumerate(['op', 'replogle', 'nakatake', 'norman', 'adamson']):
         par = {
-            'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
+            'rna': f'{task_grn_inference_dir}/resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
             "evaluation_data": f"{task_grn_inference_dir}/resources/grn_benchmark/evaluation_data//{dataset}.h5ad",
 
             'layer': 'X_norm',

src/methods/multi_omics/celloracle/script.py

@@ -6,8 +6,8 @@
 
 ## VIASH START
 par = {
-  "rna": "resources/grn_benchmark/inference_datasets/op_rna.h5ad",
-  "atac": "resources/grn_benchmark/inference_datasets/op_atac.h5ad",
+  "rna": "resources/grn_benchmark/inference_data/op_rna.h5ad",
+  "atac": "resources/grn_benchmark/inference_data/op_atac.h5ad",
   "base_grn": 'output/celloracle/base_grn.csv',
   "temp_dir": 'output/celloracle/',
   "num_workers": 10,

src/methods/single_omics/scgpt/run.sh

@@ -1,4 +1,4 @@
 viash run src/methods/single_omics/scgpt/config.vsh.yaml -- \
-    --rna resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
+    --rna resources_test/grn_benchmark/inference_data//op_rna.h5ad \
     --tf_all resources/grn_benchmark/prior/tf_all.csv \
     --prediction output/prediction.h5ad

src/methods/single_omics/scprint/run.sh

@@ -13,13 +13,13 @@
 
 
 # viash run src/methods/single_omics/scprint/config.vsh.yaml -- \
-#     --rna resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
+#     --rna resources_test/grn_benchmark/inference_data//op_rna.h5ad \
 #     --tf_all resources/grn_benchmark/prior/tf_all.csv \
 #     --prediction output/prediction.h5ad
 
 
 # python src/methods/single_omics/scprint/script.py  \
-#     --rna resources/grn_benchmark/inference_datasets/op_rna.h5ad \
+#     --rna resources/grn_benchmark/inference_data/op_rna.h5ad \
 #     --tf_all resources/grn_benchmark/prior/tf_all.csv \
 #     --prediction output/prediction.h5ad
 

src/methods/single_omics/scprint/script.py

@@ -28,7 +28,7 @@
 
 ## VIASH START
 par = {
-    'rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
+    'rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
     'tf_all': 'resources/grn_benchmark/prior/tf_all.csv',
     'prediction': 'output/grn.h5ad',
     'filtration': 'top-k',

src/process_data/explanatory_analysis/peak_annotation/script.R

@@ -11,7 +11,7 @@ library(tibble)
 
 ## VIASH START
 par <- list(
-  multiomics_atac = "resources/grn_benchmark/inference_datasets/op_atac.h5ad",
+  multiomics_atac = "resources/grn_benchmark/inference_data/op_atac.h5ad",
   annot_peak_database = "resources/grn_benchmark/prior/peak_annotation.csv"
 )
 ## VIASH END

src/process_data/op_multiomics/format_data/script.py

@@ -4,8 +4,8 @@
 ## VIASH START
 par = {
     'multiome_counts': 'resources/datasets_raw/op_multiome_sc_counts.h5ad',
-    'multiomics_rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
-    'multiomics_atac': 'resources/grn_benchmark/inference_datasets/op_atac.h5ad'
+    'multiomics_rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
+    'multiomics_atac': 'resources/grn_benchmark/inference_data/op_atac.h5ad'
 }
 ## VIASH END
 

src/process_data/pereggrn/script.py

@@ -105,7 +105,7 @@ def process_dataset(file_name):
         adata.write(f'resources/grn_benchmark/evaluation_data/{file_name}_sc.h5ad')
 
     adata_bulked.write(f'resources/extended_data/{file_name}_bulk.h5ad')
-    adata_train.write(f'resources/grn_benchmark/inference_datasets/{file_name}_rna.h5ad')
+    adata_train.write(f'resources/grn_benchmark/inference_data/{file_name}_rna.h5ad')
     adata_test.write(f'resources/grn_benchmark/evaluation_data/{file_name}_bulk.h5ad')
 
 

src/process_data/replogle_k562_gwps/run.sh

@@ -18,5 +18,5 @@ python src/process_data/replogle_k562_gwps/script.py \
         --adata_bulk resources/extended_data/replogle_bulk.h5ad \
         --adata_test_sc resources/grn_benchmark/evaluation_data/replogle_sc.h5ad \
         --adata_test_bulk resources/grn_benchmark/evaluation_data/replogle_bulk.h5ad \
-        --adata_train_bulk resources/grn_benchmark/inference_datasets/replogle_rna.h5ad \
+        --adata_train_bulk resources/grn_benchmark/inference_data/replogle_rna.h5ad \
         --adata_train_sc resources/extended_data/replogle_train_sc.h5ad \

src/process_data/test_data/run.sh

@@ -1,6 +1,6 @@
 viash run src/process_data/test_data/config.novsh.yaml -- \
-    --rna resources/grn_benchmark/inference_datasets/op_rna.h5ad --rna_test resources_test/grn_benchmark/inference_datasets//op_rna.h5ad \
-    --atac resources/grn_benchmark/inference_datasets/op_atac.h5ad --atac_test resources_test/grn_benchmark/inference_datasets//op_atac.h5ad \
+    --rna resources/grn_benchmark/inference_data/op_rna.h5ad --rna_test resources_test/grn_benchmark/inference_data//op_rna.h5ad \
+    --atac resources/grn_benchmark/inference_data/op_atac.h5ad --atac_test resources_test/grn_benchmark/inference_data//op_atac.h5ad \
     --perturbation_data resources/grn_benchmark/evaluation_data/op.h5ad --perturbation_data_test resources_test/grn_benchmark/evaluation_data/op.h5ad \
     --multiomics_counts resources/grn_benchmark/datasets_raw/op_multiome_sc_counts.h5ad --multiomics_counts_test resources_test/grn_benchmark/datasets_raw/op_multiome_sc_counts.h5ad \
     # --perturbation_counts resources/datasets_raw/op_perturbation_sc_counts.h5ad --perturbation_counts_test resources_test/datasets_raw/op_perturbation_sc_counts.h5ad \

src/process_data/test_data/script.py

@@ -12,11 +12,11 @@
 ## VIASH START
 
 par = {
-    'rna': 'resources/grn_benchmark/inference_datasets/op_rna.h5ad',
-    'rna_test': 'resources_test/grn_benchmark/inference_datasets//op_rna.h5ad',
+    'rna': 'resources/grn_benchmark/inference_data/op_rna.h5ad',
+    'rna_test': 'resources_test/grn_benchmark/inference_data//op_rna.h5ad',
 
-    'atac': 'resources/grn_benchmark/inference_datasets/op_atac.h5ad',
-    'atac_test': 'resources_test/grn_benchmark/inference_datasets//op_atac.h5ad',
+    'atac': 'resources/grn_benchmark/inference_data/op_atac.h5ad',
+    'atac_test': 'resources_test/grn_benchmark/inference_data//op_atac.h5ad',
 
     'perturbation_data': 'resources/grn_benchmark/evaluation_data//op.h5ad',
     'perturbation_data_test': 'resources_test/grn_benchmark/evaluation_data//op.h5ad',

src/workflows/run_grn_evaluation/config.vsh.yaml

@@ -25,6 +25,10 @@ argument_groups:
         type: string
         required: true
         direction: input
+      - name: --dataset_id
+        type: string
+        required: true
+        direction: input
       - name: --tf_all
         type: file
         direction: input

src/workflows/run_grn_evaluation/main.nf

@@ -39,11 +39,13 @@ workflow run_wf {
       // use 'fromState' to fetch the arguments the component requires from the overall state
       fromState: [
         evaluation_data: "evaluation_data",
+        evaluation_data_sc: "evaluation_data_sc",
         prediction: "prediction",
         ws_distance_background: "ws_distance_background",
         subsample: "subsample",
         reg_type: "reg_type",
         method_id: "method_id",
+        dataset_id: "method_id",
         num_workers: "num_workers",
         regulators_consensus: "regulators_consensus",
         ws_consensus: "ws_consensus",

src/workflows_local/benchmark/methods/script.py

@@ -20,8 +20,8 @@
 def run_grn_inference(par, dataset='op', subsample=None):
     par_local = {
         'models_dir': f'resources/grn_models/{dataset}/',
-        'rna': f'resources/grn_benchmark/inference_datasets/{dataset}_rna.h5ad',
-        'atac': f'resources/grn_benchmark/inference_datasets/{dataset}_atac.h5ad', 
+        'rna': f'resources/grn_benchmark/inference_data/{dataset}_rna.h5ad',
+        'atac': f'resources/grn_benchmark/inference_data/{dataset}_atac.h5ad', 
         'rna_positive_control': f'resources/datasets_raw/{dataset}.h5ad', 
         'num_workers': 10,
         'tmp_dir': 'output/grn_inference'

test.ipynb

@@ -50,7 +50,7 @@
     }
    ],
    "source": [
-    "adata = ad.read_h5ad('resources/grn_benchmark/inference_datasets/replogle_rna.h5ad')\n",
+    "adata = ad.read_h5ad('resources/grn_benchmark/inference_data/replogle_rna.h5ad')\n",
     "adata[adata.obs['is_control']]"
    ]
   }