refomatting completed: v1

scripts/run_grn_evaluation.sh

@@ -11,7 +11,7 @@ grn_models_folder="${resources_dir}/grn_models/" #TODO: change this
 
 reg_type="ridge"
 num_workers=10
-metric_ids="[regression_1, regression_2]"
+metric_ids="[regression_1, regression_2, ws_distance]"
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -66,7 +66,7 @@ append_entry() {
     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
-    prediction: ${grn_models_folder}/${dataset}/$1.csv
+    prediction: ${grn_models_folder}/${dataset}/$1.h5ad
     layer: "X_norm"
 HERE
 }

src/api/comp_method.yaml

@@ -16,7 +16,7 @@ arguments:
     required: false
     direction: input
   - name: --prediction
-    __merge__: file_prediction.yaml
+    __merge__: file_prediction_h5ad.yaml
     required: false
     direction: output
   - name: --tf_all
@@ -43,6 +43,16 @@ arguments:
     type: boolean
     direction: input
     default: True
+  - name: --dataset_id
+    type: string
+    direction: input
+    required: false
+    default: op
+  - name: --method_id
+    type: string
+    direction: input
+    required: false
+    default: grnboost2
 
 test_resources:
   - type: python_script

src/api/comp_metric.yaml

@@ -8,11 +8,11 @@ info:
       A metric to evaluate the performance of the inferred GRN
 arguments: 
   - name: --prediction
-    __merge__: file_prediction.yaml
+    __merge__: file_prediction_h5ad.yaml
     required: true
     direction: input
   - name: --score
-    __merge__: file_score.yaml
+    __merge__: file_score_h5ad.yaml
     required: true
     direction: output
   - name: --method_id 

src/api/comp_metric_regression.yaml

@@ -12,7 +12,7 @@ info:
 arguments: 
   - name: --evaluation_data
     __merge__: file_evaluation_h5ad.yaml
-    required: false
+    required: true
     direction: input
   - name: --tf_all
     type: file

src/api/file_prediction_h5ad.yaml

@@ -0,0 +1,22 @@
+
+type: file
+example: 'resources/grn_models/op/collectri.h5ad'
+info:
+  label: prediction
+  summary: "File indicating the inferred GRN."
+  file_type: h5ad
+  slots:
+    uns:
+      - type: string
+        name: dataset_id
+        description: "A unique identifier for the dataset"
+        required: true
+      - type: string
+        name: method_id
+        description: "A unique identifier for the inference method"
+        required: true
+      - type: DataFrame
+        name: prediction
+        description: "Inferred GRNs in the format of source, target, weight"
+        required: true
+

src/control_methods/negative_control/config.vsh.yaml

@@ -1,23 +1,26 @@
 __merge__: ../../api/comp_method.yaml
-functionality:
-  name: negative_control
-  namespace: control_methods
-  info:
-    label: Negative control
-    summary: Source-target links based on random assignment
-    description: |
-      Randomly assigns regulatory links to tf-target links with a given tf and target list. This is to perform near random.
 
-  resources:
-    - type: python_script
-      path: script.py
-    - path: main.py
-platforms:
+name: negative_control
+namespace: control_methods
+info:
+  label: Negative control
+  summary: Source-target links based on random assignment
+  description: |
+    Randomly assigns regulatory links to tf-target links with a given tf and target list. This is to perform near random.
+
+resources:
+  - type: python_script
+    path: script.py
+  - path: main.py
+engines:
   - type: docker
     image: ghcr.io/openproblems-bio/base_python:1.0.4
+    __merge__: /src/api/base_requirements.yaml
     setup:
       - type: python
         packages: [  ]
+runners:
+  - type: executable
   - type: nextflow
     directives:
       label: [ midtime, highmem, highcpu ]

src/control_methods/negative_control/script.py

@@ -45,6 +45,10 @@
     }
     sys.path.append(meta['resources_dir'])
 from main import main
-prediction = main(par)
-prediction.to_csv(par["prediction"])
+net = main(par)
+
+print('Output GRN')
+net['weight'] = net['weight'].astype(str)
+output = ad.AnnData(X=None, uns={"method_id": par['method_id'], "dataset_id": par['dataset_id'], "prediction": net[["source", "target", "weight"]]})
+output.write(par['prediction'])
 

src/control_methods/pearson_corr/config.vsh.yaml

@@ -1,31 +1,34 @@
 __merge__: ../../api/comp_method.yaml
 
-functionality:
-  name: pearson_corr
-  namespace: control_methods
-  info:
-    label: pearson_corr
-    summary: "Baseline based on correlation"
-  arguments:
-    - name: --normalize
-      type: boolean 
-      default: True 
-      direction: input
 
-  resources:
-    - type: python_script
-      path: script.py
+name: pearson_corr
+namespace: control_methods
+info:
+  label: pearson_corr
+  summary: "Baseline based on correlation"
+arguments:
+  - name: --normalize
+    type: boolean 
+    default: True 
+    direction: input
 
-    - path: /src/utils/util.py
-      dest: util.py
-platforms:
+resources:
+  - type: python_script
+    path: script.py
+
+  - path: /src/utils/util.py
+    dest: util.py
+engines:
   - type: docker
     image: ghcr.io/openproblems-bio/base_python:1.0.4
+    __merge__: /src/api/base_requirements.yaml
     setup:
       - type: python
         # packages: [ magic-impute ]
         packages: [  ]
   - type: native
+runners:
+  - type: executable
   - type: nextflow
     directives:
       label: [midtime, midmem, midcpu]

src/control_methods/pearson_corr/script.py

@@ -70,4 +70,6 @@ def create_corr_net(par):
 net = create_corr_net(par)
 
 print('Output GRN')
-net.to_csv(par['prediction'])
+net['weight'] = net['weight'].astype(str)
+output = ad.AnnData(X=None, uns={"method_id": par['method_id'], "dataset_id": par['dataset_id'], "prediction": net[["source", "target", "weight"]]})
+output.write(par['prediction'])

src/control_methods/positive_control/config.vsh.yaml

@@ -1,26 +1,29 @@
 __merge__: ../../api/comp_method.yaml
 
-functionality:
-  name: positive_control
-  namespace: control_methods
-  info:
-    label: positive_control
-    summary: "Baseline based on correlation"
 
-  resources:
-    - type: python_script
-      path: script.py
-    - path: /src/utils/util.py
-      dest: util.py
+name: positive_control
+namespace: control_methods
+info:
+  label: positive_control
+  summary: "Baseline based on correlation"
 
-platforms:
+resources:
+  - type: python_script
+    path: script.py
+  - path: /src/utils/util.py
+    dest: util.py
+
+engines:
   - type: docker
     image: ghcr.io/openproblems-bio/base_python:1.0.4
+    __merge__: /src/api/base_requirements.yaml
     setup:
       - type: python
         # packages: [ magic-impute ]
         packages: [  ]
   - type: native
+runners:
+  - type: executable
   - type: nextflow
     directives:
       label: [midtime, midmem, midcpu]

src/control_methods/positive_control/script.py

@@ -70,4 +70,7 @@ def create_corr_net(par):
 
 net = create_corr_net(par)
 
-net.to_csv(par['prediction'])
+print('Output GRN')
+net['weight'] = net['weight'].astype(str)
+output = ad.AnnData(X=None, uns={"method_id": par['method_id'], "dataset_id": par['dataset_id'], "prediction": net[["source", "target", "weight"]]})
+output.write(par['prediction'])