normalize as non default for control models

scripts/run_benchmark_single_omics.sh → scripts/run_benchmark_all.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
-RUN_ID="benchmark_donor_0_default"
+RUN_ID="benchmark_donor_0_baselines_specific"
 # resources_dir="./resources_test/"
 resources_dir="s3://openproblems-data/resources/grn"
 publish_dir="${resources_dir}/results/${RUN_ID}"
@@ -11,9 +11,9 @@ subsample=-2
 max_workers=10
 layer='scgen_pearson'
 metric_ids="[regression_1, regression_2]"
-cell_type_specific=false #for controls
+cell_type_specific=true #for controls
 # method_ids="[tigress, ennet, scsgl, pidc]"
-method_ids="[pearson_corr, pearson_causal, positive_control, portia, grnboost2]"
+method_ids="[pearson_corr, pearson_causal, positive_control]"
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -45,21 +45,21 @@ HERE
 #   -c src/common/nextflow_helpers/labels_ci.config \
 #   -params-file ${param_file}
 
-./tw-windows-x86_64.exe launch `
-    https://github.com/openproblems-bio/task_grn_inference.git `
-    --revision build/main `
-    --pull-latest `
-    --main-script target/nextflow/workflows/run_benchmark/main.nf `
-    --workspace 53907369739130 `
-    --compute-env 6TeIFgV5OY4pJCk8I0bfOh `
-    --params-file ./params/benchmark_donor_0_default.yaml `
-    --config src/common/nextflow_helpers/labels_tw.config
+# ./tw-windows-x86_64.exe launch `
+#     https://github.com/openproblems-bio/task_grn_inference.git `
+#     --revision build/main `
+#     --pull-latest `
+#     --main-script target/nextflow/workflows/run_benchmark/main.nf `
+#     --workspace 53907369739130 `
+#     --compute-env 6TeIFgV5OY4pJCk8I0bfOh `
+#     --params-file ./params/benchmark_donor_0_default.yaml `
+#     --config src/common/nextflow_helpers/labels_tw.config
 
-# ./tw launch https://github.com/openproblems-bio/task_grn_inference \
-#   --revision build/main \
-#   --pull-latest \
-#   --main-script target/nextflow/workflows/run_benchmark/main.nf \
-#   --workspace 53907369739130 \
-#   --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
-#   --params-file ${param_file} \
-#   --config src/common/nextflow_helpers/labels_tw.config
+./tw launch https://github.com/openproblems-bio/task_grn_inference \
+  --revision build/main \
+  --pull-latest \
+  --main-script target/nextflow/workflows/run_benchmark/main.nf \
+  --workspace 53907369739130 \
+  --compute-env 6TeIFgV5OY4pJCk8I0bfOh \
+  --params-file ${param_file} \
+  --config src/common/nextflow_helpers/labels_tw.config

scripts/sbatch/batch_scenic.sh

@@ -1,11 +1,14 @@
 #!/bin/bash
 #SBATCH --time=12:00:00
-#SBATCH --job-name=scenic
+#SBATCH --job-name=genie3
 #SBATCH --output=logs/%j.out
 #SBATCH --error=logs/%j.err
 #SBATCH --mail-type=END
 #SBATCH [email protected]
 #SBATCH --cpus-per-task=20
 #SBATCH --mem=64G 
 
-singularity exec ../../images/scenic python src/methods/single_omics/scenic/script.py 
+# singularity exec ../../images/scenic python src/methods/single_omics/scenic/script.py 
+# singularity exec ../../images/scenic python src/methods/single_omics/grnboost2/script.py 
+singularity exec ../../images/scenic python src/methods/single_omics/genie3/script.py 
+

src/api/comp_method.yaml

@@ -47,6 +47,10 @@ functionality:
       type: boolean
       direction: input
       default: true
+    - name: --normalize
+      type: boolean
+      direction: input
+      default: false
 
 
 

src/control_methods/pearson/script.py

@@ -63,11 +63,11 @@ def create_corr_net(X, gene_names, groups, par):
 tf_all = np.loadtxt(par['tf_all'], dtype=str)
 groups = multiomics_rna.obs.cell_type
 tf_all = np.intersect1d(tf_all, gene_names)
-
-print('Noramlize data')
-sc.pp.normalize_total(multiomics_rna)
-sc.pp.log1p(multiomics_rna)
-sc.pp.scale(multiomics_rna)
+if par['normalize']:
+    print('Noramlize data')
+    sc.pp.normalize_total(multiomics_rna)
+    sc.pp.log1p(multiomics_rna)
+    sc.pp.scale(multiomics_rna)
 
 print('Create corr net')
 net = create_corr_net(multiomics_rna.X, multiomics_rna.var_names, groups, par)

src/control_methods/pearson_causal/script.py

@@ -65,10 +65,11 @@ def create_corr_net(X, gene_names, groups, par):
 groups = multiomics_rna.obs.cell_type
 tf_all = np.intersect1d(tf_all, gene_names)
 
-print('Noramlize data')
-sc.pp.normalize_total(multiomics_rna)
-sc.pp.log1p(multiomics_rna)
-sc.pp.scale(multiomics_rna)
+if par['normalize']:
+    print('Noramlize data')
+    sc.pp.normalize_total(multiomics_rna)
+    sc.pp.log1p(multiomics_rna)
+    sc.pp.scale(multiomics_rna)
 
 print('Create corr net')
 net = create_corr_net(multiomics_rna.X, multiomics_rna.var_names, groups, par)

src/control_methods/positive_control/script.py

@@ -60,13 +60,18 @@ def create_corr_net(X, gene_names, groups, par):
 multiomics_rna = ad.read_h5ad(par["perturbation_data"])
 
 
+if par['normalize']:
+    print('Noramlize data')
+    sc.pp.normalize_total(multiomics_rna)
+    sc.pp.log1p(multiomics_rna)
+    sc.pp.scale(multiomics_rna)
+
 gene_names = multiomics_rna.var_names.to_numpy()
 tf_all = np.loadtxt(par['tf_all'], dtype=str)
 groups = multiomics_rna.obs.cell_type
 tf_all = np.intersect1d(tf_all, gene_names)
 
 
-
 print('Create corr net')
 net = create_corr_net(multiomics_rna.X, multiomics_rna.var_names, groups, par)
 

src/methods/multi_omics/celloracle/script.py

@@ -5,16 +5,17 @@
 
 ## VIASH START
 par = {
-  "multiomics_rna": "resources/grn-benchmark/multiomics_rna.h5ad",
-  "multiomics_atac": "resources/grn-benchmark/multiomics_atac.h5ad",
+  "multiomics_rna": "resources_test/grn-benchmark/multiomics_rna.h5ad",
+  "multiomics_atac": "resources_test/grn-benchmark/multiomics_atac.h5ad",
+  "base_grn": 'output/celloracle/base_grn.csv',
   "temp_dir": 'output/celloracle/',
   "num_workers": 4,
-  "prediction": "output/prediction.h5ad",
+  "prediction": "output/celloracle_test.h5ad",
 }
 ## VIASH END
-# meta = {
-#   "resources_dir":'resources'
-# }
+meta = {
+  "resources_dir":'src/methods/multi_omics/celloracle'
+}
 par['links'] = f"{par['temp_dir']}/links.celloracle.links" 
 
 sys.path.append(meta["resources_dir"])