overal score is added to runs

openproblems-bio · Sep 21, 2024 · 916d854 · 916d854
1 parent b1d37ce
commit 916d854
Show file tree

Hide file tree

Showing 6 changed files with 668 additions and 261 deletions.
diff --git a/runs.ipynb b/runs.ipynb
diff --git a/scripts/run_benchmark_all.sh b/scripts/run_benchmark_all.sh
@@ -1,7 +1,6 @@
 #!/bin/bash
 
-# RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
-RUN_ID="celloracle_d0_hvg"
+RUN_ID="d0_hvgs_baseline"
 # resources_dir="./resources/"
 resources_dir="s3://openproblems-data/resources/grn"
 publish_dir="${resources_dir}/results/${RUN_ID}"
@@ -13,10 +12,7 @@ layer='scgen_pearson'
 metric_ids="[regression_1, regression_2]"
 cell_type_specific=false #for controls
 normalize=false
-only_hvgs=true
-# method_ids="[tigress, ennet, scsgl, pidc]"
-# method_ids="[pearson_corr, pearson_causal, positive_control]"
-method_ids="[celloracle]"
+method_ids="[pearson_corr, pearson_causal, positive_control]"
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -27,7 +23,7 @@ param_list:
     metric_ids: $metric_ids
     method_ids: $method_ids
     perturbation_data: ${resources_dir}/grn-benchmark/perturbation_data.h5ad
-    multiomics_rna: ${resources_dir}/grn-benchmark/multiomics_rna_0.h5ad
+    multiomics_rna: ${resources_dir}/grn-benchmark/multiomics_rna_0_hvgs.h5ad
     multiomics_atac: ${resources_dir}/grn-benchmark/multiomics_atac_0.h5ad
     reg_type: $reg_type
     subsample: $subsample
@@ -37,7 +33,6 @@ param_list:
     tf_all: ${resources_dir}/prior/tf_all.csv
     cell_type_specific: ${cell_type_specific}
     normalize: ${normalize}
-    only_hvgs: ${only_hvgs}
 
 output_state: "state.yaml"
 publish_dir: "$publish_dir"

diff --git a/src/control_methods/pearson/script.py b/src/control_methods/pearson/script.py
@@ -7,7 +7,6 @@
     'max_n_links': 50000,
     'prediction': 'resources/grn_models/donor_0_default/pearson.csv',
     "seed": 32,
-    'only_hvgs': True,
     'normalize': False
 }
 ## VIASH END

diff --git a/src/utils/util.py b/src/utils/util.py
@@ -50,10 +50,6 @@ def process_data(adata, par):
         adata.X = adata.X.toarray()  # You can also use .todense(), but .toarray() gives a NumPy array directly
     else:
         print("adata.X is already dense.")
-    if par['only_hvgs']:
-        print('Subsetting data to hvgs')
-        adata = adata[:, adata.var.hvg_counts]
-        print('New dimension of data: ', adata.shape)
 
 def create_corr_net(par):
     print(par)

diff --git a/src/workflows/run_benchmark/config.vsh.yaml b/src/workflows/run_benchmark/config.vsh.yaml
@@ -58,10 +58,7 @@ functionality:
           type: boolean
           required: false
           direction: input
-        - name: --only_hvgs
-          type: boolean
-          required: false
-          direction: input
+
 
 
     - name: Outputs

diff --git a/src/workflows/run_benchmark/main.nf b/src/workflows/run_benchmark/main.nf
@@ -85,7 +85,6 @@ workflow run_wf {
         perturbation_data:"perturbation_data",
         cell_type_specific:"cell_type_specific",
         normalize:"normalize",
-        only_hvgs:"only_hvgs",
         num_workers:"num_workers"
 
       ],