small changes to config

Author: janursa

scripts/prior/run_ws_background.sh

@@ -25,5 +25,5 @@ for dataset in "${datasets[@]}"; do
         --background_distance "resources/grn_benchmark/prior/ws_distance_background_${dataset}.csv" \
         --tf_all "resources/grn_benchmark/prior/tf_all.csv" \
         --evaluation_data_sc "resources/processed_data/${dataset}_evaluation_sc.h5ad" \
-        --max_workers 100 
+        --num_workers 100 
 done

scripts/process_data/rest.sh

@@ -13,9 +13,9 @@
 
 set -e
 
-# python src/process_data/main/adamson/script.py 
+python src/process_data/main/adamson/script.py 
 # python src/process_data/main/nakatake/script.py 
-# python src/process_data/main/norman/script.py
+python src/process_data/main/norman/script.py
 
 # echo "Processing opsca"
 # python src/process_data/main/opsca/script.py 
@@ -27,5 +27,5 @@ set -e
 
 # echo "Processing 300BCG"
 # python src/process_data/main/300BCG/script.py 
-echo "Processing IBD"
-python src/process_data/main/ibd/script.py 
+# echo "Processing IBD"
+# python src/process_data/main/ibd/script.py 

scripts/repo/run_grn_evaluation copy.sh

@@ -12,7 +12,7 @@ publish_dir="${resources_dir}/results/${RUN_ID}"
 grn_models_folder="${resources_dir}/grn_models"
 
 subsample=-2
-max_workers=10
+num_workers=10
 layer=scgen_pearson
 metric_ids="[regression_1, regression]"
 
@@ -44,7 +44,7 @@ append_entry() {
     reg_type: $reg_type
     method_id: $1
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     tf_all: ${resources_dir}/prior/tf_all.csv
     layer: ${layer}
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
@@ -61,7 +61,7 @@ append_entry_control() {
     reg_type: $reg_type
     method_id: $1
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     tf_all: ${resources_dir}/prior/tf_all.csv
     layer: ${layer}
     consensus: ${resources_dir}/prior/consensus-num-regulators.json

scripts/repo/run_grn_evaluation_all_layers.sh

@@ -9,7 +9,7 @@ publish_dir="s3://openproblems-data/resources/grn/results/${RUN_ID}"
 grn_models_folder="${resources_dir}/grn_models"
 
 subsample=-2
-max_workers=10
+num_workers=10
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -38,7 +38,7 @@ append_entry() {
     reg_type: $reg_type
     method_id: $1
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
     ${2:+tf_all: ${resources_dir}/prior/tf_all.csv}
     ${3:+prediction: ${grn_models_folder}/$1.csv}

scripts/repo/run_pc_vs_nc.sh

@@ -14,7 +14,7 @@ grn_models_folder="${resources_dir}/grn_models"
 
 
 reg_type=ridge
-max_workers=10
+num_workers=10
 layer=scgen_pearson
 
 param_file="./params/${RUN_ID}.yaml"
@@ -42,7 +42,7 @@ append_entry() {
     reg_type: $reg_type
     method_id: ${2}-${1}
     subsample: $2
-    max_workers: $max_workers
+    num_workers: $num_workers
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
     prediction: ${grn_models_folder}/$1.csv
     degree: 0

scripts/repo/run_robust_analys.sh

@@ -15,7 +15,7 @@ grn_models_folder="${resources_dir}/grn_models/d0_hvgs"
 
 reg_type=ridge
 subsample=-2
-max_workers=10
+num_workers=10
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -49,7 +49,7 @@ append_entry() {
     method_id: ${2}-${1}
     layer: ${3}
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
     prediction: ${grn_models_folder}/$1.csv
     tf_all: ${resources_dir}/prior/tf_all.csv

scripts/repo/run_robust_analys_causal.sh

@@ -7,7 +7,7 @@ publish_dir="${resources_dir}/results/${RUN_ID}"
 
 reg_type=ridge
 subsample=-2
-max_workers=10
+num_workers=10
 layer=(scgen_pearson)
 metric_ids="[regression_1]"
 
@@ -26,7 +26,7 @@ cat >> $param_file << HERE
     method_id: baseline_corr_causal
     layer: ${layer}
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
     tf_all: ${resources_dir}/prior/tf_all.csv
     causal: True
@@ -42,7 +42,7 @@ append_entry() {
     method_id: baseline_corr-${1}
     layer: ${layer}
     subsample: $subsample
-    max_workers: $max_workers
+    num_workers: $num_workers
     consensus: ${resources_dir}/prior/consensus-num-regulators.json
     tf_all: ${resources_dir}/prior/tf_all.csv
     causal: False

scripts/run_all.sh

@@ -1,7 +1,7 @@
 set -e
 
 # datasets=( 'replogle' 'op' 'nakatake' 'adamson' 'norman'  'xaira_HEK293T' 'xaira_HCT116'  'parsebioscience' 'ibd_uc' 'ibd_cd' '300BCG' ) #'replogle' 'op' 'nakatake' 'adamson' 'norman'  'xaira_HEK293T' 'xaira_HCT116'  'parsebioscience' 'ibd_uc' 'ibd_cd'  '300BCG') #
-datasets=( 'op' 'replogle'   ) #'replogle' 'op' 'nakatake' 'adamson' 'norman'  'xaira_HEK293T' 'xaira_HCT116'  'parsebioscience' 'ibd_uc' 'ibd_cd' '300BCG') #
+datasets=( 'op'  ) #'replogle' 'op' 'nakatake' 'adamson' 'norman'  'xaira_HEK293T' 'xaira_HCT116'  'parsebioscience' 'ibd_uc' 'ibd_cd' '300BCG') #
 run_local=false # set to true to run locally, false to run on AWS
 
 run_grn_inference=false

src/api/comp_metric.yaml

@@ -44,6 +44,10 @@ arguments:
     type: integer
     direction: input
     default: 20
+  - name: --n_top_genes
+    type: integer
+    direction: input
+    default: 3000
 
 test_resources:
   - type: python_script

src/metrics/all_metrics/helper.py

@@ -10,7 +10,7 @@
 from regression.helper import main as regression
 from ws_distance.helper import main as ws_distance
 from sem.helper import main as sem
-from anchor_regression.helper import main as ar
+from anchor_regression.helper import main as anchor_regression
 from tf_recovery.helper import main as tf_recovery
 from tf_binding.helper import main as tf_binding
 from rc_tf_act.helper import main as rc_tf_act
@@ -23,7 +23,7 @@
     'regression': regression,
     'ws_distance': ws_distance,
     'sem': sem,
-    'ar': ar,
+    'anchor_regression': anchor_regression,
     'tf_recovery': tf_recovery,
     'tf_binding': tf_binding,
     'rc_tf_act': rc_tf_act,
@@ -35,6 +35,7 @@ def main(par):
     dataset_id = ad.read_h5ad(par['evaluation_data'], backed='r').uns['dataset_id']
     rr_store = []
     metrics = DATASETS_METRICS[dataset_id]
+    print(f"Computing metrics for dataset {dataset_id}: {metrics}")
     # metrics = ['gs_recovery', 'tf_binding']
 
     for metric_name in metrics: