test runs

scripts/run_benchmark_single_omics.sh

@@ -1,12 +1,12 @@
 #!/bin/bash
 
 # RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
-RUN_ID="single_omics"
-resources_dir="s3://openproblems-data/resources_test/grn"
-publish_dir="s3://openproblems-data/resources_test/grn/results/${RUN_ID}"
+RUN_ID="single_omics_test"
+# resources_dir="s3://openproblems-data/resources_test/grn"
+# publish_dir="s3://openproblems-data/resources_test/grn/results/${RUN_ID}"
 
-# resources_dir="./resources_test/"
-# publish_dir="output/${RUN_ID}"
+resources_dir="./resources_test/"
+publish_dir="output/${RUN_ID}"
 
 reg_type=ridge
 subsample=-2

scripts/run_pc_vs_nc.sh

@@ -4,19 +4,18 @@
 
 subsamples=(-2 -3 -4)
 
-RUN_ID="robust_analy_$1"
-resources_dir="resources"
-publish_dir="output/${RUN_ID}"
+RUN_ID="robust_analy_reg2_$1"
+# resources_dir="resources"
+resources_dir="s3://openproblems-data/resources/grn"
 
-# resources_dir="s3://openproblems-data/resources/grn"
-# publish_dir="s3://openproblems-data/resources/grn/results/${RUN_ID}"
+publish_dir="${resources_dir}/${RUN_ID}"
 
 grn_models_folder="${resources_dir}/grn_models"
 
 
 reg_type=ridge
 max_workers=10
-layer=pearson
+layer=scgen_pearson
 
 param_file="./params/${RUN_ID}.yaml"
 
@@ -30,7 +29,6 @@ grn_names=(
 )
 
 
-
 # Start writing to the YAML file
 cat > $param_file << HERE
 param_list:
@@ -66,12 +64,12 @@ output_state: "state.yaml"
 publish_dir: "$publish_dir"
 HERE
 
-nextflow run . \
-  -main-script  target/nextflow/workflows/run_robustness_analysis/main.nf \
-  -profile docker \
-  -with-trace \
-  -c src/common/nextflow_helpers/labels_ci.config \
-  -params-file ${param_file}
+# nextflow run . \
+#   -main-script  target/nextflow/workflows/run_robustness_analysis/main.nf \
+#   -profile docker \
+#   -with-trace \
+#   -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_benchmark.git `

scripts/run_robust_analys.sh

@@ -3,12 +3,12 @@
 # RUN_ID="run_$(date +%Y-%m-%d_%H-%M-%S)"
 
 degrees=(0 10 20 50 100)
-noise_type="$1" #"net"
+noise_type="$1" #"net", "weight", "sign"
 echo $noise_type
 
-RUN_ID="robust_analy_$1"
-resources_dir="resources"
-# resources_dir="s3://openproblems-data/resources/grn"
+RUN_ID="robust_analy_reg2_$1" 
+# resources_dir="resources"
+resources_dir="s3://openproblems-data/resources/grn"
 
 publish_dir="${resources_dir}/results/${RUN_ID}"
 

src/api/comp_method.yaml

@@ -23,7 +23,7 @@ functionality:
       __merge__: file_prediction.yaml
       required: false
       direction: output
-      default: output/grn.csv
+      example: output/grn.csv
     - name: --temp_dir
       type: string
       direction: input

src/methods/multi_omics/scenicplus/config.vsh.yaml

@@ -33,7 +33,7 @@ functionality:
 
 platforms:
   - type: docker
-    image: apassemi/scenicplus:1.0.0
+    image: apassemi/scenicplus:1.0.1
     setup:
       - type: python
         packages: [ flatbuffers ]

src/methods/multi_omics/scenicplus/script.py

@@ -607,7 +607,7 @@
             os.path.join(out_dir, 'cistarget-db', 'v10nr_clust_public.zip')
         )
         with zipfile.ZipFile(os.path.join(out_dir, 'cistarget-db', 'v10nr_clust_public.zip'), 'r') as zip_ref:
-            zip_ref.extractall(os.path.join(out_dir))
+            zip_ref.extractall(os.path.join(out_dir, 'cistarget-db'))
 
     # Download chromosome sizes
     if not os.path.exists(os.path.join(out_dir, 'cistarget-db', 'hg38.chrom.sizes')):

src/methods/multi_omics/scglue/main.py

@@ -141,7 +141,6 @@ def cis_inference(par):
         if attr["qval"] < 0.05
     )
 
-
     scglue.genomics.Bed(atac.var).write_bed(f"{par['temp_dir']}/peaks.bed", ncols=3)
     scglue.genomics.write_links(
         gene2peak,
@@ -150,8 +149,6 @@ def cis_inference(par):
         f"{par['temp_dir']}/gene2peak.links", keep_attrs=["score"]
     )
 
-
-
     motif_bed = scglue.genomics.read_bed(par['motif_file']) ## http://download.gao-lab.org/GLUE/cisreg/JASPAR2022-hg38.bed.gz
     tfs = pd.Index(motif_bed["name"]).intersection(rna.var_names)
     rna[:, np.union1d(genes, tfs)].write_loom(f"{par['temp_dir']}/rna.loom")

src/metrics/regression_1/main.py

@@ -176,6 +176,7 @@ def main(par):
     tf_all = np.loadtxt(par['tf_all'], dtype=str)
     gene_names = perturbation_data.var.index.to_numpy()
     net = pd.read_csv(par['prediction'])
+    # net['weight'] = net.weight.abs()
     # subset to keep only those links with source as tf
     if par['apply_tf']:
         net = net[net.source.isin(tf_all)]

src/robustness_analysis/script.py

@@ -23,7 +23,7 @@
   assert 'weight' in prediction.columns 
   print('Add noise to weight')
   std_dev = prediction['weight'].std()
-  noise = np.random.normal(0, degree * std_dev, size=prediction['weight'].shape)
+  noise = np.random.normal(loc=0, scale=degree * std_dev, size=prediction['weight'].shape)
   prediction['weight'] += noise
 
 elif type == 'links': # shuffle source-target-weight

src/workflows/run_benchmark_single_omics/main.nf

@@ -24,16 +24,16 @@ workflow run_wf {
   // ]
 
   methods = [
-    ennet,
-    grnboost2,
-    scsgl,    
-    tigress
+    portia,
+    // ennet
+    grnboost2
+    // scsgl,    
+    // tigress
   ]
 
   // construct list of metrics
   metrics = [
-    regression_1,
-    regression_2
+    regression_1
   ]
 
   /****************************
@@ -87,7 +87,8 @@ workflow run_wf {
           method_id: comp.config.functionality.name,
           prediction: output.prediction
         ]
-      }
+      },
+      auto: [publish: "state"]
     )
 
     // run all metrics