# HG changeset patch
# User bgruening
# Date 1744624576 0
# Node ID b353dad17ab7b0ee8d1c90219e8d328c79be3752
# Parent 98431bd19f18edad599a25ce50da36e39634ecbc
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 973836fb40ecb9c0ac26f675d12b20fc8e5f51f4
diff -r 98431bd19f18 -r b353dad17ab7 fetch_cbioportal_data.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/fetch_cbioportal_data.py Mon Apr 14 09:56:16 2025 +0000
@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+
+import argparse
+import os
+
+from flexynesis.utils import CBioPortalData
+
+
+def main():
+ parser = argparse.ArgumentParser(description="Fetch and prepare cBioPortal data for Flexynesis.")
+ parser.add_argument("--study_id", required=True, help="cBioPortal study ID (e.g., 'brca_tcga')")
+ parser.add_argument("--data_types", required=True, help="Comma-separated list of data types (e.g., 'clin,mut,omics')")
+ parser.add_argument("--mapped_files", default=None, help="Comma-separated list of .txt files to map to data_types (optional)")
+ parser.add_argument("--split_ratio", type=float, default=0.7, help="Training/test split ratio (0.0 to 1.0)")
+ parser.add_argument("--output_dir", required=True, help="Output directory for datasets")
+
+ args = parser.parse_args()
+
+ data_types = args.data_types.split(",")
+ if "clin" not in data_types:
+ raise ValueError("Clinical data ('clin') is required for splitting the dataset.")
+
+ file_mapping = {
+ "clin": "data_clinical_patient.txt", # can be any with 'clinical' in file name
+ "mut": "data_mutations.txt", # any with 'mutations' in file name
+ "omics": "data_cna.txt",
+ "other": None
+ }
+
+ if args.mapped_files:
+ mapped_files = args.mapped_files.split(",")
+ if len(mapped_files) != len(data_types):
+ raise ValueError(f"Number of mapped files ({len(mapped_files)}) must match number of data types ({len(data_types)}).")
+ files_to_fetch = {dt: mf for dt, mf in zip(data_types, mapped_files)}
+ for mf in mapped_files:
+ if not mf.endswith(".txt"):
+ raise ValueError(f"Mapped file '{mf}' must end with '.txt'.")
+ else:
+ files_to_fetch = {dt: file_mapping[dt] for dt in data_types if dt in file_mapping}
+
+ invalid_types = set(data_types) - set(file_mapping.keys())
+ if invalid_types:
+ raise ValueError(f"Invalid data types: {invalid_types}. Supported types: {list(file_mapping.keys())}")
+
+ cbioportal = CBioPortalData(study_id=args.study_id)
+ cbioportal.get_cbioportal_data(study_id=args.study_id, files=files_to_fetch)
+ dataset = cbioportal.split_data(ratio=args.split_ratio)
+
+ os.makedirs(args.output_dir, exist_ok=True)
+
+ for data_type in data_types:
+ if data_type in dataset['train']:
+ train_file = os.path.join(args.output_dir, f"{data_type}_train.csv")
+ dataset['train'][data_type].to_csv(train_file, index=True)
+ if data_type in dataset['test']:
+ test_file = os.path.join(args.output_dir, f"{data_type}_test.csv")
+ dataset['test'][data_type].to_csv(test_file, index=True)
+
+
+if __name__ == "__main__":
+ main()
diff -r 98431bd19f18 -r b353dad17ab7 flexynesis.xml
--- a/flexynesis.xml Mon Aug 12 17:58:02 2024 +0000
+++ b/flexynesis.xml Mon Apr 14 09:56:16 2025 +0000
@@ -71,6 +71,7 @@
#end if
--fusion_type $fusion_type
--hpo_iter $hpo_iter
+ --val_size $val_size
--finetuning_samples $finetuning_samples
--variance_threshold $variance_threshold
--correlation_threshold $correlation_threshold
@@ -84,6 +85,7 @@
$use_loss_weighting
$use_cv
$evaluate_baseline_performance
+ --feature_importance_method $feature_importance_method
$disable_marker_finding
\${GALAXY_FLEXYNESIS_EXTRA_ARGUMENTS}
]]>
@@ -110,6 +112,7 @@
+
@@ -133,6 +136,7 @@
+
@@ -189,22 +193,26 @@
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
@@ -216,10 +224,18 @@
-
+
+
+
+
+
+
+
+
+
@@ -249,17 +265,21 @@
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
-
@@ -271,10 +291,18 @@
-
+
+
+
+
+
+
+
+
+
@@ -299,22 +327,26 @@
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
@@ -326,10 +358,18 @@
-
+
+
+
+
+
+
+
+
+
@@ -337,7 +377,7 @@
-
+
@@ -359,21 +399,23 @@
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
-
@@ -399,23 +441,25 @@
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-
@@ -451,25 +495,29 @@
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
@@ -481,7 +529,155 @@
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -512,46 +708,6 @@
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
.. class:: warningmark
diff -r 98431bd19f18 -r b353dad17ab7 macros.xml
--- a/macros.xml Mon Aug 12 17:58:02 2024 +0000
+++ b/macros.xml Mon Apr 14 09:56:16 2025 +0000
@@ -1,6 +1,6 @@
- 0.2.10
- 0
+ 0.2.17
+ 1
24.1
@@ -65,10 +65,16 @@
+
+
+
+
+
+