Mercurial > repos > bgruening > flexynesis
changeset 1:0bef7ea84b7f draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 973836fb40ecb9c0ac26f675d12b20fc8e5f51f4
| author | bgruening |
|---|---|
| date | Mon, 14 Apr 2025 09:56:46 +0000 |
| parents | bd808d1c4e0c |
| children | |
| files | fetch_cbioportal_data.py flexynesis.xml macros.xml |
| diffstat | 3 files changed, 340 insertions(+), 117 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fetch_cbioportal_data.py Mon Apr 14 09:56:46 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()
--- a/flexynesis.xml Mon Aug 12 17:58:14 2024 +0000 +++ b/flexynesis.xml Mon Apr 14 09:56:46 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} ]]></command> @@ -110,6 +112,7 @@ <option value="RandomForest">RandomForest</option> <option value="SVM">SVM</option> <option value="RandomSurvivalForest">RandomSurvivalForest</option> + <option value="XGBoost">XGBoost</option> </param> <when value="DirectPred"/> <when value="GNN"> @@ -133,6 +136,7 @@ <when value="RandomForest"/> <when value="SVM"/> <when value="RandomSurvivalForest"/> + <when value="XGBoost"/> </conditional> <param argument="--target_variables" type="text" label="Target variables" help="Which variables in 'clin.csv' to use for predictions, comma-separated if multiple."> <sanitizer invalid_char=""> @@ -189,22 +193,26 @@ <tests> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="foo"/> - </repeat> <conditional name="training_type"> <param name="model" value="s_train"/> - <param name="model_class" value="DirectPred"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> + <conditional name="model_class"> + <param name="model_class" value="DirectPred"/> + </conditional> <param name="target_variables" value="Erlotinib"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -216,10 +224,18 @@ <has_n_lines n="50"/> </assert_contents> </element> - <element name="job.feature_importance"> + <element name="job.feature_importance.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="GradientShap"/> + </assert_contents> + </element> + <element name="job.feature_importance.IntegratedGradients"> + <assert_contents> + <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> + <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="IntegratedGradients"/> </assert_contents> </element> <element name="job.feature_logs.bar"> @@ -249,17 +265,21 @@ </test> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> <conditional name="training_type"> <param name="model" value="s_train"/> - <param name="model_class" value="DirectPred"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <conditional name="model_class"> + <param name="model_class" value="DirectPred"/> + </conditional> <param name="target_variables" value="Erlotinib"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -271,10 +291,18 @@ <has_n_lines n="50"/> </assert_contents> </element> - <element name="job.feature_importance"> + <element name="job.feature_importance.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="GradientShap"/> + </assert_contents> + </element> + <element name="job.feature_importance.IntegratedGradients"> + <assert_contents> + <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> + <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="IntegratedGradients"/> </assert_contents> </element> <element name="job.feature_logs.bar"> @@ -299,22 +327,26 @@ </test> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="foo"/> - </repeat> <conditional name="training_type"> <param name="model" value="s_train"/> - <param name="model_class" value="DirectPred"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> + <conditional name="model_class"> + <param name="model_class" value="DirectPred"/> + </conditional> <param name="target_variables" value="Irinotecan"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -326,10 +358,18 @@ <has_n_lines n="50"/> </assert_contents> </element> - <element name="job.feature_importance"> + <element name="job.feature_importance.GradientShap"> <assert_contents> <has_text_matching expression="Irinotecan,0,,bar,A2M,"/> <has_text_matching expression="Irinotecan,0,,bar,ABCC4,"/> + <has_text_matching expression="GradientShap"/> + </assert_contents> + </element> + <element name="job.feature_importance.IntegratedGradients"> + <assert_contents> + <has_text_matching expression="Irinotecan,0,,bar,A2M,"/> + <has_text_matching expression="Irinotecan,0,,bar,ABCC4,"/> + <has_text_matching expression="IntegratedGradients"/> </assert_contents> </element> <element name="job.feature_logs.bar"> @@ -337,7 +377,7 @@ <has_n_lines n="25"/> </assert_contents> </element> - <element name="job.feature_logs.bar"> + <element name="job.feature_logs.omics_foo"> <assert_contents> <has_n_lines n="25"/> </assert_contents> @@ -359,21 +399,23 @@ </test> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="foo"/> - </repeat> <conditional name="training_type"> <param name="model" value="us_train"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> <param name="model_class" value="supervised_vae"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -399,23 +441,25 @@ </test> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> - <param name="layer_main" value="input"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="foo"/> - <param name="layer" value="output"/> - </repeat> <conditional name="training_type"> <param name="model" value="cm_train"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <param name="layer_main" value="input"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + <param name="layer" value="output"/> + </repeat> <param name="model_class" value="CrossModalPred"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -451,25 +495,29 @@ </test> <test> <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="bar"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="foo"/> - </repeat> <conditional name="training_type"> <param name="model" value="s_train"/> - <param name="model_class" value="GNN"/> - <param name="gnn_conv_type" value="GC"/> - <param name="string_organism" value="9606"/> - <param name="string_node_name" value="gene_name"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> + <conditional name="model_class"> + <param name="model_class" value="GNN"/> + <param name="gnn_conv_type" value="GC"/> + <param name="string_organism" value="9606"/> + <param name="string_node_name" value="gene_name"/> + </conditional> <param name="target_variables" value="Erlotinib"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> </conditional> - <param name="hpo_iter" value="1"/> <output_collection name="results" type="list"> <element name="job.embeddings_test"> <assert_contents> @@ -481,7 +529,155 @@ <has_n_lines n="50"/> </assert_contents> </element> - <element name="job.feature_importance"> + <element name="job.feature_importance.GradientShap"> + <assert_contents> + <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> + <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="GradientShap"/> + </assert_contents> + </element> + <element name="job.feature_importance.IntegratedGradients"> + <assert_contents> + <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> + <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> + <has_text_matching expression="IntegratedGradients"/> + </assert_contents> + </element> + <element name="job.feature_logs.bar"> + <assert_contents> + <has_n_lines n="25"/> + </assert_contents> + </element> + <element name="job.feature_logs.omics_foo"> + <assert_contents> + <has_n_lines n="25"/> + </assert_contents> + </element> + <element name="job.predicted_labels"> + <assert_contents> + <has_text_matching expression="source_dataset:A-704,Erlotinib,"/> + <has_text_matching expression="target_dataset:KMRC-20,Erlotinib,"/> + </assert_contents> + </element> + <element name="job.stats"> + <assert_contents> + <has_text_matching expression="GNN,Erlotinib,numerical,mse,"/> + <has_text_matching expression="GNN,Erlotinib,numerical,r2,"/> + <has_text_matching expression="GNN,Erlotinib,numerical,pearson_corr,"/> + </assert_contents> + </element> + </output_collection> + </test> + <test> + <param name="non_commercial_use" value="True"/> + <conditional name="training_type"> + <param name="model" value="us_train"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="b ar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="f oo"/> + </repeat> + <param name="model_class" value="supervised_vae"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> + </conditional> + <output_collection name="results" type="list"> + <element name="job.embeddings_test"> + <assert_contents> + <has_n_lines n="50"/> + </assert_contents> + </element> + <element name="job.embeddings_train"> + <assert_contents> + <has_n_lines n="50"/> + </assert_contents> + </element> + <element name="job.feature_logs.b_ar"> + <assert_contents> + <has_n_lines n="25"/> + </assert_contents> + </element> + <element name="job.feature_logs.omics_f_oo"> + <assert_contents> + <has_n_lines n="25"/> + </assert_contents> + </element> + </output_collection> + </test> + <test> + <param name="non_commercial_use" value="True"/> + <conditional name="training_type"> + <param name="model" value="s_train"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> + <conditional name="model_class"> + <param name="model_class" value="XGBoost"/> + </conditional> + <param name="target_variables" value="Erlotinib"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + </section> + </conditional> + <output_collection name="results" type="list"> + <element name="job.stats"> + <assert_contents> + <has_text_matching expression="XGBoostRegressor,Erlotinib,numerical,mse,"/> + <has_text_matching expression="XGBoostRegressor,Erlotinib,numerical,r2,"/> + <has_text_matching expression="XGBoostRegressor,Erlotinib,numerical,pearson_corr,"/> + </assert_contents> + </element> + </output_collection> + </test> + <test> + <param name="non_commercial_use" value="True"/> + <conditional name="training_type"> + <param name="model" value="s_train"/> + <param name="train_clin" value="train/clin" ftype="csv"/> + <param name="test_clin" value="test/clin" ftype="csv"/> + <param name="train_omics_main" value="train/gex" ftype="csv"/> + <param name="test_omics_main" value="test/gex" ftype="csv"/> + <param name="assay_main" value="bar"/> + <repeat name="omics"> + <param name="train_omics" value="train/cnv" ftype="csv"/> + <param name="test_omics" value="test/cnv" ftype="csv"/> + <param name="assay" value="foo"/> + </repeat> + <conditional name="model_class"> + <param name="model_class" value="DirectPred"/> + </conditional> + <param name="target_variables" value="Erlotinib"/> + <section name="advanced"> + <param name="hpo_iter" value="1"/> + <param name="feature_importance_method" value="IntegratedGradients"/> + <param name="val_size" value="0.2"/> + </section> + </conditional> + <output_collection name="results" type="list"> + <element name="job.embeddings_test"> + <assert_contents> + <has_n_lines n="50"/> + </assert_contents> + </element> + <element name="job.embeddings_train"> + <assert_contents> + <has_n_lines n="50"/> + </assert_contents> + </element> + <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib,0,,bar,A2M,"/> <has_text_matching expression="Erlotinib,0,,bar,ABCC4,"/> @@ -512,46 +708,6 @@ </element> </output_collection> </test> - <test> - <param name="non_commercial_use" value="True"/> - <param name="train_clin" value="train/clin" ftype="csv"/> - <param name="test_clin" value="test/clin" ftype="csv"/> - <param name="train_omics_main" value="train/gex" ftype="csv"/> - <param name="test_omics_main" value="test/gex" ftype="csv"/> - <param name="assay_main" value="b ar"/> - <repeat name="omics"> - <param name="train_omics" value="train/cnv" ftype="csv"/> - <param name="test_omics" value="test/cnv" ftype="csv"/> - <param name="assay" value="f oo"/> - </repeat> - <conditional name="training_type"> - <param name="model" value="us_train"/> - <param name="model_class" value="supervised_vae"/> - </conditional> - <param name="hpo_iter" value="1"/> - <output_collection name="results" type="list"> - <element name="job.embeddings_test"> - <assert_contents> - <has_n_lines n="50"/> - </assert_contents> - </element> - <element name="job.embeddings_train"> - <assert_contents> - <has_n_lines n="50"/> - </assert_contents> - </element> - <element name="job.feature_logs.b_ar"> - <assert_contents> - <has_n_lines n="25"/> - </assert_contents> - </element> - <element name="job.feature_logs.omics_f_oo"> - <assert_contents> - <has_n_lines n="25"/> - </assert_contents> - </element> - </output_collection> - </test> </tests> <help> .. class:: warningmark
--- a/macros.xml Mon Aug 12 17:58:14 2024 +0000 +++ b/macros.xml Mon Apr 14 09:56:46 2025 +0000 @@ -1,6 +1,6 @@ <macros> - <token name="@TOOL_VERSION@">0.2.10</token> - <token name="@VERSION_SUFFIX@">0</token> + <token name="@TOOL_VERSION@">0.2.17</token> + <token name="@VERSION_SUFFIX@">1</token> <token name="@PROFILE@">24.1</token> <xml name="requirements"> <requirements> @@ -65,10 +65,16 @@ <param argument="--log_transform" type="boolean" truevalue="--log_transform True" falsevalue="" checked="false" label="Whether to apply log-transformation to input data matrices" /> <param argument="--early_stop_patience" type="integer" min="-1" value="10" label="How many epochs to wait when no improvements in validation loss are observed." help="Set to -1 to disable early stopping." /> <param argument="--hpo_iter" type="integer" min="1" value="100" label="Number of iterations for hyperparameter optimisation." /> + <param argument="--val_size" type="float" min="0.0" max="1" value="0.2" label="Proportion of training data to be used as validation split"/> <param argument="--hpo_patience" type="integer" min="0" value="10" label="How many hyperparameter optimisation iterations to wait for when no improvements are observed." help="Set to 0 to disable early stopping." /> <param argument="--use_cv" type="boolean" truevalue="--use_cv" falsevalue="" checked="false" label="Cross validation" help="If set, a 5-fold cross-validation training will be done. Otherwise, a single training on 80 percent of the dataset is done. " /> <param argument="--use_loss_weighting" type="boolean" truevalue="--use_loss_weighting True" falsevalue="" checked="true" label="Whether to apply loss-balancing using uncertainty weights method." /> <param argument="--evaluate_baseline_performance" type="boolean" truevalue="--evaluate_baseline_performance" falsevalue="" checked="false" label="Enable modeling also with Random Forest + SVMs to see the performance of off-the-shelf tools on the same dataset." /> + <param argument="--feature_importance_method" type="select" label="which method(s) to use to compute feature importance scores."> + <option value="Both" selected="true">Both</option> + <option value="IntegratedGradients">IntegratedGradients</option> + <option value="GradientShap">GradientShap</option> + </param> <param argument="--disable_marker_finding" type="boolean" truevalue="--disable_marker_finding" falsevalue="" checked="false" label="Disable marker discovery after model training." /> </section> </xml>