Mercurial > repos > bgruening > flexynesis
view flexynesis.xml @ 6:33816f44fc7d draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 6b520305ec30e6dc37eba92c67a5368cea0fc5ad
| author | bgruening |
|---|---|
| date | Wed, 23 Jul 2025 07:49:41 +0000 |
| parents | 466b593fd87e |
| children |
line wrap: on
line source
<tool id="flexynesis" name="Flexynesis" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> <description>A deep-learning based multi-omics bulk sequencing data integration suite</description> <macros> <import>macros.xml</import> </macros> <expand macro="edam"/> <expand macro="requirements"/> <required_files> <include path="flexynesis_plot.py" /> <include path="flexynesis_utils.py" /> <include path="convert.py" /> <include path="index_to_name.py" /> </required_files> <command detect_errors="exit_code"><![CDATA[ @CHECK_NON_COMMERCIAL_USE@ mkdir -p input/test input/train output && ln -s '$train_clin' input/train/clin.tabular && python '$__tool_directory__/convert.py' input/train/clin.tabular input/train/clin.csv && ln -s '$test_clin' input/test/clin.tabular && python '$__tool_directory__/convert.py' input/test/clin.tabular input/test/clin.csv && #if str($assay_main) != '': #set $name = str($assay_main.replace(" ", "_")) ln -s '$train_omics_main' input/train/${name}.tabular && python '$__tool_directory__/convert.py' input/train/${name}.tabular input/train/${name}.csv && ln -s '$test_omics_main' input/test/${name}.tabular && python '$__tool_directory__/convert.py' input/test/${name}.tabular input/test/${name}.csv && #set $data_names = [$name] #else ln -s '$train_omics_main' input/train/main.tabular && python '$__tool_directory__/convert.py' input/train/main.tabular input/train/main.csv && ln -s '$test_omics_main' input/test/main.tabular && python '$__tool_directory__/convert.py' input/test/main.tabular input/test/main.csv && #set $data_names = ['main'] #end if #if str($training_type.model) == 'cm_train': #if str($layer_main) == 'input': #set $input_layers = $data_names #set $output_layers = [] #else #set $input_layers = [] #set $output_layers = $data_names #end if #end if #for $i, $element in enumerate($omics) #if str($element.train_omics) != 'None' and str($element.test_omics) != 'None': #if str($element.assay) != '': #set $i = str($element.assay.replace(" ", "_")) ln -s '${element.train_omics}' input/train/${i}.tabular && python '$__tool_directory__/convert.py' input/train/${i}.tabular input/train/${i}.csv && ln -s '${element.test_omics}' input/test/${i}.tabular && python '$__tool_directory__/convert.py' input/test/${i}.tabular input/test/${i}.csv && $data_names.append(str($i)) #if str($training_type.model) == 'cm_train': #if str($element.layer) == 'input': $input_layers.append(str($i)) #else $output_layers.append(str($i)) #end if #end if #else ln -s '${element.train_omics}' input/train/omics_${i}.tabular && python '$__tool_directory__/convert.py' input/train/omics_${i}.tabular input/train/omics_${i}.csv && ln -s '${element.test_omics}' input/test/omics_${i}.tabular && python '$__tool_directory__/convert.py' input/test/omics_${i}.tabular input/test/omics_${i}.csv && $data_names.append("omics_" + str($i)) #if str($training_type.model) == 'cm_train': #if str($element.layer) == 'input': $input_layers.append("omics_" + str($i)) #else $output_layers.append("omics_" + str($i)) #end if #end if #end if #end if #end for #if str($training_type.model) == 's_train': ## set target variables #if str($target_variables) != 'None': targets=`'$__tool_directory__/index_to_name.py' input/train/clin.csv $target_variables` && echo "Target variables: \$targets" && #end if ## set survival variables #if str($surv_event_var) != 'None' and str($surv_time_var) != 'None': survival_event=`'$__tool_directory__/index_to_name.py' input/train/clin.csv $surv_event_var` && ## check if survival variable is numerical echo "Survival event variable: \$survival_event" && python '$__tool_directory__/flexynesis_utils.py' --util validate_survival --clin input/train/clin.csv --clin_variable \$survival_event && survival_time=`$__tool_directory__/index_to_name.py input/train/clin.csv $surv_time_var` && echo "Survival time variable: \$survival_time" && #end if ## set clinical variables for Cox model #if str($plot.plot_cox_conditional.plot_cox) == 'yes': #if str($plot.plot_cox_conditional.clinical_variables) != 'None': covars=`'$__tool_directory__/index_to_name.py' input/train/clin.csv $plot.plot_cox_conditional.clinical_variables` && ## check if covariates is numerical echo "Clinical variables for Cox model: \$covars" && python '$__tool_directory__/flexynesis_utils.py' --util validate_covariate --clin input/train/clin.csv --clin_variable \$covars && #end if #end if #end if flexynesis --data_path input --outdir output --model_class $model_class #if str($model_class) == 'GNN': --gnn_conv_type $gnn_conv_type --string_organism $string_organism --string_node_name $string_node_name #end if #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_variables \$targets #end if #if str($surv_event_var) != 'None' and str($surv_time_var) != 'None': --surv_event_var \$survival_event --surv_time_var \$survival_time #end if #end if #if str($training_type.model) == 'cm_train': --input_layers $str(",".join($input_layers)) --output_layers $str(",".join($output_layers)) #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 --subsample $subsample --features_min $features_min --features_top_percentile $features_top_percentile --data_types $str(",".join($data_names)) --early_stop_patience $early_stop_patience --hpo_patience $hpo_patience $log_transform $use_loss_weighting $use_cv $evaluate_baseline_performance --feature_importance_method $feature_importance_method \${GALAXY_FLEXYNESIS_EXTRA_ARGUMENTS} ## convert flexynesis output files to tabular format && for file in output/*.csv; do if [ -f "\$file" ]; then basename="\${file%.csv}"; python '$__tool_directory__/convert.py' "\$file" "\${basename}.tabular"; echo "Converted \$file to \${basename}.tabular"; fi done #if str($training_type.model) == 's_train': #if str($plot.plot_embeddings_conditional.plot_embeddings) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type dimred --embeddings output/job.embeddings_test.tabular --labels output/job.predicted_labels.tabular --method $plot.plot_embeddings_conditional.method #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_embeddings_conditional.format --dpi $plot.plot_embeddings_conditional.dpi #end if #if str($plot.plot_km_conditional.plot_km) == 'yes': #if str($surv_event_var) == '' or str($surv_time_var) == '': && echo "Survival event and time variables must be specified for Kaplan-Meier plots." && exit 1 #else && python '$__tool_directory__/flexynesis_plot.py' --plot_type kaplan_meier --labels output/job.predicted_labels.tabular --survival_data input/test/clin.csv --surv_event_var \$survival_event --surv_time_var \$survival_time --output_dir plots --format $plot.plot_km_conditional.format --dpi $plot.plot_km_conditional.dpi #end if #end if #if str($plot.plot_cox_conditional.plot_cox) == 'yes': #if str($surv_event_var) == '' or str($surv_time_var) == '': && echo "Survival event and time variables must be specified for cox plots." && exit 1 #else && python '$__tool_directory__/flexynesis_plot.py' --plot_type cox #if str($feature_importance_method) == 'GradientShap': --important_features output/job.feature_importance.GradientShap.tabular #else if str($feature_importance_method) == 'IntegratedGradients': --important_features output/job.feature_importance.IntegratedGradients.tabular #else --important_features output/job.feature_importance.IntegratedGradients.tabular #end if --clinical_train input/train/clin.csv --clinical_test input/test/clin.csv #if str($plot.plot_cox_conditional.omics_name) != '': #set $omics_name = str($plot.plot_cox_conditional.omics_name.replace(" ", "_")) --omics_train input/train/${omics_name}.csv --omics_test input/test/${omics_name}.csv --layer ${omics_name} #else --omics_train input/train/${data_names}.csv --omics_test input/test/${data_names}.csv --layer ${data_names} #end if --surv_time_var \$survival_time --surv_event_var \$survival_event #if str($plot.plot_cox_conditional.clinical_variables) != 'None': --clinical_variables \$covars #end if --top_features $plot.plot_cox_conditional.top_features #if str($plot.plot_cox_conditional.crossval_conditional.crossval) == 'yes': --crossval #end if #if str($plot.plot_cox_conditional.crossval_conditional.crossval) == 'yes': --n_splits $plot.plot_cox_conditional.crossval_conditional.n_splits #end if --random_state 42 --output_dir plots --format $plot.plot_cox_conditional.format --dpi $plot.plot_cox_conditional.dpi #end if #end if #if str($plot.plot_scatter_conditional.plot_scatter) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type scatter --labels output/job.predicted_labels.tabular #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_scatter_conditional.format --dpi $plot.plot_scatter_conditional.dpi #end if #if str($plot.plot_concordance_conditional.plot_concordance) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type concordance_heatmap --labels output/job.predicted_labels.tabular #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_concordance_conditional.format --dpi $plot.plot_concordance_conditional.dpi #end if #if str($plot.plot_pr_curves_conditional.plot_pr_curves) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type pr_curve --labels output/job.predicted_labels.tabular #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_pr_curves_conditional.format --dpi $plot.plot_pr_curves_conditional.dpi #end if #if str($plot.plot_roc_curves_conditional.plot_roc_curves) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type roc_curve --labels output/job.predicted_labels.tabular #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_roc_curves_conditional.format --dpi $plot.plot_roc_curves_conditional.dpi #end if #if str($plot.plot_boxplot_conditional.plot_boxplot) == 'yes': && python '$__tool_directory__/flexynesis_plot.py' --plot_type box_plot --labels output/job.predicted_labels.tabular #if str($training_type.model) == 's_train': #if str($target_variables) != 'None': --target_value \$targets #end if #end if --output_dir plots --format $plot.plot_boxplot_conditional.format --dpi $plot.plot_boxplot_conditional.dpi #end if #end if ]]></command> <inputs> <expand macro="commercial_use_param"/> <conditional name="training_type"> <param name="model" type="select" label="Type of Analysis" > <option value="s_train">Supervised training</option> <option value="us_train">Unsupervised Training</option> <option value="cm_train">Cross-modality Training</option> </param> <when value="s_train"> <expand macro="main_inputs"/> <repeat name="omics" min="0" title="Multiple omics layers?"> <expand macro="extra_inputs"/> </repeat> <conditional name="model_class" label="Model class"> <param argument="--model_class" type="select" label="Model class" help="The kind of model class to instantiate"> <option value="DirectPred">DirectPred</option> <option value="GNN">GNN</option> <option value="MultiTripletNetwork">MultiTripletNetwork</option> <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"> <param argument="--gnn_conv_type" type="select" label="Which graph convolution type to use."> <option value="GC">GC</option> <option value="GCN">GCN</option> <option value="SAGE">SAGE</option> </param> <param argument="--string_organism" type="select" label="STRING DB organism"> <option value="9606">Homo sapiens</option> <option value="10090">Mus musculus</option> <option value="10116">Rattus norvegicus</option> <option value="9544">Macaca mulatta</option> </param> <param argument="--string_node_name" type="select" label="String node name" > <option value="gene_name">Gene name</option> <option value="gene_id">Gene id</option> </param> </when> <when value="MultiTripletNetwork"/> <when value="RandomForest"/> <when value="SVM"/> <when value="RandomSurvivalForest"/> <when value="XGBoost"/> </conditional> <param argument="--target_variables" type="data_column" data_ref="train_clin" optional="true" multiple="true" label="Column name in the train clinical data to use for predictions, multiple targets are allowed"/> <param argument="--surv_event_var" type="data_column" data_ref="train_clin" optional="true" label="Column name in the train clinical data to use as survival event"/> <param argument="--surv_time_var" type="data_column" data_ref="train_clin" optional="true" label="Column name in the train clinical data to use as survival time"/> <expand macro="advanced"/> <section name="plot" title="Visualization"> <conditional name="plot_embeddings_conditional"> <param name="plot_embeddings" type="select" label="Generate embeddings plot?" help="Generate PCA or UMAP plot of the test dataset"> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <param name="method" type="select" label="Transformation method"> <option value="pca" selected="true">PCA</option> <option value="umap">UMAP</option> </param> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_km_conditional"> <param name="plot_km" type="select" label="Generate kaplan meier curves plot?" help="Generate KM curves plot of risk subtype based on predicted events probabilities"> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_cox_conditional"> <param name="plot_cox" type="select" label="Generate hazard ratio plot?" help="Performs Cox regression on data based on top features and selected clinical covariates."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <param name="omics_name" type="text" label="Omics layer to use for cox input" optional="true" help="If not specified, the first omics layer will be used."> <expand macro="sanitizer_printable"/> </param> <param argument="--clinical_variables" type="data_column" data_ref="train_clin" optional="true" multiple="true" label="Columns in the train clinical data to use as clinical covariates and include in the Cox model (e.g SEX, AGE, ...), multiple covariates are allowed"/> <param argument="--top_features" type="integer" min="1" value="20" label="Number of top important features to include in Cox model"/> <conditional name="crossval_conditional"> <param name="crossval" type="select" label="Performs K-fold cross-validation?"> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="yes"> <param name="n_splits" type="integer" min="2" value="5" label="Number of folds for cross-validation"/> </when> <when value="no"/> </conditional> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_scatter_conditional"> <param name="plot_scatter" type="select" label="Generate scatter plot?" help="Generates a scatter plot of numeric true and predicted labels for all available targets."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_concordance_conditional"> <param name="plot_concordance" type="select" label="Generate concordance heatmap plot?" help="Generates a plot showing the concordance between true and predicted labels for all targets."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_pr_curves_conditional"> <param name="plot_pr_curves" type="select" label="Generate precision-recall curves plot?" help="Generates precision-recall curves for all available targets."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_roc_curves_conditional"> <param name="plot_roc_curves" type="select" label="Generate ROC curves plot?" help="Generates ROC curves for all available targets."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> <conditional name="plot_boxplot_conditional"> <param name="plot_boxplot" type="select" label="Generate boxplot?" help="Generates a boxplot for all available targets."> <option value="yes">Yes</option> <option value="no" selected="true">No</option> </param> <when value="no"> </when> <when value="yes"> <expand macro="plots_common_param"/> </when> </conditional> </section> </when> <when value="us_train"> <expand macro="main_inputs"/> <repeat name="omics" min="0" title="Multiple omics layers?"> <expand macro="extra_inputs"/> </repeat> <param argument="--model_class" type="select" label="Model class" help="The kind of model class to instantiate"> <option value="supervised_vae">supervised_vae</option> </param> <expand macro="advanced"/> </when> <when value="cm_train"> <expand macro="main_inputs"/> <param name="layer_main" type="select" label="Use this omics data as input or output layer?"> <option value="input">Input</option> <option value="output">output</option> </param> <repeat name="omics" min="0" title="Multiple omics layers?"> <expand macro="extra_inputs"/> <param name="layer" type="select" label="Use this omics data as input or output layer?"> <option value="input">Input</option> <option value="output">output</option> </param> </repeat> <param argument="--model_class" type="select" label="Model class" help="The kind of model class to instantiate"> <option value="CrossModalPred">CrossModalPred</option> </param> <expand macro="advanced"/> </when> </conditional> </inputs> <outputs> <collection name="results" type="list" label="${tool.name} on ${on_string}: results"> <discover_datasets pattern="(?P<name>.+)\.tabular$" format="tabular" directory="output"/> </collection> <collection name="plots" type="list" label="${tool.name} on ${on_string}: plots"> <discover_datasets pattern="__name_and_ext__" directory="plots"/> <filter>training_type['model'] == 's_train' and (training_type['plot']['plot_embeddings_conditional']['plot_embeddings'] == 'yes' or training_type['plot']['plot_km_conditional']['plot_km'] == 'yes' or training_type['plot']['plot_cox_conditional']['plot_cox'] == 'yes' or training_type['plot']['plot_scatter_conditional']['plot_scatter'] == 'yes' or training_type['plot']['plot_concordance_conditional']['plot_concordance'] == 'yes' or training_type['plot']['plot_pr_curves_conditional']['plot_pr_curves'] == 'yes' or training_type['plot']['plot_roc_curves_conditional']['plot_roc_curves'] == 'yes' or training_type['plot']['plot_boxplot_conditional']['plot_boxplot'] == 'yes')</filter> </collection> </outputs> <tests> <!-- test 1: Supervised training with GEX and CNV data, DirectPred model, Erlotinib target --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="3"/> <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_importance.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <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.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\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 2: Supervised training with GEX data, DirectPred model, Erlotinib target --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="3"/> <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_importance.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <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.predicted_labels"> <assert_contents> <has_text_matching expression="source_dataset:A-704\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 3: Supervised training with GEX and CNV data, DirectPred model, Irinotecan target --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="4"/> <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_importance.GradientShap"> <assert_contents> <has_text_matching expression="Irinotecan\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Irinotecan\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Irinotecan\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Irinotecan\t0\t\tbar\tABCC4\t"/> <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.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\tIrinotecan\t"/> <has_text_matching expression="target_dataset:KMRC-20\tIrinotecan\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tIrinotecan\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tIrinotecan\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tIrinotecan\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 4: Un-supervised training with GEX and CNV data, supervised_vae model --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </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.bar"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> <element name="job.feature_logs.foo"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> </output_collection> </test> <!-- test 5: Cross-modality training with GEX and CNV data, CrossModalPred model --> <test expect_num_outputs="1"> <param name="non_commercial_use" value="True"/> <conditional name="training_type"> <param name="model" value="cm_train"/> <param name="train_clin" value="train/clin" ftype="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <param name="layer_main" value="input"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <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> <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.bar"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> <element name="job.feature_logs.foo"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> <element name="job.test_decoded.foo"> <assert_contents> <has_n_lines n="23"/> </assert_contents> </element> <element name="job.train_decoded.foo"> <assert_contents> <has_n_lines n="23"/> </assert_contents> </element> </output_collection> </test> <!-- test 6: Supervised training with GEX and CNV data, GNN model, Erlotinib target --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <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="3"/> <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_importance.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <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.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\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="GNN\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="GNN\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="GNN\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 7: test 4 + checking whitespace in assay name --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="b ar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <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.f_oo"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> </output_collection> </test> <!-- test 8: Supervised training with GEX and CNV data, XGBoost model, Erlotinib target --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="XGBoost"/> </conditional> <param name="target_variables" value="3"/> <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\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="XGBoostRegressor\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="XGBoostRegressor\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 9: test 1 + checking IntegratedGradients method --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="3"/> <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\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> </assert_contents> </element> <element name="job.feature_logs.bar"> <assert_contents> <has_n_lines n="25"/> </assert_contents> </element> <element name="job.feature_logs.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\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> <!-- test 10: dimred plot --> <test expect_num_outputs="2"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="3"/> <section name="advanced"> <param name="hpo_iter" value="1"/> </section> <section name="plot"> <conditional name="plot_embeddings_conditional"> <param name="plot_embeddings" value="yes"/> <param name="method" value="pca"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </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.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <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.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\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> <output_collection name="plots" type="list"> <element name="job.embeddings_test_pca_Erlotinib_known"> <assert_contents> <has_image_center_of_mass center_of_mass="962,732" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1941" delta="10"/> </assert_contents> </element> <element name="job.embeddings_test_pca_Erlotinib_predicted"> <assert_contents> <has_image_center_of_mass center_of_mass="959.5,732.5" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1941" delta="10"/> </assert_contents> </element> </output_collection> </test> <!-- test 11: km plot --> <test expect_num_outputs="2"> <expand macro="common_test"> <section name="plot"> <conditional name="plot_km_conditional"> <param name="plot_km" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="clin_km_km_risk_subtypes"> <assert_contents> <has_image_center_of_mass center_of_mass="971,732" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1941" delta="10"/> </assert_contents> </element> </output_collection> </test> <!-- test 12: cox plot --> <test expect_num_outputs="2"> <expand macro="common_test"> <section name="plot"> <conditional name="plot_cox_conditional"> <param name="plot_cox" value="yes"/> <param name="omics_name" value="bar"/> <param name="clinical_variables" value="2,3"/> <param name="top_features" value="10"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.feature_importance.IntegratedGradients_cox_hazard_ratios"> <assert_contents> <has_image_center_of_mass center_of_mass="972,737" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1941" delta="10"/> </assert_contents> </element> </output_collection> </test> <!-- test 13: scatter plot --> <test expect_num_outputs="2"> <expand macro="common_test"> <section name="plot"> <conditional name="plot_scatter_conditional"> <param name="plot_scatter" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.predicted_labels_scatter_Erlotinib"> <assert_contents> <has_image_center_of_mass center_of_mass="969,735" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1940" delta="10"/> </assert_contents> </element> </output_collection> </test> <!-- test 14: concordance plot --> <test expect_num_outputs="2"> <expand macro="common_test"> <section name="plot"> <conditional name="plot_concordance_conditional"> <param name="plot_concordance" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.predicted_labels_concordance_Erlotinib"> <assert_contents> <has_image_center_of_mass center_of_mass="1547,1590" eps="30"/> <has_image_channels channels="3"/> <has_image_height height="3000" delta="50"/> <has_image_width width="3192" delta="50"/> </assert_contents> </element> </output_collection> </test> <!-- test 15: pr curve plot --> <test expect_num_outputs="2"> <expand macro="common_test_class"> <section name="plot"> <conditional name="plot_pr_curves_conditional"> <param name="plot_pr_curves" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.predicted_labels_pr_curves_class"> <assert_contents> <has_image_center_of_mass center_of_mass="975,732" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="20"/> <has_image_width width="1941" delta="20"/> </assert_contents> </element> </output_collection> </test> <!-- test 16: roc curve plot --> <test expect_num_outputs="2"> <expand macro="common_test_class"> <section name="plot"> <conditional name="plot_roc_curves_conditional"> <param name="plot_roc_curves" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.predicted_labels_roc_curves_class"> <assert_contents> <has_image_center_of_mass center_of_mass="970,730" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="20"/> <has_image_width width="1941" delta="20"/> </assert_contents> </element> </output_collection> </test> <!-- test 17: boxplot plot --> <test expect_num_outputs="2"> <expand macro="common_test_class"> <section name="plot"> <conditional name="plot_boxplot_conditional"> <param name="plot_boxplot" value="yes"/> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.predicted_labels_box_plot_class_buz"> <assert_contents> <has_image_center_of_mass center_of_mass="1485,882" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1783" delta="20"/> <has_image_width width="2967" delta="20"/> </assert_contents> </element> <element name="job.predicted_labels_box_plot_class_qux"> <assert_contents> <has_image_center_of_mass center_of_mass="1485,882" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1765" delta="20"/> <has_image_width width="2967" delta="20"/> </assert_contents> </element> </output_collection> </test> <!-- test 18: cox plot with multiple clinical variables + crossvar--> <test expect_num_outputs="2"> <expand macro="common_test"> <section name="plot"> <conditional name="plot_cox_conditional"> <param name="plot_cox" value="yes"/> <param name="omics_name" value="bar"/> <param name="clinical_variables" value="2,3"/> <param name="top_features" value="10"/> <conditional name="crossval_conditional"> <param name="crossval" value="yes"/> <param name="n_splits" value="5"/> </conditional> <param name="format" value="jpg"/> <param name="dpi" value="300"/> </conditional> </section> </expand> <output_collection name="plots" type="list"> <element name="job.feature_importance.IntegratedGradients_cox_hazard_ratios"> <assert_contents> <has_image_center_of_mass center_of_mass="972,737" eps="20"/> <has_image_channels channels="3"/> <has_image_height height="1461" delta="10"/> <has_image_width width="1941" delta="10"/> </assert_contents> </element> </output_collection> </test> <!-- test 19: Supervised training with GEX and CNV data, DirectPred model, Erlotinib and Crizotinib targets --> <test expect_num_outputs="1"> <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="tabular"/> <param name="test_clin" value="test/clin" ftype="tabular"/> <param name="train_omics_main" value="train/gex" ftype="tabular"/> <param name="test_omics_main" value="test/gex" ftype="tabular"/> <param name="assay_main" value="bar"/> <repeat name="omics"> <param name="train_omics" value="train/cnv" ftype="tabular"/> <param name="test_omics" value="test/cnv" ftype="tabular"/> <param name="assay" value="foo"/> </repeat> <conditional name="model_class"> <param name="model_class" value="DirectPred"/> </conditional> <param name="target_variables" value="3,2"/> <section name="advanced"> <param name="hpo_iter" value="1"/> </section> </conditional> <assert_stdout> <has_text_matching expression="Target variables: Erlotinib,Crizotinib"/> </assert_stdout> <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.GradientShap"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="Crizotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Crizotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="GradientShap"/> </assert_contents> </element> <element name="job.feature_importance.IntegratedGradients"> <assert_contents> <has_text_matching expression="Erlotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Erlotinib\t0\t\tbar\tABCC4\t"/> <has_text_matching expression="Crizotinib\t0\t\tbar\tA2M\t"/> <has_text_matching expression="Crizotinib\t0\t\tbar\tABCC4\t"/> <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.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\tErlotinib\t"/> <has_text_matching expression="source_dataset:A-704\tCrizotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tErlotinib\t"/> <has_text_matching expression="target_dataset:KMRC-20\tCrizotinib\t"/> </assert_contents> </element> <element name="job.stats"> <assert_contents> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tCrizotinib\tnumerical\tmse\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tCrizotinib\tnumerical\tr2\t"/> <has_text_matching expression="DirectPred\tErlotinib\tnumerical\tpearson_corr\t"/> <has_text_matching expression="DirectPred\tCrizotinib\tnumerical\tpearson_corr\t"/> </assert_contents> </element> </output_collection> </test> </tests> <help><![CDATA[ @COMMON_HELP@ .. image:: https://raw.githubusercontent.com/BIMSBbioinfo/flexynesis/c4634d97f84e51f569dcfdab2caf42c9be453ef6/img/graphical_abstract.jpg :width: 600 ----- **Input Files** **clin.tabular** clin.tabular contains the sample metadata. The first column contains unique sample identifiers. The other columns contain sample-associated clinical variables. NA values are allowed in the clinical variables. The format might look like so: ======== === === === , v1 v2 ... -------- --- --- --- sample1 a b ... -------- --- --- --- sample2 c d ... -------- --- --- --- sample3 e f ... -------- --- --- --- ... ... ... ... ======== === === === . **omics.tabular** The first column of the feature tables must be unique feature identifiers (e.g. gene names). The column names must be sample identifiers that should overlap with those in the clin.tabular. They don't have to be completely identical or in the same order. Samples from the clin.tabular that are not represented in the omics table will be dropped. The format might look like so: ===== ======= ======= ======= ======= , sample1 sample2 sample3 ... ----- ------- ------- ------- ------- gene1 0 1 2 ... ----- ------- ------- ------- ------- gene2 3 3 5 ... ----- ------- ------- ------- ------- gene3 2 3 4 ... ----- ------- ------- ------- ------- ... ... ... ... ... ===== ======= ======= ======= ======= . .. class:: infomark **Concordance between train/test splits:** The corresponding omics files in train/test splits must contain overlapping feature names (they don't have to be identical or in the same order). The clin.tabular files in train/test must contain matching clinical variables. ----- **Supervised Training** **Minimum requirements** * clin.tabular and omics.tabular files for training and testing * Selection of a tool/model * One target variable which can be numerical or categorical for regression/classification tasks. Flexynesis supports both single-task and multi-task training. We can provide one or more target variables and optionally survival variables as input and Flexynesis will build the appropriate model architecture. If the selected variable is numerical, a Multi-Layered-Perceptron (MLP) with MSE loss will be used. If a categorical variable is provided, an MLP with cross-entropy-loss will be utilized. If survival variables are provided, an MLP with Cox-Proportional-Hazards loss will be attached to the model. **Regression:** If your target variable is numerical, Flexynesis will build a regression model. **Classification:** If your target variable is categorical, Flexynesis will build a classification model. **Survival Analysis:** If your target variable is survival data, Flexynesis will build a survival analysis model. For survival analysis, two separate variables are required, where the first variable is a numeric event variable (consisting of 0's or 1's, where 1 means an event such as disease progression or death has occurred). The second variable is also a numeric time variable, which indicates how much time it took since last patient follow-up. .. class:: infomark **Note:** Flexynesis can be trained with multiple target variables, which can be a mixture of regression/classification/survival tasks. .. class:: infomark **Note:** For the supervised tasks, the user can easily switch between different model architectures. .. class:: infomark **Note:** If you choose **MultiTripletNetwork** model, the first target variable should be a categorical variable. .. class:: infomark **Note:** If you choose **GNN** model, the features should have the same naming convention between different omics modalities. .. class:: infomark **Note:** The **GNN** model only works with genes (for example CpG methylation sites does not work). The reason is that GNNs require a prior knowledge network, which is currently set to use STRING database. ----- **Unsupervised Training** In the absence of any target variables or survival variables, you can use a VAE architecture to carry out unsupervised training. ----- **Cross-modality Training** We have implemented a special case of VAEs where the input data layers and output data layers can be set to different data modalities. The purpose of a cross-modality encoder is to learn embeddings that can translate from one data modality to another. Crossmodality encoder we implemented supports both single/multiple input layers and also one or more target/survival variables can be added to the model. .. class:: infomark **Note:** if you use same input and output layers, it will be the same as unsupervised training. ----- .. class:: infomark **Modality fusion:** Flexynesis currently supports two main ways of fusing different omics data modalities: 1. Early fusion: The input data matrices are initially concatenated and pushed through the networks 2. Intermediate fusion: The input data matrices are initially pushed through the networks to obtain a modality-specific embedding space, which then gets concatenated to serve as input for the supervisor MLPs. .. _Documentation: https://bimsbstatic.mdc-berlin.de/akalin/buyar/flexynesis/site/ .. _copyright holders: https://github.com/BIMSBbioinfo/flexynesis ]]></help> <expand macro="creator"/> <expand macro="citations"/> </tool>