Flexynesis plot

tools/flexynesis/.shed.yml

@@ -4,7 +4,7 @@ description: This is a deep-learning based multi-omics bulk sequencing data inte
 homepage_url: https://github.com/BIMSBbioinfo/flexynesis/tree/main
 long_description: The package includes multiple types of deep learning architectures such as simple fully connected networks, supervised variational autoencoders, graph convolutional networks, multi-triplet networks different options of data layer fusion, and automates feature selection and hyperparameter optimisation.
 remote_repository_url: https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis
-categories: 
+categories:
 - Machine Learning
 - Statistics
 - Systems Biology

tools/flexynesis/flexynesis_cbioportal_import.xml

@@ -6,116 +6,105 @@
     <expand macro="requirements"/>
     <command detect_errors="exit_code"><![CDATA[
         @CHECK_NON_COMMERCIAL_USE@
-        python '$__tool_directory__/fetch_cbioportal_data.py'
-            --study_id '$study_id'
-            --data_types '$data_types'
-            #if $mapped_files:
-                --mapped_files '$mapped_files'
-            #end if
-            --split_ratio '$split_ratio'
-            --output_dir 'output'
+        mkdir -p output/data output/meta &&
+        python '$cbio_config' &&
+        cat cbioportal_data.txt &&
+        mv $str($study_id)/data* output/data/ &&
+        mv $str($study_id)/meta* output/meta/ &&
+        mv $str($study_id)/*.htm output/cBioPortal_validation_report.html &&
+        cd output/data &&
+        for file in *; do if [[ -f \$file ]]; then mv "\$file" "\${file%.txt}.tabular"; fi; done
     ]]></command>
+    <configfiles>
+        <configfile name="cbio_config"><![CDATA[
+from flexynesis.utils import CBioPortalData
+from contextlib import redirect_stdout
+
+cbioportal = CBioPortalData(study_id='$study_id')
+cbioportal.get_cbioportal_data(study_id='$study_id')
+
+output_path = f"cbioportal_data.txt"
+with open(output_path, 'w') as f:
+    with redirect_stdout(f):
+        cbioportal.get_cbioportal_data('lgg_tcga')
+        ]]></configfile>
+    </configfiles>
     <inputs>
-        <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
-            <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
-        </param>
-        <param name="study_id" type="text" label="cBioPortal study ID" help="The ID of the study to fetch from cBioPortal (e.g., 'brca_tcga')." />
-        <param name="data_types" type="select" multiple="true" label="Data types to fetch" help="Select the types of data to retrieve from cBioPortal.">
-            <option value="clin" selected="true">Clinical data (default: data_clinical_patient.txt)</option>
-            <option value="mut">Mutations (default: data_mutations.txt)</option>
-            <option value="omics">Omics data (default: data_cna.txt)</option>
-            <option value="other">Other custom data</option>
+        <expand macro="commercial_use_param"/>
+        <param name="study_id" label="cBioPortal study ID" type="select" help="contact the administrator of this Galaxy instance if you miss a study ID">
+            <options from_data_table="cbioportal">
+                <filter type="static_value" value="1" column="2"/>
+            </options>
         </param>
-        <param name="mapped_files" type="text" optional="true" label="Mapped files" help="Comma-separated list of .txt files to map to the selected data types (e.g., 'data_clinical_sample.txt,data_mutations.txt,data_castom.txt'). Must match the number and order of data types." />
-        <param name="split_ratio" type="float" value="0.7" min="0.0" max="1.0" label="Training/Test split ratio" help="Proportion of data to use for training (e.g., 0.7 means 70% train, 30% test)." />
     </inputs>
     <outputs>
-        <collection name="datasets" type="list" label="${tool.name} on ${study_id}: datasets">
-            <discover_datasets pattern="(?P&lt;name&gt;.+_(train|test))\.csv$" format="csv" directory="output" />
+        <collection name="data" type="list" label="${tool.name} on ${study_id}: datasets">
+            <discover_datasets pattern="__name_and_ext__" format="tabular" directory="output/data"/>
         </collection>
+        <collection name="meta" type="list" label="${tool.name} on ${study_id}: metadata">
+            <discover_datasets pattern="__name_and_ext__" format="tabular" directory="output/meta"/>
+        </collection>
+        <data name="report" format="html" label="${tool.name} on ${study_id}: cBioPortal validation report" from_work_dir="output/cBioPortal_validation_report.html"/>
     </outputs>
     <tests>
-        <test expect_num_outputs="1">
+        <test expect_num_outputs="3">
             <param name="non_commercial_use" value="True"/>
-            <param name="study_id" value="lgg_tcga" />
-            <param name="data_types" value="clin,mut" />
-            <param name="split_ratio" value="0.7" />
-            <output_collection name="datasets" type="list">
-                <element name="clin_test">
+            <param name="study_id" value="lgg_tcga"/>
+            <output_collection name="data" type="list" count="17">
+                <element name="data_clinical_patient">
                     <assert_contents>
                         <has_text_matching expression="PATIENT_ID"/>
+                        <has_n_lines n="520"/>
                     </assert_contents>
                 </element>
-                <element name="clin_train">
-                    <assert_contents>
-                        <has_text_matching expression="PATIENT_ID"/>
-                    </assert_contents>
-                </element>
-                <element name="mut_test">
-                    <assert_contents>
-                        <has_text_matching expression="Hugo_Symbol"/>
-                    </assert_contents>
-                </element>
-                <element name="mut_train">
+                <element name="data_cna">
                     <assert_contents>
                         <has_text_matching expression="Hugo_Symbol"/>
+                        <has_n_lines n="24777"/>
                     </assert_contents>
                 </element>
             </output_collection>
-        </test>
-        <test expect_num_outputs="1">
-            <param name="non_commercial_use" value="True"/>
-            <param name="study_id" value="lgg_tcga" />
-            <param name="data_types" value="clin,mut,other" />
-            <param name="mapped_files" value="data_clinical_patient.txt,data_mutations.txt,data_cna.txt" />
-            <param name="split_ratio" value="0.8" />
-            <output_collection name="datasets" type="list">
-                <element name="clin_train">
+            <output_collection name="meta" type="list" count="18">
+                <element name="meta_clinical_patient">
                     <assert_contents>
-                        <has_text_matching expression="PATIENT_ID"/>
+                        <has_text_matching expression="cancer_study_identifier: lgg_tcga"/>
+                        <has_n_lines n="4"/>
                     </assert_contents>
                 </element>
-                <element name="mut_train">
+                <element name="meta_cna">
                     <assert_contents>
-                        <has_text_matching expression="Hugo_Symbol"/>
-                    </assert_contents>
-                </element>
-                <element name="other_test">
-                    <assert_contents>
-                        <has_text_matching expression="Hugo_Symbol"/>
+                        <has_text_matching expression="data_filename: data_cna.txt"/>
+                        <has_n_lines n="8"/>
                     </assert_contents>
                 </element>
             </output_collection>
+            <output name="report">
+                <assert_contents>
+                    <has_text_matching expression="cBioPortal validation report"/>
+                </assert_contents>
+            </output>
         </test>
-    </tests><help><![CDATA[
+    </tests>
+    <help><![CDATA[
+@COMMON_HELP@
+
 **Flexynesis cBioPortal import**
 
-This tool fetches data from cBioPortal using the Flexynesis `CBioPortalData` class and prepares it for use with the Flexynesis Galaxy tool. It downloads a specified study, extracts the requested data types, splits them into training and test sets, and outputs them as CSV files compatible with Flexynesis (e.g., `clin_train.csv`, `mut_test.csv`).
+This tool fetches data from cBioPortal using the Flexynesis `CBioPortalData`.
 
 **Inputs**
 
 - **cBioPortal study ID**: The identifier of the study to fetch (e.g., `brca_tcga`, `lgg_tcga`). Find study IDs on the cBioPortal.
-- **Data types to fetch**: Select one or more data types to retrieve. 'Clinical data' (`clin`) is required for splitting. Options:
-    - `clin`: Clinical data (default: `data_clinical_patient.txt`)
-    - `mut`: Mutation data (default: `data_mutations.txt`)
-    - `omics`: Omics data (default: `data_cna.txt`)
-    - `other`: Custom data type (requires `--mapped_files`)
-- **Mapped files (optional)**: A comma-separated list of `.txt` files to override default filenames. Must match the number and order of selected data types (e.g., `data_clinical_sample.txt,data_mutations.txt,data_custom.txt`).
-- **Training/Test split ratio**: The proportion of data for training (e.g., 0.7 means 70% train, 30% test).
 
 **Outputs**
 
-A collection of datasets including:
-    - `clin_train.csv` and `clin_test.csv`: Training and test clinical data (always included).
-    - `mut_train.csv` and `mut_test.csv`: Training and test mutation data (if selected).
-    - `omics_train.csv` and `omics_test.csv`: Training and test omics/CNA data (if selected).
-    - `other_train.csv` and `other_test.csv`: Training and test custom data (if `other` is selected with a mapped file).
-
-These datasets can be used as inputs to the Flexynesis Galaxy tool for multi-omics analysis.
+Two collections of data and metadata datasets and an additional html report.
 
-**Note**: Ensure the study ID is valid and the selected data types (or mapped files) are available in the study archive. Clinical data (`clin`) is mandatory for splitting.
+.. _Documentation: https://bimsbstatic.mdc-berlin.de/akalin/buyar/flexynesis/site/
+.. _copyright holders: https://github.com/BIMSBbioinfo/flexynesis
 ]]></help>
-    <citations>
-        <citation type="doi">10.1101/2024.07.16.603606</citation>
-    </citations>
+    <expand macro="creator">
+        <person givenName="Polina" familyName="Polunina" email="polunina@informatik.uni-freiburg.de"/>
+    </expand>
+    <expand macro="citations"/>
 </tool>