Skip to content

update flexynesis cbio tool #1643

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bgruening merged 5 commits into from
Jun 26, 2025
Merged

update flexynesis cbio tool #1643

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f07cda4
add studies in a variable
nilchia Jun 25, 2025
fb5246e
fix 2nd test
nilchia Jun 25, 2025
3919ee0
test pass
nilchia Jun 25, 2025
1b928c6
add note about filter
nilchia Jun 25, 2025
69fad77
increase delta and eps
nilchia Jun 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 18 additions & 18 deletions tools/flexynesis/flexynesis.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1045,18 +1045,18 @@
<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="5"/>
<has_image_center_of_mass center_of_mass="962,732" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1941"/>
<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="5"/>
<has_image_center_of_mass center_of_mass="959.5,732.5" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1941"/>
<has_image_height height="1461" delta="10"/>
<has_image_width width="1941" delta="10"/>
</assert_contents>
</element>
</output_collection>
Expand All @@ -1076,10 +1076,10 @@
<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="5"/>
<has_image_center_of_mass center_of_mass="971,732" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1941"/>
<has_image_height height="1461" delta="10"/>
<has_image_width width="1941" delta="10"/>
</assert_contents>
</element>
</output_collection>
Expand All @@ -1102,10 +1102,10 @@
<output_collection name="plots" type="list">
<element name="job.final_model_cox_hazard_ratios">
<assert_contents>
<has_image_center_of_mass center_of_mass="972,737" eps="5"/>
<has_image_center_of_mass center_of_mass="972,737" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1941"/>
<has_image_height height="1461" delta="10"/>
<has_image_width width="1941" delta="10"/>
</assert_contents>
</element>
</output_collection>
Expand All @@ -1124,10 +1124,10 @@
<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="5"/>
<has_image_center_of_mass center_of_mass="969,735" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1940"/>
<has_image_height height="1461" delta="10"/>
<has_image_width width="1940" delta="10"/>
</assert_contents>
</element>
</output_collection>
Expand Down Expand Up @@ -1257,10 +1257,10 @@
<output_collection name="plots" type="list">
<element name="job.final_model_cox_hazard_ratios">
<assert_contents>
<has_image_center_of_mass center_of_mass="972,737" eps="5"/>
<has_image_center_of_mass center_of_mass="972,737" eps="20"/>
<has_image_channels channels="3"/>
<has_image_height height="1461"/>
<has_image_width width="1941"/>
<has_image_height height="1461" delta="10"/>
<has_image_width width="1941" delta="10"/>
</assert_contents>
</element>
</output_collection>
Expand Down
114 changes: 105 additions & 9 deletions tools/flexynesis/flexynesis_cbioportal_import.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,28 @@
</macros>
<expand macro="requirements"/>
<command detect_errors="exit_code"><![CDATA[
## list of studies with html report
#set $htm_studies = ['lgg_tcga', 'cesc_tcga']
#set $html_studies = ['acc_tcga_gdc', 'alal_target_gdc', 'aml_target_gdc', 'aml_tcga_gdc', 'blca_tcga_gdc',
'bll_target_gdc', 'brain_cptac_gdc', 'brca_tcga_gdc', 'breast_cptac_gdc', 'ccrcc_tcga_gdc',
'cesc_tcga_gdc', 'chol_tcga_gdc', 'chrcc_tcga_gdc', 'coad_cptac_gdc', 'coad_tcga_gdc',
'difg_tcga_gdc', 'dlbclnos_tcga_gdc', 'esca_tcga_gdc', 'gbm_tcga_gdc', 'hcc_tcga_gdc',
'hgsoc_tcga_gdc', 'hnsc_tcga_gdc', 'luad_cptac_gdc', 'luad_tcga_gdc', 'lusc_cptac_gdc',
'lusc_tcga_gdc', 'mnet_tcga_gdc', 'nbl_target_gdc', 'nsgct_tcga_gdc', 'ohnca_cptac_gdc',
'os_target_gdc', 'ovary_cptac_gdc', 'paad_tcga_gdc', 'pancreas_cptac_gdc', 'plmeso_tcga_gdc',
'prad_tcga_gdc', 'prcc_tcga_gdc', 'rcc_cptac_gdc', 'read_tcga_gdc', 'skcm_tcga_gdc',
'soft_tissue_tcga_gdc', 'stad_tcga_gdc', 'thpa_tcga_gdc', 'thym_tcga_gdc', 'ucec_tcga_gdc',
'ucs_tcga_gdc', 'uec_cptac_gdc', 'um_tcga_gdc', 'wt_target_gdc']
@CHECK_NON_COMMERCIAL_USE@
mkdir -p output/data output/meta &&
python '$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 &&
#if $study_id in $htm_studies:
mv $str($study_id)/*.htm output/cBioPortal_validation_report.html &&
#else if $study_id in $html_studies:
mv $str($study_id)/validation_reports/*validation.html output/cBioPortal_validation_report.html &&
#end if
cd output/data &&
for file in *; do if [[ -f \$file ]]; then mv "\$file" "\${file%.txt}.tabular"; fi; done
]]></command>
Expand All @@ -22,11 +37,6 @@ 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>
Expand All @@ -44,9 +54,18 @@ with open(output_path, 'w') as f:
<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 ${study_id}: cBioPortal validation report" from_work_dir="output/cBioPortal_validation_report.html"/>
<data name="report" format="html" label="${tool.name} on ${study_id}: cBioPortal validation report" from_work_dir="output/cBioPortal_validation_report.html">
<!-- note about the filter here:
Not all studies in the cbioportal datahub have html reports.
The main repository can be find here: https://github.com/cBioPortal/datahub/
Two studies in https://github.com/cBioPortal/datahub/tree/master/public have html reports (as .htm files),
and studies in crdc here: https://github.com/cBioPortal/datahub/tree/master/crdc have html reports
So from 479 studies only 51 have this report. -->
<filter>study_id in ['lgg_tcga', 'cesc_tcga', 'acc_tcga_gdc', 'alal_target_gdc', 'aml_target_gdc', 'aml_tcga_gdc', 'blca_tcga_gdc', 'bll_target_gdc', 'brain_cptac_gdc', 'brca_tcga_gdc', 'breast_cptac_gdc', 'ccrcc_tcga_gdc', 'cesc_tcga_gdc', 'chol_tcga_gdc', 'chrcc_tcga_gdc', 'coad_cptac_gdc', 'coad_tcga_gdc', 'difg_tcga_gdc', 'dlbclnos_tcga_gdc', 'esca_tcga_gdc', 'gbm_tcga_gdc', 'hcc_tcga_gdc', 'hgsoc_tcga_gdc', 'hnsc_tcga_gdc', 'luad_cptac_gdc', 'luad_tcga_gdc', 'lusc_cptac_gdc', 'lusc_tcga_gdc', 'mnet_tcga_gdc', 'nbl_target_gdc', 'nsgct_tcga_gdc', 'ohnca_cptac_gdc', 'os_target_gdc', 'ovary_cptac_gdc', 'paad_tcga_gdc', 'pancreas_cptac_gdc', 'plmeso_tcga_gdc', 'prad_tcga_gdc', 'prcc_tcga_gdc', 'rcc_cptac_gdc', 'read_tcga_gdc', 'skcm_tcga_gdc', 'soft_tissue_tcga_gdc', 'stad_tcga_gdc', 'thpa_tcga_gdc', 'thym_tcga_gdc', 'ucec_tcga_gdc', 'ucs_tcga_gdc', 'uec_cptac_gdc', 'um_tcga_gdc', 'wt_target_gdc']</filter>
Copy link
Copy Markdown
Owner

@bgruening bgruening Jun 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please add a large comment

</data>
</outputs>
<tests>
<!-- test 1: html report public-->
<test expect_num_outputs="3">
<param name="non_commercial_use" value="True"/>
<param name="study_id" value="lgg_tcga"/>
Expand Down Expand Up @@ -84,6 +103,77 @@ with open(output_path, 'w') as f:
</assert_contents>
</output>
</test>
<!-- test 2: html report crdc-->
<test expect_num_outputs="3">
<param name="non_commercial_use" value="True"/>
<param name="study_id" value="acc_tcga_gdc"/>
<output_collection name="data" type="list" count="14">
<element name="data_clinical_patient">
<assert_contents>
<has_text_matching expression="PATIENT_ID"/>
<has_n_lines n="97"/>
</assert_contents>
</element>
<element name="data_cna">
<assert_contents>
<has_text_matching expression="Entrez_Gene_Id"/>
<has_n_lines n="38322"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="meta" type="list" count="15">
<element name="meta_clinical_patient">
<assert_contents>
<has_text_matching expression="cancer_study_identifier: acc_tcga_gdc"/>
<has_n_lines n="4"/>
</assert_contents>
</element>
<element name="meta_cna">
<assert_contents>
<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>
<!-- test 3: no report -->
<test expect_num_outputs="2">
<param name="non_commercial_use" value="True"/>
<param name="study_id" value="acc_2019"/>
<output_collection name="data" type="list" count="8">
<element name="data_clinical_patient">
<assert_contents>
<has_text_matching expression="PATIENT_ID"/>
<has_n_lines n="1050"/>
</assert_contents>
</element>
<element name="data_cna">
<assert_contents>
<has_text_matching expression="Hugo_Symbol"/>
<has_n_lines n="21673"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="meta" type="list" count="9">
<element name="meta_clinical_patient">
<assert_contents>
<has_text_matching expression="cancer_study_identifier:acc_2019"/>
<has_n_lines n="4"/>
</assert_contents>
</element>
<element name="meta_cna">
<assert_contents>
<has_text_matching expression="data_filename: data_cna.txt"/>
<has_n_lines n="8"/>
</assert_contents>
</element>
</output_collection>
</test>
</tests>
<help><![CDATA[
@COMMON_HELP@
Expand All @@ -98,10 +188,16 @@ This tool fetches data from cBioPortal using the Flexynesis `CBioPortalData`.

**Outputs**

Two collections of data and metadata datasets and an additional html report.
Two collections of data and metadata datasets and an additional html report (if available).


The available datasets can be checked from here_

If the study ID is not available, please contact the administrator of this Galaxy instance.

.. _Documentation: https://bimsbstatic.mdc-berlin.de/akalin/buyar/flexynesis/site/
.. _copyright holders: https://github.com/BIMSBbioinfo/flexynesis
.. _here: https://github.com/cBioPortal/datahub/
]]></help>
<expand macro="creator">
<person givenName="Polina" familyName="Polunina" email="polunina@informatik.uni-freiburg.de"/>
Expand Down
2 changes: 1 addition & 1 deletion tools/flexynesis/macros.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<macros>
<token name="@TOOL_VERSION@">0.2.20</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@VERSION_SUFFIX@">1</token>
<token name="@PROFILE@">24.1</token>
<xml name="requirements">
<requirements>
Expand Down
2 changes: 2 additions & 0 deletions tools/flexynesis/test-data/loc.sample
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1,3 @@
lgg_tcga lgg_tcga 1
acc_tcga_gdc acc_tcga_gdc 1
acc_2019 acc_2019 1
Loading