Mercurial > repos > galaxyp > fragpipe
changeset 8:da1531027506 draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/fragpipe commit 6413a461059c4a421a7812a08f244c224cde8ee2
| author | galaxyp |
|---|---|
| date | Fri, 17 Oct 2025 16:22:52 +0000 |
| parents | 3f947afe3f71 |
| children | |
| files | fragpipe_manifest_generator.xml generate_manifest.py test-data/manifest-generator/test1.manifest test-data/manifest-generator/test2.manifest |
| diffstat | 4 files changed, 272 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fragpipe_manifest_generator.xml Fri Oct 17 16:22:52 2025 +0000 @@ -0,0 +1,198 @@ +<tool id="fragpipe_manifest_generator" name="FragPipe Manifest Generator" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.2"> + <description> + Generate a FragPipe Manifest File (Experimental Design File) + </description> + + <macros> + <import>macros.xml</import> + <import>msfragger_macros.xml</import> + <token name="@SCAN_DATA_TYPE_REGEX@">(DDA|DDA+|DIA|GPF-DIA|DIA-Quant|DIA-Lib)</token> + <token name="@RUN_GENERATOR@"><![CDATA[ + python '$__tool_directory__/generate_manifest.py' + + #if $experiment_conditional_element.entry_type == 'consecutive' + --exp-consec + #elif $experiment_conditional_element.entry_type == 'assign_all' + --exp-assign-all '$experiment_conditional_element.experiment' + #elif $experiment_conditional_element.entry_type == 'column' + --exp-col '$experiment_conditional_element.experiment_values' + #end if + + #if $bioreplicate_conditional_element.entry_type == 'consecutive' + --bio-consec + #elif $bioreplicate_conditional_element.entry_type == 'assign_all' + --bio-assign-all '$bioreplicate_conditional_element.bioreplicate' + #elif $bioreplicate_conditional_element.entry_type == 'column' + --bio-col '$bioreplicate_conditional_element.bioreplicate_values' + #end if + + #if $scan_data_type_conditional_element.entry_type == 'assign_all' + --type-assign-all '$scan_data_type_conditional_element.scan_data_type' + #elif $scan_data_type_conditional_element.entry_type == 'column' + --type-col '$scan_data_type_conditional_element.scan_data_type_values' + #end if + + #for $sf in $inputs_element + #set $i_name = $ln_name($sf) + $i_name + #end for + ]]></token> + + <xml name="scan_parameters"> + <!-- Input Scan Files --> + <param name="inputs" type="data" format="mzml,mzxml,thermo.raw" multiple="true" label="Proteomics spectrum files" help="All input scan files must be named with one of the following extensions: .mzML, .mzXML, or .raw"/> + + <!-- Experiment input --> + <conditional name="experiment_conditional"> + <param name="entry_type" type="select" label="Assign experiments"> + <option value="none" selected="true">Leave blank</option> + <option value="consecutive">Assign consecutive integers</option> + <option value="column">Enter column values</option> + <option value="assign_all">Assign to all scan files</option> + </param> + <when value="none"/> + <when value="consecutive"/> + <when value="column"> + <param name="experiment_values" type="text" label="Comma-separated experiment numbers"> + <validator type="empty_field"/> + </param> + </when> + <when value="assign_all"> + <param name="experiment" type="text" label="Experiment"> + <validator type="empty_field"/> + </param> + </when> + </conditional> + + <!-- Bioreplicate input --> + <conditional name="bioreplicate_conditional"> + <param name="entry_type" type="select" label="Assign bioreplicates"> + <option value="none" selected="true">Leave blank</option> + <option value="consecutive">Assign consecutive integers</option> + <option value="column">Enter column values</option> + <option value="assign_all">Assign to all scan files</option> + </param> + <when value="none"/> + <when value="consecutive"/> + <when value="column"> + <param name="bioreplicate_values" type="text" label="Comma-separated bioreplicate numbers"> + <validator type="empty_field"/> + </param> + </when> + <when value="assign_all"> + <param name="bioreplicate" type="text" label="Bioreplicate"> + <validator type="empty_field"/> + </param> + </when> + </conditional> + + <!-- Data type input --> + <conditional name="scan_data_type_conditional"> + <param name="entry_type" type="select" label="Assign scan_data_types"> + <option value="column">Enter column values</option> + <option value="assign_all" selected="true">Assign to all scan files</option> + </param> + <when value="assign_all"> + <param name="scan_data_type" type="select" optional="false" label="Data Type"> + <option value="DDA" selected="true">DDA</option> + <option value="DDA+">DDA+</option> + <option value="DIA">DIA</option> + <option value="GPF-DIA">GPF-DIA</option> + <option value="DIA-Quant">DIA-Quant</option> + <option value="DIA-Lib">DIA-Lib</option> + </param> + </when> + <when value="column"> + <param name="scan_data_type_values" type="text" optional="false" label="Comma-separated Data Types"> + <validator type="regex">^@SCAN_DATA_TYPE_REGEX@(,@SCAN_DATA_TYPE_REGEX)*$</validator> + </param> + </when> + </conditional> + </xml> + </macros> + + <requirements> + <requirement type="package" version="3.11">python</requirement> + </requirements> + + <command><![CDATA[ + @CMD_IMPORTS@ + + #set $experiment_conditional_element = $experiment_conditional + #set $bioreplicate_conditional_element = $bioreplicate_conditional + #set $scan_data_type_conditional_element = $scan_data_type_conditional + #set $inputs_element = $inputs + + @RUN_GENERATOR@ + + #for $i, $g in enumerate($scan_groups) + #set $experiment_conditional_element = $g.experiment_conditional + #set $bioreplicate_conditional_element = $g.bioreplicate_conditional + #set $scan_data_type_conditional_element = $g.scan_data_type_conditional + #set $inputs_element = $g.inputs + + && @RUN_GENERATOR@ + #end for + ]]> + </command> + + <inputs> + <expand macro="scan_parameters"/> + <repeat name="scan_groups" title="Additional Scan Groups"> + <expand macro="scan_parameters"/> + </repeat> + </inputs> + + <outputs> + <data name="manifest_file" format="tabular" label="FragPipe Manifest File" from_work_dir="fp.manifest"/> + </outputs> + + <tests> + <!-- Test different entry types --> + <test expect_num_outputs="1"> + <param name="inputs" value="basic-search/test1.mzML,basic-search/test2.mzML" ftype="mzml"/> + <param name="experiment_conditional|entry_type" value="consecutive"/> + <param name="bioreplicate_conditional|entry_type" value="column"/> + <param name="bioreplicate_conditional|bioreplicate_values" value="3,4"/> + <param name="scan_data_type_conditional|entry_type" value="assign_all"/> + <param name="scan_data_type_conditional|scan_data_type" value="DIA"/> + <output name="manifest_file" ftype="tabular" file="manifest-generator/test1.manifest" compare="contains"/> + </test> + <!-- Test scan groups --> + <test expect_num_outputs="1"> + <param name="inputs" value="basic-search/test1.mzML" ftype="mzml"/> + <param name="experiment_conditional|entry_type" value="assign_all"/> + <param name="experiment_conditional|experiment" value="1"/> + <param name="bioreplicate_conditional|entry_type" value="assign_all"/> + <param name="bioreplicate_conditional|bioreplicate" value="1"/> + <param name="scan_data_type_conditional|entry_type" value="assign_all"/> + <param name="scan_data_type_conditional|scan_data_type" value="DIA"/> + <repeat name="scan_groups"> + <param name="inputs" value="basic-search/test2.mzML" ftype="mzml"/> + <param name="experiment_conditional|entry_type" value="assign_all"/> + <param name="experiment_conditional|experiment" value="2"/> + <param name="bioreplicate_conditional|entry_type" value="assign_all"/> + <param name="bioreplicate_conditional|bioreplicate" value="2"/> + <param name="scan_data_type_conditional|entry_type" value="assign_all"/> + <param name="scan_data_type_conditional|scan_data_type" value="GPF-DIA"/> + </repeat> + <output name="manifest_file" ftype="tabular" file="manifest-generator/test2.manifest" compare="contains"/> + </test> + </tests> + <help> +Generates a *manifest file* that may be used as input for the FragPipe Galaxy tool, or headless FragPipe_. +This file is analagous to an experimental design file. + +The tool takes as input a collection of scan files, or multiple collections using the *Insert Additional Scan Groups* parameter, and options for assigning experiment numbers, bioreplicates, +and data types for each file. + +Each scan group will have values from three columns applied to it using different methods. + +- Assign consecutive integers: The scans will be number consecutively starting with 1. +- Enter column values: The column values for each scan file are entered as a comma-delimited list in the same order as the files. +- Assign to all scan files: A value supplied by the user is applied to all files. + +.. _FragPipe: https://fragpipe.nesvilab.org/docs/tutorial_headless.html + </help> + <expand macro="citations" /> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/generate_manifest.py Fri Oct 17 16:22:52 2025 +0000 @@ -0,0 +1,70 @@ +#!/usr/bin/env python3 + +# +# Generates a FragPipe Manifest file. +# + +import argparse +import csv + +# The three columns for each scanfile are "Experiment, Bioreplicate, and Data type +column_types = ('exp', 'bio', 'type') +output_filename = 'fp.manifest' + + +# Add column values to a list of rows for each scan file. +def add_column(column_type, args, rows): + nfiles = len(args.scanfiles) + + # Each scan file is numbered 1 through n in column + if getattr(args, f'{column_type}_consec'): + vals = range(1, nfiles + 1) + + # All scan files have same value in column + elif getattr(args, f'{column_type}_assign_all'): + vals = [getattr(args, f'{column_type}_assign_all')] * nfiles + + # Values are provided for scan files in a comma-delimited list + elif getattr(args, f'{column_type}_col'): + vals = getattr(args, f'{column_type}_col').split(',') + if len(vals) != nfiles: + raise ValueError((f'Incorrect number of values entered for column {column_type}. ' + 'Exactly one value must be entered for each scan file.')) + + # Otherwise, this column remains empty. + else: + vals = [''] * nfiles + + for i, row in enumerate(rows): + row.append(vals[i]) + + +def main(): + parser = argparse.ArgumentParser() + + # Each column has the same methods for populating + for column_type in column_types: + parser.add_argument(f'--{column_type}-consec', action='store_true') + parser.add_argument(f'--{column_type}-assign-all') + parser.add_argument(f'--{column_type}-col') + + # Scanfile names, which should be identical to history identifiers + parser.add_argument('scanfiles', nargs='+') + + args = parser.parse_args() + + # Create and populate data structure for tabular output + rows = [[scanfile] for scanfile in args.scanfiles] + for column_type in column_types: + add_column(column_type, args, rows) + + # Write out manifest file. + # Use mode=a as the script will be called once for each scan group. + with open(output_filename, mode='a') as outf: + manifest_writer = csv.writer(outf, delimiter='\t') + for row in rows: + manifest_writer.writerow(row) + + +if __name__ == "__main__": + main()