Major refactoring in the Isobaric workflow enabling to work similar to proteomicsLFQ #692
+153
−26
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| process ISOBARIC_WORKFLOW { | ||
| tag "${expdes.baseName}" | ||
| label 'process_high' | ||
| label 'openms' | ||
|
|
||
| container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? | ||
| 'oras://ghcr.io/bigbio/openms-tools-thirdparty-sif:2025.04.14' : | ||
| 'ghcr.io/bigbio/openms-tools-thirdparty:2025.04.14' }" | ||
|
|
||
| input: | ||
| val(labelling_type) | ||
| path(mzmls) | ||
| path(id_files) | ||
| path(expdes) | ||
|
|
||
| output: | ||
| path "${expdes.baseName}_openms.mzTab", emit: out_mztab | ||
| path "${expdes.baseName}_openms.consensusXML", emit: out_consensusXML | ||
| path "*.log", emit: log | ||
| path "versions.yml", emit: versions | ||
|
|
||
| script: | ||
| def args = task.ext.args ?: '' | ||
| def extractBaseName = { filename -> | ||
| def name = filename.toString() | ||
| name = name.replaceAll(/\.mzML$/, '') | ||
|
|
||
| if (name.endsWith('.idXML')) { | ||
| name = name.replaceAll(/\.idXML$/, '') | ||
| name = name.replaceAll(/_(comet|msgf|sage|consensus)(_perc)?(_filter)?(_fdr)?$/, '') | ||
| } | ||
| return name | ||
| } | ||
|
|
||
| def mzml_sorted = mzmls.collect().sort{ a, b -> | ||
| extractBaseName(a.name) <=> extractBaseName(b.name) | ||
| } | ||
| def id_sorted = id_files.collect().sort{ a, b -> | ||
| extractBaseName(a.name) <=> extractBaseName(b.name) | ||
| } | ||
|
|
||
| // Build isotope correction matrix argument if enabled | ||
| def isotope_correction = "" | ||
| if (params.isotope_correction && params.plex_corr_matrix_file != null) { | ||
| def matrix_lines = new File(params.plex_corr_matrix_file).readLines() | ||
| .findAll { !it.startsWith('#') && it.trim() } | ||
| .drop(1) | ||
| .collect { line -> | ||
| def values = line.split('/') | ||
| if (labelling_type == 'tmt18plex' || labelling_type == 'tmt16plex') { | ||
| return "\"${values[1]}/${values[2]}/${values[3]}/${values[4]}/${values[5]}/${values[6]}/${values[7]}/${values[8]}\"" | ||
| } else { | ||
| return "\"${values[1]}/${values[2]}/${values[3]}/${values[4]}\"" | ||
| } | ||
| } | ||
| def correction_matrix = matrix_lines.join(" ") | ||
| isotope_correction = "-quantification:isotope_correction true -${labelling_type}:correction_matrix ${correction_matrix}" | ||
| } | ||
|
|
||
| """ | ||
| IsobaricWorkflow \\ | ||
| -threads ${task.cpus} \\ | ||
| -in ${mzml_sorted.join(' ')} \\ | ||
| -in_id ${id_sorted.join(' ')} \\ | ||
| -exp_design ${expdes} \\ | ||
| -type ${labelling_type} \\ | ||
| -inference_method ${params.protein_inference_method} \\ | ||
| -protein_quantification ${params.protein_quant} \\ | ||
| -psmFDR ${params.psm_level_fdr_cutoff} \\ | ||
| -proteinFDR ${params.protein_level_fdr_cutoff} \\ | ||
| -picked_fdr ${params.picked_fdr} \\ | ||
| -picked_decoy_string ${params.decoy_string} \\ | ||
|
Comment on lines
+71
to
+72
Contributor
There was a problem hiding this comment. Propagate the decoy-position setting in this new path. The pipeline already exposes 🤖 Prompt for AI Agents |
||
| -extraction:min_precursor_purity ${params.min_precursor_purity} \\ | ||
| -extraction:precursor_isotope_deviation ${params.precursor_isotope_deviation} \\ | ||
| -extraction:min_reporter_intensity ${params.min_reporter_intensity} \\ | ||
| ${isotope_correction} \\ | ||
| -out ${expdes.baseName}_openms.consensusXML \\ | ||
| -out_mzTab ${expdes.baseName}_openms.mzTab \\ | ||
| $args \\ | ||
| 2>&1 | tee isobaricworkflow.log | ||
|
|
||
| cat <<-END_VERSIONS > versions.yml | ||
| "${task.process}": | ||
| IsobaricWorkflow: \$(IsobaricWorkflow 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1) | ||
| END_VERSIONS | ||
| """ | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| name: isobaric_workflow | ||
| description: Extracts and normalizes isobaric labeling information from an LC-MS/MS experiment. | ||
| keywords: | ||
| - OpenMS | ||
| - quantification | ||
| tools: | ||
| - IsobaricWorkflow: | ||
| description: | | ||
| Extracts and normalizes isobaric labeling information from an LC-MS/MS experiment. | ||
| homepage: https://abibuilder.cs.uni-tuebingen.de/archive/openms/Documentation/release/latest/html/TOPP_IsobaricWorkflow.html | ||
| documentation: https://abibuilder.cs.uni-tuebingen.de/archive/openms/Documentation/release/latest/html/TOPP_IsobaricWorkflow.html | ||
| - mzmls: | ||
| type: file | ||
| description: Input Spectra in mzML format | ||
| pattern: "*.mzML" | ||
| - id_files: | ||
| type: file | ||
| description: Identifications in idXML or mzIdentML format with posterior error probabilities as score type. | ||
| pattern: "*.idXML" | ||
| - expdes: | ||
| type: file | ||
| description: An experimental design file | ||
| pattern: "*.tsv" | ||
| output: | ||
| - out_mztab: | ||
| type: file | ||
| description: mzTab file with analysis results | ||
| pattern: "*.mzTab" | ||
| - out_consensusXML: | ||
| type: file | ||
| description: ConsensusXML file for visualization and further processing in OpenMS. | ||
| pattern: "*.consensusXML" | ||
| - log: | ||
| type: file | ||
| description: log file | ||
| pattern: "*.log" | ||
| - version: | ||
| type: file | ||
| description: File containing software version | ||
| pattern: "versions.yml" | ||
| authors: | ||
| - "@MaLLLiYA" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fail fast if the mzML/idXML pairing drifts.
Upstream these files are already matched by sample, but this process rebuilds that pairing by sorting both lists independently and then passing them positionally to
-in/-in_id. If a filename falls outside the current normalization regex, the command still runs but can quantitate against the wrong ID file.🛠️ Suggested guard
def mzml_sorted = mzmls.collect().sort{ a, b -> extractBaseName(a.name) <=> extractBaseName(b.name) } def id_sorted = id_files.collect().sort{ a, b -> extractBaseName(a.name) <=> extractBaseName(b.name) } + def mzml_names = mzml_sorted.collect { extractBaseName(it.name) } + def id_names = id_sorted.collect { extractBaseName(it.name) } + if (mzml_names != id_names) { + throw new IllegalArgumentException("Mismatched IsobaricWorkflow inputs: mzML=${mzml_names} idXML=${id_names}") + }🤖 Prompt for AI Agents