Merge pull request #329 from jonasscheid/add-chromatogram-extractor

CHANGELOG.md

@@ -3,6 +3,12 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v2.6.1dev
+
+### `Added`
+
+- Added `PYOPENMS_CHROMATOGRAMEXTRACTOR` extracting MS1 Chromatograms and visualize them in multiQC report [#329](https://github.com/nf-core/mhcquant/pull/329)
+
 ## v2.6.0 - nfcore/mhcquant "Mr Bob" - 2024/06/17
 
 ### `Added`

assets/multiqc_config.yml

@@ -3,9 +3,9 @@ custom_logo_url: https://github.com/nf-core/mhcquant
 custom_logo_title: "nf-core/mhcquant"
 
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mhcquant/releases/tag/2.6.0" target="_blank">nf-core/mhcquant</a>
+  This report has been generated by the <a href="https://github.com/nf-core/mhcquant/tree/dev" target="_blank">nf-core/mhcquant</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/mhcquant/2.6.0/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/mhcquant/dev/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mhcquant-methods-description":
     order: -1000
@@ -15,5 +15,41 @@ report_section_order:
     order: -1002
 
 export_plots: true
-
 disable_version_detection: true
+
+# Modules to run
+run_modules:
+  - custom_content
+
+# Custom tables and plots
+custom_data:
+  # Summary of chromatogram plot
+  chromatogram:
+    plot_type: "linegraph"
+    file_format: "csv"
+    section_name: "MS1 Chromatogram"
+    description: |
+      An MS1 chromatogram is a plot of the intensity of precursor ions (MS1) detected over time,
+      typically with retention time (RT) on the x-axis and ion intensity on the y-axis.
+      It represents the total ion current (TIC) from the MS1 scan,
+      which is useful for monitoring the overall elution profile of compounds during a chromatographic separation.
+    pconfig:
+      id: "chromatogram"
+      title: "MS1 Chromatograms"
+      xlab: "Retention time [min]"
+      xmin: 0
+      ylab: "Intensity"
+      logswitch: true
+      logswitch_active: true
+
+sp:
+  chromatogram:
+    fn: "*_chrom.csv"
+## Define the order of sections
+#module_order:
+#  - custom_content
+#
+## Set the order of custom code plots and tables
+#custom_content:
+#  order:
+#    - chromatogram

bin/chromatogram_extractor.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python
+# Written by Jonas Scheid under the MIT license
+
+import logging
+import csv
+import argparse
+import matplotlib.pyplot as plt
+
+import pandas as pd
+import pyopenms as oms
+
+# Setup logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+
+
+def parse_arguments():
+    parser = argparse.ArgumentParser(description='Exctract TICs of MS1 Spectra')
+    parser.add_argument('-in','--input', type=str, help='Path to the spectrum file')
+    parser.add_argument('-out', '--output', type=str, help='Path to the output CSV file containing RT and TIC of Precursors')
+    return parser.parse_args()
+
+def main():
+    args = parse_arguments()
+    input_file = args.input
+    output_file = args.output
+
+    # Load the mzML file
+    logging.info(f'Loading file: {input_file}')
+    exp = oms.MSExperiment()
+    mzml_file = oms.MzMLFile()
+    mzml_file.load(input_file, exp)
+
+    # Get RT and Spectrum TIC of MS1 Spectra
+    chromatogram = [(spectrum.getRT() / 60 , spectrum.calculateTIC()) for spectrum in exp.getSpectra() if spectrum.getMSLevel() == 1]
+    logging.info(f'Found {len(chromatogram)} MS1 Spectra')
+    logging.info(f'RT range: {round(chromatogram[0][0],2)} - {round(chromatogram[-1][0],2)} [min]')
+    # Create pandas df
+    chromatogram_df = pd.DataFrame(chromatogram, columns=['RT', 'TIC'])
+    # bin data into minutes and take the mean of the TIC
+    chromatogram_df = chromatogram_df.groupby('RT').mean().reset_index()
+    # Add RT=0 and Intensity=0 to start and end of chromatogram_df
+    start = pd.DataFrame([{'RT': 0, 'TIC': 0}])
+    end = pd.DataFrame([{'RT': chromatogram_df['RT'].max(), 'TIC': 0}])
+    # Concatenate the DataFrames
+    chromatogram_df = pd.concat([start, chromatogram_df, end], ignore_index=True)
+
+    # Write to csv
+    chromatogram_df.to_csv(output_file, index=False, header=False)
+
+if __name__ == '__main__':
+    main()

conf/modules.config

@@ -186,6 +186,12 @@ process {
         ]
     }
 
+    withName: 'PYOPENMS_CHROMATOGRAMEXTRACTOR' {
+        publishDir  = [
+            enabled: false
+        ]
+    }
+
     withName: 'OPENMS_MAPALIGNERIDENTIFICATION' {
         ext.args    = [
             "-model:type linear",

modules.json

@@ -12,7 +12,7 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
+                        "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
                         "installed_by": ["modules"]
                     },
                     "openms/decoydatabase": {

modules/local/pyopenms_chromatogramextractor.nf

@@ -0,0 +1,47 @@
+process PYOPENMS_CHROMATOGRAMEXTRACTOR {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::pyopenms=3.1.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/pyopenms:3.1.0--py311h9b8898c_0' :
+        'biocontainers/pyopenms:3.1.0--py311h9b8898c_0' }"
+
+    input:
+        tuple val(meta), path(mzml)
+
+    output:
+        tuple val(meta), path("*.csv")  , emit: csv
+        path "versions.yml"             , emit: versions
+
+    when:
+        task.ext.when == null || task.ext.when
+
+    script:
+        def prefix           = task.ext.prefix ?: "${mzml.baseName}"
+        def args             = task.ext.args  ?: ''
+
+        """
+        chromatogram_extractor.py \\
+            -in $mzml \\
+            -out ${prefix}_chrom.csv \\
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            pyOpenMS: \$(pip show pyopenms | grep Version | cut -d ' ' -f 2)
+        END_VERSIONS
+        """
+
+    stub:
+        def args = task.ext.args ?: ''
+        def prefix = task.ext.prefix ?: "${mzml.baseName}"
+
+        """
+        touch ${prefix}_chrom.csv
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            pyOpenMS: \$(pip show pyopenms | grep Version | cut -d ' ' -f 2)
+        END_VERSIONS
+        """
+}

nextflow.config

@@ -292,7 +292,7 @@ manifest {
     description     = """Identify and quantify peptides from mass spectrometry raw data"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '2.6.0'
+    version         = '2.6.1dev'
     doi             = '10.1021/acs.jproteome.9b00313'
 }