Merge pull request #332 from jonasscheid/add-idmassaccuracy

Add idmassaccuracy module and QC plot

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - Added `PYOPENMS_CHROMATOGRAMEXTRACTOR` extracting MS1 Chromatograms and visualize them in multiQC report [#329](https://github.com/nf-core/mhcquant/pull/329)
+- Added `OPENMS_IDMASSACCURACY` and `DATAMASH_HISTOGRAM` to compute fragment mass errors and visualizte them in multiQC report [#332](https://github.com/nf-core/mhcquant/pull/332)
 
 ## v2.6.0 - nfcore/mhcquant "Mr Bob" - 2024/06/17
 

assets/multiqc_config.yml

@@ -34,22 +34,43 @@ custom_data:
       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
 
+  # Mass error plot
+  mass_error:
+    plot_type: "linegraph"
+    file_format: "tsv"
+    section_name: "Fragment mass error"
+    description: |
+      The fragment mass error describes the differences between observed and theoretical fragment ion masses.
+      It helps assessing the accuracy and calibration of the mass spectrometer by visualizing the error range
+      and potential deviations. Depending on your configurations this error is plotted in Dalton (Da)
+      or parts-per-million (ppm).
+    pconfig:
+      xlab: "Mass deviation [Da/ppm]"
+      ylab: "Frequency"
+#id: custom_box
+#plot_type: 'box'
+#section_name: 'Custom box plot'
+#description: "Box plot for a sample"
+#pconfig:
+#    title: 'Box plot'
+
 sp:
   chromatogram:
     fn: "*_chrom.csv"
-## Define the order of sections
+  mass_error:
+    fn: "*_binned.tsv"
+### Define the order of sections
 #module_order:
 #  - custom_content
 #
 ## Set the order of custom code plots and tables
 #custom_content:
 #  order:
 #    - chromatogram
+#    - mass_error

conf/modules.config

@@ -241,6 +241,24 @@ process {
         ]
     }
 
+    withName: 'OPENMS_IDMASSACCURACY' {
+        ext.prefix  = {"${meta.spectra}"}
+        ext.args    = [
+            (params.precursor_error_units == 'ppm') ? "-precursor_error_ppm": "",
+            "-fragment_mass_tolerance ${params.fragment_mass_tolerance}"
+        ].join(' ').trim()
+        publishDir  = [
+            enabled: false
+        ]
+    }
+
+    withName: 'DATAMASH_HISTOGRAM' {
+        ext.prefix  = {"${meta.spectra}"}
+        publishDir  = [
+            enabled: false
+        ]
+    }
+
     withName: 'MS2RESCORE' {
         ext.args   = [
             "--ms2_tolerance ${2 * params.fragment_mass_tolerance}",

modules.json

@@ -12,7 +12,7 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "06c8865e36741e05ad32ef70ab3fac127486af48",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
                     "openms/decoydatabase": {
@@ -25,6 +25,11 @@
                         "git_sha": "bbcad23c681ff85336aef1c41345bc313d921b5d",
                         "installed_by": ["modules"]
                     },
+                    "openms/idmassaccuracy": {
+                        "branch": "master",
+                        "git_sha": "f768b283dbd8fc79d0d92b0f68665d7bed94cabc",
+                        "installed_by": ["modules"]
+                    },
                     "openms/idmerger": {
                         "branch": "master",
                         "git_sha": "bbcad23c681ff85336aef1c41345bc313d921b5d",

modules/local/datamash_histogram.nf

@@ -0,0 +1,52 @@
+process DATAMASH_HISTOGRAM {
+    tag "$meta.id"
+    label 'process_single'
+
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/datamash:1.1.0--0' :
+        'biocontainers/datamash:1.1.0--0' }"
+
+    input:
+    tuple val(meta), path(tsv)
+
+    output:
+    tuple val(meta), path("*.tsv"), emit: binned_tsv
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    datamash \\
+        bin:0.0002 1 \\
+        $args \\
+        < $tsv \\
+    | \\
+    datamash \\
+        --sort \\
+        --group 1 \\
+        count 1 \\
+        > ${prefix}_binned.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        datamash: \$(datamash --version | grep 'datamash' | cut -d ' ' -f4)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_binned.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        datamash: \$(datamash --version | grep 'datamash' | cut -d ' ' -f4)
+    END_VERSIONS
+    """
+}