Merge pull request #24 from ajmaurais/mz_shift

Add m/z shift option

docs/source/workflow_parameters.rst

@@ -101,6 +101,9 @@ The ``params`` Section
    * -
      - ``msconvert.do_simasspectra``
      - If starting with raw files, this is the value used by ``msconvert`` for the ``do_simasspectra`` parameter. Default: ``true``.
+   * -
+     - ``msconvert.mz_shift_ppm``
+     - If starting with raw files, ``msconvert`` will shift all mz values by ``n`` ppm when converting to ``mzML``. If ``null`` the mz values are not shifed. Default: ``null``.
    * -
      - ``encyclopedia.chromatogram.params``
      - If you are generating a chromatogram library for quantification, this is the command line options passed to EncyclopeDIA during the chromatogram generation step. Default: ``'-enableAdvancedOptions -v2scoring'`` If you do not wish to pass any options to EncyclopeDIA, this must be set to ``''``.

modules/msconvert.nf

@@ -1,5 +1,30 @@
+
+/**
+ * Generate the msconvert command based off user defined parameters.
+ */
+def msconvert_command() {
+    return """
+    wine msconvert -v --zlib --mzML --64 \
+        --ignoreUnknownInstrumentError --filter "peakPicking true 1-" \
+        ${params.msconvert.do_demultiplex ? '--filter "demultiplex optimization=overlap_only"' : ''} \
+        ${params.msconvert.do_simasspectra ? '--simAsSpectra' : ''} \
+        ${params.msconvert.mz_shift_ppm == null ? '' : '--filter "mzShift ' + "${params.msconvert.mz_shift_ppm}" + 'ppm msLevels=1-"'} \
+    """
+}
+
+/**
+ * Calculate a unique hash for msconvert configuration.
+ *
+ * The hash combines the text of the msconvert command without the raw file and
+ * the proteowizard container.
+ */
+def msconvert_cache_dir() {
+    def str = params.images.proteowizard + msconvert_command()
+    return str.md5()
+}
+
 process MSCONVERT {
-    storeDir "${params.mzml_cache_directory}/${workflow.commitId}/${params.msconvert.do_demultiplex}/${params.msconvert.do_simasspectra}"
+    storeDir "${params.mzml_cache_directory}/${msconvert_cache_dir()}"
     publishDir params.output_directories.msconvert, pattern: "*.mzML", failOnError: true, mode: 'copy', enabled: params.msconvert_only && !params.panorama.upload
     label 'process_medium'
     label 'process_high_memory'
@@ -8,26 +33,14 @@ process MSCONVERT {
 
     input:
         path raw_file
-        val do_demultiplex
-        val do_simasspectra
 
     output:
         path("${raw_file.baseName}.mzML"), emit: mzml_file
 
     script:
 
-    demultiplex_param = do_demultiplex ? '--filter "demultiplex optimization=overlap_only"' : ''
-    simasspectra = do_simasspectra ? '--simAsSpectra' : ''
-
     """
-    wine msconvert \
-        ${raw_file} \
-        -v \
-        --zlib \
-        --mzML \
-        --ignoreUnknownInstrumentError \
-        --filter "peakPicking true 1-" \
-        --64 ${simasspectra} ${demultiplex_param}
+    ${msconvert_command()} ${raw_file}
     """
 
     stub:

modules/skyline.nf

@@ -304,7 +304,7 @@ process SKYLINE_RUN_REPORTS {
 
     for skyrfile in ./*.skyr; do
         # Add report to document
-        echo "--report-add=\\"${skyrfile}\\"" >> export_reports.bat
+        echo "--report-add=\\"${skyrfile}\\" --report-conflict-resolution=overwrite" >> export_reports.bat
 
         # Export report
         awk -F'"' '/<view name=/ { print $2 }' "$skyrfile" | while read reportname; do

nextflow.config

@@ -57,8 +57,10 @@ params {
     email = null                    // email to notify of workflow outcome, leave null to send no email
     skyline.template_file = null    // the skyline template, if null use default_skyline_template_file
     panorama_upload = false;        // whether or not to upload the results to PanoramaWeb
+
     msconvert.do_demultiplex = true;          // whether or not to demultiplex with msconvert
     msconvert.do_simasspectra = true;         // whether or not to do simAsSpectra with msconvert
+    msconvert.mz_shift_ppm = null             // shift all mz values by n ppn.
 
     // If set to true, only run msconvert and stop. Resulting mzML files will be saved to the
     // "msconvert" subdirectory of the results directory.

resources/pipeline.config

@@ -45,6 +45,7 @@ params {
 	// options for msconvert
     msconvert.do_demultiplex = true;          // whether or not to demultiplex with msconvert
     msconvert.do_simasspectra = true;         // whether or not to do simAsSpectra with msconvert
+    msconvert.mz_shift_ppm = null             // shift all mz values by n ppn.
 
     // default parameters for Encyclopedia searches, can be overridden
     encyclopedia.chromatogram.params    = '-enableAdvancedOptions -v2scoring'
@@ -114,4 +115,4 @@ mail {
     smtp.starttls.enable = true
     smtp.starttls.required = false
     mail.smtp.ssl.protocols = 'TLSv1.2'
-}
+}

workflows/get_mzmls.nf

@@ -80,9 +80,7 @@ workflow get_mzmls {
             }.set{ms_file_ch}
 
         // Convert raw files if applicable
-        MSCONVERT(ms_file_ch.raw,
-                  params.msconvert.do_demultiplex,
-                  params.msconvert.do_simasspectra)
+        MSCONVERT(ms_file_ch.raw)
 
         mzml_ch = MSCONVERT.out.concat(ms_file_ch.mzml)
 }

workflows/get_pdc_files.nf

@@ -42,9 +42,7 @@ workflow get_pdc_files {
             | map{row -> tuple(row.url, row.file_name, row.md5sum)} \
             | GET_FILE
 
-        MSCONVERT(GET_FILE.out.downloaded_file,
-                  params.msconvert.do_demultiplex,
-                  params.msconvert.do_simasspectra)
+        MSCONVERT(GET_FILE.out.downloaded_file)
 
         wide_mzml_ch = MSCONVERT.out.mzml_file
 }