allow skip raw conversion

daichengxin · May 13, 2024 · 0a096b5 · 0a096b5
1 parent f571096
commit 0a096b5
Show file tree

Hide file tree

Showing 6 changed files with 43 additions and 20 deletions.
diff --git a/bin/diann_convert.py b/bin/diann_convert.py
@@ -39,12 +39,13 @@ def cli():
 @click.option("--folder", "-f")
 @click.option("--exp_design", "-d")
 @click.option("--diann_version", "-v")
+@click.option("--skip_mzTab", "-s")
 @click.option("--dia_params", "-p")
 @click.option("--charge", "-c")
 @click.option("--missed_cleavages", "-m")
 @click.option("--qvalue_threshold", "-q", type=float)
 @click.pass_context
-def convert(ctx, folder, exp_design, dia_params, diann_version, charge, missed_cleavages, qvalue_threshold):
+def convert(ctx, folder, exp_design, dia_params, diann_version, skip_mzTab, charge, missed_cleavages, qvalue_threshold):
     """
     Convert DIA-NN output to MSstats, Triqler or mzTab.
     The output formats are used for quality control and downstream analysis.
@@ -138,16 +139,17 @@ def convert(ctx, folder, exp_design, dia_params, diann_version, charge, missed_c
     logger.info(f"Triqler input file is saved as {exp_out_prefix}_triqler_in.tsv")
     del out_triqler
 
-    mztab_out = f"{Path(exp_design).stem}_out.mzTab"
-    # Convert to mzTab
-    diann_directory.convert_to_mztab(
-        report=report,
-        f_table=f_table,
-        charge=charge,
-        missed_cleavages=missed_cleavages,
-        dia_params=dia_params,
-        out=mztab_out,
-    )
+    if not skip_mzTab:
+        mztab_out = f"{Path(exp_design).stem}_out.mzTab"
+        # Convert to mzTab
+        diann_directory.convert_to_mztab(
+            report=report,
+            f_table=f_table,
+            charge=charge,
+            missed_cleavages=missed_cleavages,
+            dia_params=dia_params,
+            out=mztab_out,
+        )
 
 
 def _true_stem(x):

diff --git a/modules/local/diannconvert/main.nf b/modules/local/diannconvert/main.nf
@@ -22,7 +22,7 @@ process DIANNCONVERT {
     output:
     path "*msstats_in.csv", emit: out_msstats
     path "*triqler_in.tsv", emit: out_triqler
-    path "*.mzTab", emit: out_mztab
+    path "*.mzTab", emit: out_mztab optional true
     path "*.log", emit: log
     path "versions.yml", emit: version
 
@@ -39,6 +39,7 @@ process DIANNCONVERT {
         --folder ./ \\
         --exp_design ${exp_design} \\
         --diann_version ./version/versions.yml \\
+        --skip_mzTab $params.skip_raw_conversion \\
         --dia_params "${dia_params}" \\
         --charge $params.max_precursor_charge \\
         --missed_cleavages $params.allowed_missed_cleavages \\

diff --git a/modules/local/pmultiqc/main.nf b/modules/local/pmultiqc/main.nf
@@ -21,7 +21,7 @@ process PMULTIQC {
 
     script:
     def args = task.ext.args ?: ''
-    def disable_pmultiqc = (params.enable_pmultiqc) && (params.export_mztab) ? "" : "--disable_plugin"
+    def disable_pmultiqc = (params.enable_pmultiqc) && (params.export_mztab) && (!params.skip_raw_conversion) ? "" : "--disable_plugin"
     def disable_table_plots = (params.enable_pmultiqc) && (params.skip_table_plots) ? "--disable_table" : ""
     def disable_idxml_index = (params.enable_pmultiqc) && (params.pmultiqc_idxml_skip) ? "--ignored_idxml" : ""
 

diff --git a/nextflow.config b/nextflow.config
@@ -189,6 +189,7 @@ params {
     species_genes           = false
     diann_normalize         = true
     diann_speclib           = null
+    skip_raw_conversion     = false
 
     // DIA-NN: Extras
     skip_preliminary_analysis    = false

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -175,6 +175,13 @@
                     "description": "Force initial re-indexing of input mzML files. Also fixes some common mistakes in slightly incomplete/outdated mzMLs. (Default: true for safety)",
                     "fa_icon": "far fa-check-square",
                     "help_text": "Force re-indexing in the beginning of the pipeline to make sure that indices are up-to-date and to avoid redundant indexing on-demand in steps that require an index (e.g., Comet)."
+                },
+                "skip_raw_conversion": {
+                    "type": "boolean",
+                    "default": false,
+                    "description": "Convert RAW files to mzML for DIA-NN workflow",
+                    "fa_icon": "far fa-check-square",
+                    "help_text": "Whether to convert RAW files to .mzML for DIA-NN workflow"
                 }
             },
             "fa_icon": "far fa-chart-bar"

diff --git a/workflows/quantms.nf b/workflows/quantms.nf
@@ -61,13 +61,23 @@ workflow QUANTMS {
     //
     // SUBWORKFLOW: File preparation
     //
-    FILE_PREPARATION (
-        CREATE_INPUT_CHANNEL.out.ch_meta_config_iso.mix(CREATE_INPUT_CHANNEL.out.ch_meta_config_lfq).mix(CREATE_INPUT_CHANNEL.out.ch_meta_config_dia)
-    )
+    statistics = Channel.empty()
+    ch_raw_input = Channel.empty()
+    if (params.skip_raw_conversion == false) {
+        FILE_PREPARATION (
+            CREATE_INPUT_CHANNEL.out.ch_meta_config_iso.mix(CREATE_INPUT_CHANNEL.out.ch_meta_config_lfq).mix(CREATE_INPUT_CHANNEL.out.ch_meta_config_dia)
+        )
+        ch_versions = ch_versions.mix(FILE_PREPARATION.out.version.ifEmpty(null))
+        statistics = FILE_PREPARATION.out.statistics
+    } else {
+        ch_raw_input = CREATE_INPUT_CHANNEL.out.ch_meta_config_dia
+        if (ch_raw_input.ifEmpty(true)) {
+            exit 1, 'Allows skipping of raw data conversions in the DIA workflow only!'
+        }
+    }
 
-    ch_versions = ch_versions.mix(FILE_PREPARATION.out.version.ifEmpty(null))
 
-    FILE_PREPARATION.out.results
+    ch_raw_input.mix(FILE_PREPARATION.out.results)
             .branch {
                 dia: it[0].acquisition_method.contains("dia")
                 iso: it[0].labelling_type.contains("tmt") || it[0].labelling_type.contains("itraq")
@@ -131,7 +141,7 @@ workflow QUANTMS {
         ch_msstats_in = ch_msstats_in.mix(LFQ.out.msstats_in)
         ch_versions = ch_versions.mix(LFQ.out.versions.ifEmpty(null))
 
-        DIA(ch_fileprep_result.dia, CREATE_INPUT_CHANNEL.out.ch_expdesign, FILE_PREPARATION.out.statistics)
+        DIA(ch_fileprep_result.dia, CREATE_INPUT_CHANNEL.out.ch_expdesign, statistics)
         ch_pipeline_results = ch_pipeline_results.mix(DIA.out.diann_report)
         ch_msstats_in = ch_msstats_in.mix(DIA.out.msstats_in)
         ch_versions = ch_versions.mix(DIA.out.versions.ifEmpty(null))
@@ -161,7 +171,9 @@ workflow QUANTMS {
     ch_methods_description                = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description))
     ch_multiqc_files                      = ch_multiqc_files.mix(ch_multiqc_config)
     ch_multiqc_files                      = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-    ch_multiqc_files                      = ch_multiqc_files.mix(FILE_PREPARATION.out.statistics)
+    if (!params.skip_raw_conversion) {
+        ch_multiqc_files                      = ch_multiqc_files.mix(FILE_PREPARATION.out.statistics)
+    }
     ch_multiqc_files                      = ch_multiqc_files.mix(ch_collated_versions)
     ch_multiqc_files                      = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false))
     ch_multiqc_quantms_logo               = file("$projectDir/assets/nf-core-quantms_logo_light.png")