Merge pull request #2 from daichengxin/dev

fixed version yaml

bin/mzml_statistics.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+
+from pyopenms import MzMLFile, MSExperiment
+import os
+import pandas as pd
+import click
+
+CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
+
+
+@click.group(context_settings=CONTEXT_SETTINGS)
+def cli():
+    pass
+
+
+@click.command("mzml_dataframe")
+@click.option("--mzml_folder", "-d")
+@click.pass_context
+def mzml_dataframe(ctx, mzml_folder):
+
+    file_columns = ["File_Name", "SpectrumID", "MSLevel", "Charge", "MS2_peaks", "Base_Peak_Intensity"]
+    mzml_paths = list(i for i in os.listdir(mzml_folder) if i.endswith(".mzML"))
+    mzml_count = 1
+
+    def parse_mzml(file_name, file_columns):
+        info = []
+        exp = MSExperiment()
+        MzMLFile().load(file_name, exp)
+        for i in exp:
+            name = os.path.split(file_name)[1]
+            id = i.getNativeID()
+            MSLevel = i.getMSLevel()
+            if MSLevel == 2:
+                charge_state = i.getPrecursors()[0].getCharge()
+                peaks_tuple = i.get_peaks()
+                peak_per_ms2 = len(peaks_tuple[0])
+                if i.getMetaValue("base peak intensity"):
+                    base_peak_intensity = i.getMetaValue("base peak intensity")
+                else:
+                    base_peak_intensity = max(peaks_tuple[1]) if len(peaks_tuple[1]) > 0 else "null"
+                info_list = [name, id, 2, charge_state, peak_per_ms2, base_peak_intensity]
+            else:
+                info_list = [name, id, MSLevel, "null", "null", "null"]
+
+            info.append(info_list)
+
+        return pd.DataFrame(info, columns=file_columns)
+
+    for i in mzml_paths:
+        mzml_df = parse_mzml(mzml_folder + i, file_columns)
+        tsv_header = True if mzml_count == 1 else False
+        mzml_df.to_csv("mzml_info.tsv", mode="a", sep="\t", index=False, header=tsv_header)
+        mzml_count += 1
+
+
+cli.add_command(mzml_dataframe)
+
+if __name__ == "__main__":
+    cli()

modules/local/diannconvert/main.nf

@@ -2,11 +2,11 @@ process DIANNCONVERT {
     tag "$exp_design.Name"
     label 'process_low'
 
-    conda (params.enable_conda ? "conda-forge::pandas_schema conda-forge::lzstring bioconda::pmultiqc=0.0.13" : null)
+    conda (params.enable_conda ? "conda-forge::pandas_schema conda-forge::lzstring bioconda::pmultiqc=0.0.16" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/pmultiqc:0.0.13--pyhdfd78af_0"
+        container "https://depot.galaxyproject.org/singularity/pmultiqc:0.0.16--pyhdfd78af_0"
     } else {
-        container "quay.io/biocontainers/pmultiqc:0.0.13--pyhdfd78af_0"
+        container "quay.io/biocontainers/pmultiqc:0.0.16--pyhdfd78af_0"
     }
 
     input:

modules/local/mzmlstatistics/main.nf

@@ -0,0 +1,34 @@
+process MZMLSTATISTICS {
+    label 'process_medium'
+    // TODO could be easily parallelized
+    label 'process_single_thread'
+
+    conda (params.enable_conda ? "conda-forge::pandas_schema conda-forge::lzstring bioconda::pmultiqc=0.0.16" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/pmultiqc:0.0.16--pyhdfd78af_0"
+    } else {
+        container "quay.io/biocontainers/pmultiqc:0.0.16--pyhdfd78af_0"
+    }
+
+    input:
+    path("out/*")
+
+    output:
+    path "mzml_info.tsv", emit: mzml_statistics
+    path "versions.yml", emit: version
+    path "*.log", emit: log
+
+    script:
+    def args = task.ext.args ?: ''
+
+    """
+    mzml_statistics.py mzml_dataframe \\
+        --mzml_folder "./out/" \\
+        |& tee mzml_statistics.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pyopenms: \$(echo "2.8.0")
+    END_VERSIONS
+    """
+}

modules/local/mzmlstatistics/meta.yml

@@ -0,0 +1,26 @@
+name: MZMLSTATISTICS
+description: A module for mzMLs statistics
+keywords:
+  - mzML
+  - statistics
+tools:
+  - custom:
+      description: |
+        A custom module for mzMLs statistics.
+      homepage: https://github.com/bigbio/quantms
+      documentation: https://github.com/bigbio/quantms/tree/readthedocs
+input:
+  - mzmls:
+      type: dir
+      description: mzML files directory
+output:
+  - mzml_statistics:
+      type: file
+      description: mzMLs statistics file
+      pattern: "mzml_info.tsv"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "versions.yml"
+authors:
+  - "@wanghong"

modules/local/openms/consensusid/main.nf

@@ -37,7 +37,7 @@ process CONSENSUSID {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        ConsensusID: \$(ConsensusID 2>&1  | grep -E '^Version(.*)' | sed 's/Version: //g')
+        ConsensusID: \$(ConsensusID 2>&1  | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/decoydatabase/main.nf

@@ -33,7 +33,7 @@ process DECOYDATABASE {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        DecoyDatabase: \$(DecoyDatabase 2>&1  | grep -E '^Version(.*)' | sed 's/Version: //g')
+        DecoyDatabase: \$(DecoyDatabase 2>&1  | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/epifany/main.nf

@@ -36,7 +36,7 @@ process EPIFANY {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        Epifany: \$(Epifany 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        Epifany: \$(Epifany 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/extractpsmfeatures/main.nf

@@ -31,7 +31,7 @@ process EXTRACTPSMFEATURES {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        PSMFeatureExtractor: \$(PSMFeatureExtractor 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        PSMFeatureExtractor: \$(PSMFeatureExtractor 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/falsediscoveryrate/main.nf

@@ -33,7 +33,7 @@ process FALSEDISCOVERYRATE {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        FalseDiscoveryRate: \$(FalseDiscoveryRate 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        FalseDiscoveryRate: \$(FalseDiscoveryRate 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/filemerge/main.nf

@@ -32,7 +32,7 @@ process FILEMERGE {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        FileMerger: \$(FileMerger 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        FileMerger: \$(FileMerger 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/idconflictresolver/main.nf

@@ -28,7 +28,7 @@ process IDCONFLICTRESOLVER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IDConflictResolver: \$(IDConflictResolver 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IDConflictResolver: \$(IDConflictResolver 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/idfilter/main.nf

@@ -31,7 +31,7 @@ process IDFILTER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IDFilter: \$(IDFilter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IDFilter: \$(IDFilter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/idmapper/main.nf

@@ -32,7 +32,7 @@ process IDMAPPER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IDMapper: \$(IDMapper 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IDMapper: \$(IDMapper 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/idpep/main.nf

@@ -30,7 +30,7 @@ process IDPEP {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IDPosteriorErrorProbability: \$(IDPosteriorErrorProbability 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IDPosteriorErrorProbability: \$(IDPosteriorErrorProbability 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/idscoreswitcher/main.nf

@@ -31,7 +31,7 @@ process IDSCORESWITCHER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IDScoreSwitcher: \$(IDScoreSwitcher 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IDScoreSwitcher: \$(IDScoreSwitcher 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/indexpeptides/main.nf

@@ -57,7 +57,7 @@ process INDEXPEPTIDES {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        PeptideIndexer: \$(PeptideIndexer 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        PeptideIndexer: \$(PeptideIndexer 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/isobaricanalyzer/main.nf

@@ -44,7 +44,7 @@ process ISOBARICANALYZER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        IsobaricAnalyzer: \$(IsobaricAnalyzer --version 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        IsobaricAnalyzer: \$(IsobaricAnalyzer --version 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/msstatsconverter/main.nf

@@ -31,7 +31,7 @@ process MSSTATSCONVERTER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        MSstatsConverter: \$(MSstatsConverter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        MSstatsConverter: \$(MSstatsConverter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/mzmlindexing/main.nf

@@ -25,7 +25,7 @@ process MZMLINDEXING {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        FileConverter: \$(FileConverter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        FileConverter: \$(FileConverter 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/openmspeakpicker/main.nf

@@ -35,7 +35,7 @@ process OPENMSPEAKPICKER {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        PeakPickerHiRes: \$(PeakPickerHiRes 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g')
+        PeakPickerHiRes: \$(PeakPickerHiRes 2>&1 | grep -E '^Version(.*)' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/openms/proteininference/main.nf

@@ -37,7 +37,7 @@ process PROTEININFERENCE {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        ProteinInference: \$(ProteinInference 2>&1 | grep -E '^Version(.*) ' | sed 's/Version: //g')
+        ProteinInference: \$(ProteinInference 2>&1 | grep -E '^Version(.*) ' | sed 's/Version: //g' | cut -d ' ' -f 1)
     END_VERSIONS
     """
 }

modules/local/pmultiqc/main.nf

@@ -1,11 +1,11 @@
 process PMULTIQC {
     label 'process_high'
 
-    conda (params.enable_conda ? "conda-forge::pandas_schema conda-forge::lzstring bioconda::pmultiqc=0.0.15" : null)
+    conda (params.enable_conda ? "conda-forge::pandas_schema conda-forge::lzstring bioconda::pmultiqc=0.0.16" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/pmultiqc:0.0.15--pyhdfd78af_0"
+        container "https://depot.galaxyproject.org/singularity/pmultiqc:0.0.16--pyhdfd78af_0"
     } else {
-        container "quay.io/biocontainers/pmultiqc:0.0.15--pyhdfd78af_0"
+        container "quay.io/biocontainers/pmultiqc:0.0.16--pyhdfd78af_0"
     }
 
     input:

subworkflows/local/file_preparation.nf

@@ -4,6 +4,7 @@
 
 include { THERMORAWFILEPARSER } from '../../modules/local/thermorawfileparser/main'
 include { MZMLINDEXING } from '../../modules/local/openms/mzmlindexing/main'
+include { MZMLSTATISTICS } from '../../modules/local/mzmlstatistics/main'
 include { OPENMSPEAKPICKER } from '../../modules/local/openms/openmspeakpicker/main'
 
 workflow FILE_PREPARATION {
@@ -13,6 +14,7 @@ workflow FILE_PREPARATION {
     main:
     ch_versions = Channel.empty()
     ch_results = Channel.empty()
+    ch_statistics = Channel.empty()
 
     //
     // Divide mzml files
@@ -51,6 +53,15 @@ workflow FILE_PREPARATION {
     ch_versions = ch_versions.mix(MZMLINDEXING.out.version)
     ch_results = ch_results.mix(MZMLINDEXING.out.mzmls_indexed)
 
+    ch_results.multiMap{
+        meta: it[0]
+        mzml: it[1]
+    }.set{ ch_mzml }
+
+    MZMLSTATISTICS( ch_mzml.mzml.collect() )
+    ch_statistics = ch_statistics.mix(MZMLSTATISTICS.out.mzml_statistics)
+    ch_versions = ch_versions.mix(MZMLSTATISTICS.out.version)
+
     if (params.openms_peakpicking){
         OPENMSPEAKPICKER (
             ch_results
@@ -63,5 +74,6 @@ workflow FILE_PREPARATION {
 
     emit:
     results         = ch_results        // channel: [val(mzml_id), indexedmzml]
+    statistics      = ch_statistics     // channel: [ mzml_statistics.tsv ]
     version         = ch_versions       // channel: [ *.version.txt ]
 }

workflows/quantms.nf

@@ -102,10 +102,6 @@ workflow QUANTMS {
 
     ch_versions = ch_versions.mix(FILE_PREPARATION.out.version.ifEmpty(null))
 
-    FILE_PREPARATION.out.results
-        .map { it -> it[1] }
-        .set { ch_pmultiqc_mzmls }
-
     FILE_PREPARATION.out.results
             .branch {
                 dia: it[0].acquisition_method.contains("dia")
@@ -180,14 +176,14 @@ workflow QUANTMS {
     ch_multiqc_files = Channel.empty()
     ch_multiqc_files = ch_multiqc_files.mix(Channel.from(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)
     ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml'))
     ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
     ch_multiqc_quantms_logo = file("$projectDir/assets/nf-core-quantms_logo_light.png")
 
     SUMMARYPIPELINE (
         CREATE_INPUT_CHANNEL.out.ch_expdesign
             .combine(ch_pipeline_results.ifEmpty([]).combine(ch_multiqc_files.collect())
-            .combine(ch_pmultiqc_mzmls.collect())
             .combine(ch_ids_pmultiqc.collect().ifEmpty([])))
             .combine(ch_msstats_in.ifEmpty([])),
         ch_multiqc_quantms_logo