Merge branch 'main' of https://github.com/bigbio/nf-modules into dev

Author: ypriverol

.gitignore

@@ -198,9 +198,13 @@ dag.svg
 testing/
 testing*/
 *.pyc
+.nf-test
+*nf.test.snap
 
 # Codacy
 .codacy
 
 # IDEA
 .idea/
+
+.nf-test*

modules/bigbio/onsite/environment.yml

@@ -1,4 +1,3 @@
-name: onsite
 channels:
   - conda-forge
   - bioconda

modules/bigbio/onsite/main.nf

@@ -1,29 +1,33 @@
 process ONSITE {
-    tag "$meta.mzml_id"
+    tag "${meta.id}"
     label 'process_medium'
     label 'onsite'
 
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/pyonsite:0.0.2--pyhdfd78af_0' :
-        'quay.io/biocontainers/pyonsite:0.0.2--pyhdfd78af_0' }"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/pyonsite:0.0.2--pyhdfd78af_0'
+        : 'biocontainers/pyonsite:0.0.2--pyhdfd78af_0'}"
 
     input:
     tuple val(meta), path(mzml_file), path(id_file)
 
     output:
-    tuple val(meta), path("${id_file.baseName}_*.idXML"), emit: ptm_in_id_onsite
+    tuple val(meta), path("${prefix}_*.idXML"), emit: ptm_in_id_onsite
     path "versions.yml", emit: versions
     path "*.log", emit: log
 
+    when:
+    task.ext.when == null || task.ext.when
+
     script:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.mzml_id}"
+    prefix = task.ext.prefix ?: "${meta.id}"
 
-    // Algorithm selection: ascore (default), phosphors, or lucxor
-    def algorithm = params.onsite_algorithm ?: 'ascore'
+    // Algorithm selection: lucxor (default), ascore, or phosphors
+    def algorithm = params.onsite_algorithm ?: 'lucxor'
 
     // Common parameters for all algorithms
     def fragment_tolerance = params.onsite_fragment_tolerance ?: '0.05'
+    def compute_all_scores = params.onsite_compute_all_scores ? '--compute-all-scores' : ''
 
     // Set default value for add_decoys (can be overridden by setting params.onsite_add_decoys = false)
     def onsite_add_decoys = params.containsKey('onsite_add_decoys') ? params.onsite_add_decoys : true
@@ -39,32 +43,31 @@ process ONSITE {
     if (algorithm == 'ascore') {
         // AScore: uses -in, -id, -out, --fragment-mass-unit
         fragment_unit = params.onsite_fragment_unit ?: 'Da'
+        def optional_flags = [add_decoys, compute_all_scores, debug].findAll { a -> a }.join(' \\\n            ')
         algorithm_cmd = """
         onsite ascore \\
             -in ${mzml_file} \\
             -id ${id_file} \\
-            -out ${id_file.baseName}_ascore.idXML \\
+            -out ${prefix}_ascore.idXML \\
             --fragment-mass-tolerance ${fragment_tolerance} \\
-            --fragment-mass-unit ${fragment_unit} \\
-            ${add_decoys} \\
-            ${debug} \\
-            ${args}
+            --fragment-mass-unit ${fragment_unit}${optional_flags ? ' \\\n            ' + optional_flags : ''}
         """
-    } else if (algorithm == 'phosphors') {
+    }
+    else if (algorithm == 'phosphors') {
         // PhosphoRS: uses -in, -id, -out, --fragment-mass-unit
         fragment_unit = params.onsite_fragment_unit ?: 'Da'
+        def optional_flags = [add_decoys, compute_all_scores, debug].findAll { a -> a }.join(' \\\n            ')
         algorithm_cmd = """
         onsite phosphors \\
             -in ${mzml_file} \\
             -id ${id_file} \\
-            -out ${id_file.baseName}_phosphors.idXML \\
+            -out ${prefix}_phosphors.idXML \\
             --fragment-mass-tolerance ${fragment_tolerance} \\
-            --fragment-mass-unit ${fragment_unit} \\
-            ${add_decoys} \\
-            ${debug} \\
+            --fragment-mass-unit ${fragment_unit}${optional_flags ? ' \\\n            ' + optional_flags : ''}
             ${args}
         """
-    } else if (algorithm == 'lucxor') {
+    }
+    else if (algorithm == 'lucxor') {
         // LucXor: uses -in, -id, -out, --fragment-error-units (note: error-units not mass-unit)
         fragment_unit = params.onsite_fragment_error_units ?: 'Da'
         def fragment_method = params.onsite_fragment_method ?: 'CID'
@@ -74,20 +77,22 @@ process ONSITE {
         def max_num_perm = params.onsite_max_num_perm ?: '16384'
         def modeling_threshold = params.onsite_modeling_score_threshold ?: '0.95'
         def scoring_threshold = params.onsite_scoring_threshold ?: '0.0'
-        def min_num_psms = params.onsite_min_num_psms_model ?: '50'
+        def min_num_psms = params.onsite_min_num_psms_model ?: '5'
         def rt_tolerance = params.onsite_rt_tolerance ?: '0.01'
+        def disable_split_by_charge = params.onsite_disable_split_by_charge ? '--disable-split-by-charge' : ''
 
         // Optional target modifications - default for LucXor includes decoy
         def target_mods = params.onsite_target_modifications ? "--target-modifications ${params.onsite_target_modifications}" : "--target-modifications 'Phospho(S),Phospho(T),Phospho(Y),PhosphoDecoy(A)'"
         def neutral_losses = params.onsite_neutral_losses ? "--neutral-losses ${params.onsite_neutral_losses}" : "--neutral-losses 'sty -H3PO4 -97.97690'"
         def decoy_mass = params.onsite_decoy_mass ? "--decoy-mass ${params.onsite_decoy_mass}" : "--decoy-mass 79.966331"
         def decoy_losses = params.onsite_decoy_neutral_losses ? "--decoy-neutral-losses ${params.onsite_decoy_neutral_losses}" : "--decoy-neutral-losses 'X -H3PO4 -97.97690'"
 
+        def optional_flags = [disable_split_by_charge, compute_all_scores, debug].findAll { a -> a }.join(' \\\n            ')
         algorithm_cmd = """
         onsite lucxor \\
             -in ${mzml_file} \\
             -id ${id_file} \\
-            -out ${id_file.baseName}_lucxor.idXML \\
+            -out ${prefix}_lucxor.idXML \\
             --fragment-method ${fragment_method} \\
             --fragment-mass-tolerance ${fragment_tolerance} \\
             --fragment-error-units ${fragment_unit} \\
@@ -102,21 +107,19 @@ process ONSITE {
             --modeling-score-threshold ${modeling_threshold} \\
             --scoring-threshold ${scoring_threshold} \\
             --min-num-psms-model ${min_num_psms} \\
-            --rt-tolerance ${rt_tolerance} \\
-            ${debug} \\
-            ${args}
+            --rt-tolerance ${rt_tolerance}${optional_flags ? ' \\\n            ' + optional_flags : ''}
         """
-    } else {
-        error "Unknown onsite algorithm: ${algorithm}. Supported algorithms: ascore, phosphors, lucxor"
+    }
+    else {
+        error("Unknown onsite algorithm: ${algorithm}. Supported algorithms: ascore, phosphors, lucxor")
     }
 
     """
-    ${algorithm_cmd} \\
-        2>&1 | tee ${id_file.baseName}_${algorithm}.log
+    ${algorithm_cmd.trim()} 2>&1 | tee ${prefix}_${algorithm}.log
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        onsite: \$(onsite --version 2>&1 | grep -oP 'version \\K[0-9.]+' || echo "unknown")
+        onsite: \$(onsite --version 2>&1 | grep -oE 'version \\K[0-9.]+' || echo "unknown")
         algorithm: ${algorithm}
     END_VERSIONS
     """

modules/bigbio/onsite/meta.yml

@@ -1,5 +1,6 @@
 name: onsite
-description: Post-translational modification (PTM) localization using onsite algorithms (AScore, PhosphoRS, LucXor)
+description: Post-translational modification (PTM) localization using onsite
+  algorithms (AScore, PhosphoRS, LucXor)
 keywords:
   - onsite
   - PTM
@@ -18,39 +19,51 @@ tools:
       homepage: https://github.com/bigbio/onsite
       documentation: https://github.com/bigbio/onsite/blob/main/README.md
       tool_dev_url: https://github.com/bigbio/onsite
-      doi: ""
-      licence: ["MIT"]
+      licence:
+        - "MIT"
+      identifier: ""
 input:
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', mzml_id:'sample1' ]
-  - mzml_file:
-      type: file
-      description: Input spectrum file in mzML format
-      pattern: "*.mzML"
-  - id_file:
-      type: file
-      description: Protein/peptide identifications file in idXML format
-      pattern: "*.idXML"
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. [ id:'test', mzml_id:'sample1' ]
-  - ptm_in_id_onsite:
-      type: file
-      description: Protein/peptide identifications file with PTM localization scores
-      pattern: "*_{ascore,phosphors,lucxor}.idXML"
-  - log:
-      type: file
-      description: Log file from onsite execution
-      pattern: "*.log"
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'test', mzml_id:'sample1' ]`
+    - mzml_file:
+        type: file
+        description: Input spectrum file in mzML format
+        pattern: "*.mzML"
+        ontologies: []
+    - id_file:
+        type: file
+        description: Protein/peptide identifications file in idXML format
+        pattern: "*.idXML"
+        ontologies: []
+output:
+  ptm_in_id_onsite:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+      - ${prefix}_*.idXML:
+          type: file
+          description: Output idXML file containing PTM localization results from
+            onsite
+          pattern: "${prefix}_*.idXML"
+          ontologies: []
+  log:
+    - "*.log":
+        type: file
+        description: Log file from onsite execution
+        pattern: "*.log"
+        ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750
 authors:
   - "@ypriverol"
   - "@weizhongchun"
+  - "@enryh"

modules/bigbio/onsite/tests/main.nf.test

@@ -5,6 +5,7 @@ nextflow_process {
     process "ONSITE"
     tag "modules"
     tag "modules_onsite"
+    tag "modules_bigbio"
     tag "onsite"
 
     test("Should run AScore algorithm") {

modules/bigbio/thermorawfileparser/environment.yml

@@ -1,4 +1,3 @@
-name: thermorawfileparser
 channels:
   - conda-forge
   - bioconda

modules/bigbio/thermorawfileparser/main.nf

@@ -1,5 +1,5 @@
 process THERMORAWFILEPARSER {
-    tag "$meta.mzml_id"
+    tag "${meta.id}"
     label 'process_low'
     label 'process_single'
     label 'error_retry'
@@ -9,59 +9,64 @@ process THERMORAWFILEPARSER {
         'https://depot.galaxyproject.org/singularity/thermorawfileparser:2.0.0.dev--h9ee0642_0' :
         'biocontainers/thermorawfileparser:2.0.0.dev--h9ee0642_0' }"
 
-    stageInMode {
-        if (task.attempt == 1) {
-            if (task.executor == "awsbatch") {
-                'symlink'
-            } else {
-                'link'
-            }
-        } else if (task.attempt == 2) {
-            if (task.executor == "awsbatch") {
-                'copy'
-            } else {
-                'symlink'
-            }
-        } else {
-            'copy'
-        }
-    }
     input:
-    tuple val(meta), path(rawfile)
+    tuple val(meta), path(raw)
 
     output:
-    tuple val(meta), path("*.{mzML,mgf,parquet}"), emit: convert_files
-    path "versions.yml",   emit: versions
-    path "*.log",   emit: log
+    tuple val(meta), path("*.{mzML,mzML.gz,mgf,mgf.gz,parquet,parquet.gz}"), emit: spectra
+    tuple val("${task.process}"), val('thermorawfileparser'), eval("thermorawfileparser --version"), emit: versions_thermorawfileparser, topic: versions
+    path "*.log", emit: log
+
+    when:
+    task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    // Detect existing format options in any supported syntax: -f=2, -f 2, --format=2,
+    // or --format 2.
+    def hasFormatArg = (args =~ /(^|\s)(-f(=|\s)\d+|--format(=|\s)\d+)/).find()
     // Default to indexed mzML format (-f=2) if not specified in args
-    def formatArg = args.contains('-f=') ? '' : '-f=2'
+    def formatArg = hasFormatArg ? '' : '-f=2'
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def suffix = args.contains("--format 0") || args.contains("-f 0")
+        ? "mgf"
+        : args.contains("--format 1") || args.contains("-f 1")
+            ? "mzML"
+            : args.contains("--format 2") || args.contains("-f 2")
+                ? "mzML"
+                : args.contains("--format 3") || args.contains("-f 3")
+                    ? "parquet"
+                    : "mzML"
+    suffix = args.contains("--gzip") ? "${suffix}.gz" : "${suffix}"
 
     """
-    ThermoRawFileParser.sh -i='${rawfile}' ${formatArg} ${args} -o=./ 2>&1 | tee '${rawfile.baseName}_conversion.log'
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        ThermoRawFileParser: \$(ThermoRawFileParser.sh --version)
-    END_VERSIONS
+    thermorawfileparser \\
+        -i='${raw}' \\
+        ${formatArg} ${args} \\
+        -o=./ 2>&1 | tee '${prefix}_conversion.log'
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.mzml_id}"
     def args = task.ext.args ?: ''
-    // Determine output format from args, default to mzML
-    // Format 0 = MGF, formats 1-2 = mzML, format 3 = Parquet, format 4 = None
-    def outputExt = (args =~ /-f=0\b/).find() ? 'mgf' : 'mzML'
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def suffix = args.contains("--format 0") || args.contains("-f 0")
+        ? "mgf"
+        : args.contains("--format 1") || args.contains("-f 1")
+            ? "mzML"
+            : args.contains("--format 2") || args.contains("-f 2")
+                ? "mzML"
+                : args.contains("--format 3") || args.contains("-f 3")
+                    ? "parquet"
+                    : "mzML"
+    suffix = args.contains("--gzip") ? "${suffix}.gz" : "${suffix}"
 
     """
-    touch '${prefix}.${outputExt}'
+    touch '${prefix}.${suffix}'
     touch '${prefix}_conversion.log'
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        ThermoRawFileParser: \$(ThermoRawFileParser.sh --version)
+        ThermoRawFileParser: \$(thermorawfileparser --version)
     END_VERSIONS
     """
 }