Add tximport module (port from rnaseq) (nf-core#4884)

* Add tximport module * Populate meta * Fix up tximport * Appease eclint * Fix conda * Fix singularity * Update test_data.config * poke ci * remove rogue empty line * Update tests/config/test_data.config Co-authored-by: Maxime U Garcia <[email protected]> --------- Co-authored-by: Maxime U Garcia <[email protected]>
RSC-RP · Mar 20, 2024 · 7c31a15 · 7c31a15
1 parent 169902c
commit 7c31a15
Show file tree

Hide file tree

Showing 8 changed files with 1,201 additions and 1 deletion.
diff --git a/modules/nf-core/tximeta/tximport/environment.yml b/modules/nf-core/tximeta/tximport/environment.yml
@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "tximeta_tximport"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::bioconductor-tximeta=1.20.1"
diff --git a/modules/nf-core/tximeta/tximport/main.nf b/modules/nf-core/tximeta/tximport/main.nf
@@ -0,0 +1,48 @@
+process TXIMETA_TXIMPORT {
+    label "process_medium"
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bioconductor-tximeta%3A1.20.1--r43hdfd78af_0' :
+        'biocontainers/bioconductor-tximeta:1.20.1--r43hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path("quants/*")
+    tuple val(meta2), path(tx2gene)
+    tuple val(meta3), path(coldata)
+    val quant_type
+
+    output:
+    tuple val(meta), path("*gene_tpm.tsv")                 , emit: tpm_gene
+    tuple val(meta), path("*gene_counts.tsv")              , emit: counts_gene
+    tuple val(meta), path("*gene_counts_length_scaled.tsv"), emit: counts_gene_length_scaled
+    tuple val(meta), path("*gene_counts_scaled.tsv")       , emit: counts_gene_scaled
+    tuple val(meta), path("*gene_lengths.tsv")             , emit: lengths_gene
+    tuple val(meta), path("*transcript_tpm.tsv")           , emit: tpm_transcript
+    tuple val(meta), path("*transcript_counts.tsv")        , emit: counts_transcript
+    tuple val(meta), path("*transcript_lengths.tsv")       , emit: lengths_transcript
+    path "versions.yml"                                    , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'tximport.r'
+
+    stub:
+    """
+    touch ${meta.id}.gene_tpm.tsv
+    touch ${meta.id}.gene_counts.tsv
+    touch ${meta.id}.gene_counts_length_scaled.tsv
+    touch ${meta.id}.gene_counts_scaled.tsv
+    touch ${meta.id}.gene_lengths.tsv
+    touch ${meta.id}.transcript_tpm.tsv
+    touch ${meta.id}.transcript_counts.tsv
+    touch ${meta.id}.transcript_lengths.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        r: \$( R --version | sed '1!d; s/.*version //; s/ .*//' )
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/tximeta/tximport/meta.yml b/modules/nf-core/tximeta/tximport/meta.yml
@@ -0,0 +1,120 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "tximeta_tximport"
+description: |
+  Import transcript-level abundances and estimated counts for gene-level
+  analysis packages
+keywords:
+  - gene
+  - kallisto
+  - pseudoalignment
+  - salmon
+  - transcript
+tools:
+  - "tximeta":
+      description: "Transcript Quantification Import with Automatic Metadata"
+      homepage: "https://bioconductor.org/packages/release/bioc/html/tximeta.html"
+      documentation: "https://bioconductor.org/packages/release/bioc/vignettes/tximeta/inst/doc/tximeta.html"
+      tool_dev_url: "https://github.com/thelovelab/tximeta"
+      doi: "10.1371/journal.pcbi.1007664"
+      licence: ["GPL-2"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing information related to the experiment as a whole
+        e.g. `[ id:'SRP123456' ]`
+  - quants:
+      type: directory
+      description: Paths to subdirectories corresponding to
+        sample-wise runs of Salmon or Kallisto
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing reference information related to the species
+        reference e.g. `[ id:'yeast' ]`
+  - tx2gene:
+      type: file
+      description: A transcript to gene mapping table such as those generated
+        by custom/tx2gene
+      pattern: "*.{csv,tsv}"
+  - meta3:
+      type: map
+      description: |
+        Groovy Map containing information related to the experiment as a whole
+        e.g. `[ id:'SRP123456' ]`
+  - coldata:
+      type: file
+      description: |
+        Optional 'coldata' file equivalent to a sample sheet where the first
+        column corresponds to the sample names (directory names in the input
+        salmon/ kallisto results)
+      pattern: "*.{csv,tsv}"
+  - quant_type:
+      type: string
+      description: Quantification type, 'kallisto' or 'salmon'
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing information related to the experiment as a whole
+        e.g. `[ id:'SRP123456' ]`
+  - tpm_gene:
+      type: file
+      description: |
+        Abundance (TPM) values derived from tximport output after
+        summarizeToGene(), without a 'countsFromAbundance' specification
+      pattern: "*gene_tpm.tsv"
+  - counts_gene:
+      type: file
+      description: |
+        Count values derived from tximport output after
+        summarizeToGene(), without a 'countsFromAbundance' specification
+      pattern: "*gene_counts.tsv"
+  - counts_gene_length_scaled:
+      type: file
+      description: |
+        Count values derived from tximport output after summarizeToGene(), with
+        a 'countsFromAbundance' specification of 'lengthScaledTPM'
+      pattern: "*gene_counts_length_scaled.tsv"
+  - counts_gene_scaled:
+      type: file
+      description: |
+        Count values derived from tximport output after summarizeToGene(), with
+        a 'countsFromAbundance' specification of 'scaledTPM'
+      pattern: "*gene_counts_scaled.tsv"
+  - gene_lengths:
+      type: file
+      description: |
+        Length values derived from tximport output after summarizeToGene(),
+        without a 'countsFromAbundance' specification
+      pattern: "*gene_lengths.tsv"
+  - tpm_transcript:
+      type: file
+      description: |
+        Abundance (TPM) values derived from tximport output without
+        summarizeToGene(), without a 'countsFromAbundance' specification
+      pattern: "*transcript_tpm.tsv"
+  - counts_transcript:
+      type: file
+      description: |
+        Count values derived from tximport output without
+        summarizeToGene(), without a 'countsFromAbundance' specification
+      pattern: "*transcript_counts.tsv"
+  - transcript_lengths:
+      type: file
+      description: |
+        Length values derived from tximport output without summarizeToGene(),
+        without a 'countsFromAbundance' specification
+      pattern: "*gene_lengths.tsv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"