POC contrasts csv -> yaml

.github/workflows/ci.yml

@@ -8,6 +8,7 @@ on:
     branches:
       - dev
       - master
+      - dev_tmp
   release:
     types: [published]
   workflow_dispatch:

CHANGELOG.md

@@ -12,6 +12,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#345](https://github.com/nf-core/differentialabundance/pull/345)] - Plot differentially expressed genes by gene biotype ([@atrigila](https://github.com/atrigila), review by [@grst](https://github.com/grst))
 - [[#343](https://github.com/nf-core/differentialabundance/pull/343)] - Add pipeline-level nf-tests ([@atrigila](https://github.com/atrigila), review by [@pinin4fjords](https://github.com/pinin4fjords) and [@nschcolnicov](https://github.com/nschcolnicov))
 - [[#286](https://github.com/nf-core/differentialabundance/pull/286)] - Integration of limma voom for rnaseq data ([@KamilMaliszArdigen](https://github.com/KamilMaliszArdigen), review by [@pinin4fjords](https://github.com/pinin4fjords))
+- [[#380](https://github.com/nf-core/differentialabundance/pull/380)] - Replace local filter_diff_table module with nf-core one, and create nf-tests for tabular_to_gsea_chip. ([@nschcolnicov](https://github.com/nschcolnicov), review by [@pinin4fjords](https://github.com/pinin4fjords))
+- [[#382](https://github.com/nf-core/differentialabundance/pull/382)] - Add YAML formatted contrasts file handling. ([@nschcolnicov](https://github.com/nschcolnicov), review by [@TODO](https://github.com/TODO))
 
 ### Fixed
 

conf/modules.config

@@ -281,8 +281,8 @@ process {
         ].join(' ').trim() }
     }
 
-    withName: FILTER_DIFFTABLE {
-        ext.prefix = { "${meta.id}" }
+    withName: CUSTOM_FILTERDIFFERENTIALTABLE {
+        ext.prefix = { "${input_file.toString().split("\\.").init().join(".")}" }
         publishDir = [
             [
                 path: { "${params.outdir}/tables/differential" },

modules.json

@@ -15,6 +15,11 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "custom/filterdifferentialtable": {
+                        "branch": "master",
+                        "git_sha": "833a65446ea117d092d4940f098236b6766e7aac",
+                        "installed_by": ["modules"]
+                    },
                     "custom/matrixfilter": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",

modules/local/shinyngs/validatefomcomponents/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::r-shinyngs=2.0.0

modules/local/shinyngs/validatefomcomponents/main.nf

@@ -0,0 +1,45 @@
+process SHINYNGS_VALIDATEFOMCOMPONENTS { //TODO this module and whole folder should be deleted once https://github.com/nf-core/differentialabundance/issues/362 is closed, is replaced by the nf-core version of it.
+    tag "$sample"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "community.wave.seqera.io/library/r-shinyngs_r-yaml:aa63537f6db6190c"
+
+    input:
+    tuple val(meta),  path(sample), path(assay_files)
+    tuple val(meta2), path(feature_meta)
+    tuple val(meta3), path(contrasts)
+
+    output:
+    tuple val(meta), path("*/*.sample_metadata.tsv")   , emit: sample_meta
+    tuple val(meta), path("*/*.feature_metadata.tsv")  , emit: feature_meta, optional: true
+    tuple val(meta), path("*/*.assay.tsv")             , emit: assays
+    tuple val(meta), path("*/*.contrasts_file.tsv")    , emit: contrasts
+    path "versions.yml"                                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    // For full list of available args see
+    // https://github.com/pinin4fjords/shinyngs/blob/develop/exec/validate_fom_components.R
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: meta.id
+    def feature = feature_meta ? "--feature_metadata '$feature_meta'" : ''
+
+    """
+    validate_fom_components_yaml.R \\
+        --sample_metadata "$sample" \\
+        $feature \\
+        --assay_files "${assay_files.join(',')}" \\
+        --contrasts_file "$contrasts" \\
+        --output_directory "$prefix" \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        r-base: \$(echo \$(R --version 2>&1) | sed 's/^.*R version //; s/ .*\$//')
+        r-shinyngs: \$(Rscript -e "library(shinyngs); cat(as.character(packageVersion('shinyngs')))")
+    END_VERSIONS
+    """
+}

modules/local/shinyngs/validatefomcomponents/meta.yml

@@ -0,0 +1,100 @@
+name: "shinyngs_validatefomcomponents"
+description: validate consistency of feature and sample annotations with matrices
+  and contrasts
+keywords:
+  - expression
+  - features
+  - observations
+  - validation
+tools:
+  - "shinyngs":
+      description: "Provides Shiny applications for various array and NGS applications.
+        Currently very RNA-seq centric, with plans for expansion."
+      homepage: "https://github.com/pinin4fjords/shinyngs"
+      documentation: "https://rawgit.com/pinin4fjords/shinyngs/master/vignettes/shinyngs.html"
+      tool_dev_url: "https://github.com/pinin4fjords/shinyngs"
+      licence: ["AGPL v3"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing information on experiment, at a minimum an id.
+          e.g. [ id:'test' ]
+    - sample:
+        type: file
+        description: |
+          CSV-format sample sheet with sample metadata
+    - assay_files:
+        type: file
+        description: |
+          List of TSV-format matrix files representing different measures for the same samples (e.g. raw and normalised).
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing information on features.
+          e.g. [ id:'test' ]
+    - feature_meta:
+        type: file
+        description: |
+          TSV-format feature (e.g. gene) metadata
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing information on contrasts.
+          e.g. [ id:'test' ]
+    - contrasts:
+        type: file
+        description: |
+          CSV-format file with four columns identifying the sample sheet variable, reference level, treatment level, and optionally a comma-separated list of covariates used as blocking factors.
+output:
+  - sample_meta:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing information on experiment.
+            e.g. [ id:'test' ]
+      - "*/*.sample_metadata.tsv":
+          type: file
+          description: File containing validated sample metadata
+          pattern: "/*.sample_metadata.tsv"
+  - feature_meta:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing information on experiment.
+            e.g. [ id:'test' ]
+      - "*/*.feature_metadata.tsv":
+          type: file
+          description: File containing validated feature metadata
+          pattern: "/*.feature_metadata.tsv"
+          optional: true
+  - assays:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing information on experiment.
+            e.g. [ id:'test' ]
+      - "*/*.assay.tsv":
+          type: file
+          description: Files containing validated matrices
+          pattern: "/*.assay.tsv"
+  - contrasts:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing information on experiment.
+            e.g. [ id:'test' ]
+      - "*/*.contrasts_file.tsv":
+          type: file
+          description: Files containing validated matrices
+          pattern: "/*.contrasts_file.tsv"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@pinin4fjords"
+maintainers:
+  - "@pinin4fjords"

modules/local/tabulartogseachip/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+
+dependencies:
+  - conda-forge::gawk=5.1.0

modules/local/tabular_to_gsea_chip.nf → modules/local/tabulartogseachip/main.nf

@@ -1,11 +1,10 @@
 process TABULAR_TO_GSEA_CHIP {
 
+    tag "$id"
     label 'process_single'
 
-    conda "conda-forge::gawk=5.1.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/gawk:5.1.0' :
-        'biocontainers/gawk:5.1.0' }"
+    conda "${moduleDir}/environment.yml"
+    container "community.wave.seqera.io/library/gawk:5.1.0--fa97c4ccf4cfbc4b"
 
     input:
     path tsv
@@ -41,4 +40,15 @@ process TABULAR_TO_GSEA_CHIP {
         bash: \$(echo \$(bash --version | grep -Eo 'version [[:alnum:].]+' | sed 's/version //'))
     END_VERSIONS
     """
+
+    stub:
+    """
+    touch stub.chip
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bash: \$(echo \$(bash --version | grep -Eo 'version [[:alnum:].]+' | sed 's/version //'))
+    END_VERSIONS
+    """
+
 }

modules/local/tabulartogseachip/meta.yml

@@ -0,0 +1,41 @@
+name: tabular_to_gsea_chip
+description: Convert tabular data into GSEA-compatible CHIP files.
+keywords:
+  - GSEA
+  - CHIP
+  - Bioinformatics
+tools:
+  - gawk:
+      description: |
+        GNU Awk (gawk) is a powerful programming language designed for text processing and typically used as a data extraction and reporting tool.
+        It is used here to manipulate tabular data and create the CHIP file format.
+      homepage: https://www.gnu.org/software/gawk/
+      documentation: https://www.gnu.org/software/gawk/manual/
+      licence: ["GPL-3.0-or-later"]
+input:
+  - tsv:
+      type: file
+      description: |
+        Tab-separated values (TSV) file containing data to be converted into a CHIP file.
+  - - id:
+        type: string
+        description: |
+          Feature ID attribute in the abundance table as well as in the GTF file (e.g. the gene_id field).
+    - symbol:
+        type: string
+        description: |
+          Feature name attribute in the abundance table as well as in the GTF file (e.g. the gene symbol field).
+output:
+  - chip:
+      type: file
+      description: Generated GSEA-compatible CHIP file.
+      pattern: "*.chip"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@pinin4fjords" # Replace with actual author handles
+maintainers:
+  - "@nschcolnicov"

modules/local/tabulartogseachip/tests/main.nf.test

@@ -0,0 +1,49 @@
+nextflow_process {
+
+    name "Test Process TABULAR_TO_GSEA_CHIP"
+    script "../main.nf"
+    process "TABULAR_TO_GSEA_CHIP"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "tabular_to_gsea_chip"
+
+    test("test_tabular_to_gsea_chip") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.fromPath("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/differentialabundance/modules_testdata/Mus_musculus.anno.feature_metadata.tsv")
+                input[1] = ["gene_id", "gene_name"]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+            )
+        }
+    }
+
+    test("test_tabular_to_gsea_chip - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.fromPath("https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/differentialabundance/modules_testdata/Mus_musculus.anno.feature_metadata.tsv")
+                input[1] = ["gene_id", "gene_name"]
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+            )
+        }
+    }
+}