Merge pull request #382 from nf-core/issue_370

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

@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#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
 

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"

nextflow_schema.json

@@ -42,7 +42,7 @@
                     "type": "string",
                     "description": "A CSV file describing sample contrasts",
                     "help_text": "This file is used to define groups of samples from 'input' to compare.  It must contain at least the columns 'variable', 'reference', 'target' and 'blocking', where 'variable' is a column in the input sample sheet, 'reference' and 'target' are values in that column, and blocking is a colon-separated list of additional 'blocking' variables (can be an empty string)",
-                    "pattern": "^\\S+\\.(csv|tsv)$",
+                    "pattern": "^\\S+\\.(yaml|yml|csv)$",
                     "format": "file-path",
                     "mimetype": "text/csv",
                     "fa_icon": "fas fa-adjust"

tests/test.nf.test

@@ -34,4 +34,34 @@ nextflow_pipeline {
                 )
         }
     }
+
+    test("Test profile with yaml contrasts") {
+
+        when {
+            params {
+                outdir        = "$outputDir"
+                contrasts     = "https://github.com/nf-core/test-datasets/raw/refs/heads/differentialabundance/testdata/SRP254919.contrasts.yaml"
+            }
+        }
+
+        then {
+            // stable_name: All files + folders in ${params.outdir}/ with a stable name
+            def stable_name = getAllFilesFromDir(params.outdir, relative: true, includeDir: true, ignore: ['pipeline_info/*.{html,json,txt}'])
+            // stable_path: All files in ${params.outdir}/ with stable content
+            def stable_path = getAllFilesFromDir(params.outdir, ignoreFile: 'tests/.nftignore')
+            assertAll(
+                { assert workflow.success},
+                { assert snapshot(
+                    // Number of successful tasks
+                    workflow.trace.succeeded().size(),
+                    // pipeline versions.yml file for multiqc from which Nextflow version is removed because we tests pipelines on multiple Nextflow versions
+                    removeNextflowVersion("$outputDir/pipeline_info/collated_versions.yml"),
+                    // All stable path name, with a relative path
+                    stable_name,
+                    // All files with stable contents
+                    stable_path
+                ).match() }
+                )
+        }
+    }
 }