Use nf-validation plugin for parameter and samplesheet validation

CHANGELOG.md

@@ -5,11 +5,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## v3.13.0dev - [date]
 
+### Credits
+
+Special thanks to the following for their contributions to the release:
+
+- [Adam Talbot](https://github.com/adamrtalbot)
+- [Júlia Mir Pedrol](https://github.com/mirpedrol)
+- [Matthias Zepper](https://github.com/MatthiasZepper)
+- [Maxime Garcia](https://github.com/maxulysse)
+
+Thank you to everyone else that has contributed by reporting bugs, enhancements or in any other way, shape or form.
+
 ### Enhancements & fixes
 
 - [PR #1049](https://github.com/nf-core/rnaseq/pull/1049) - Display a warning when `--extra_star_align_args` are used with `--aligner star_rsem`
 - [PR #1051](https://github.com/nf-core/rnaseq/pull/1051) - Remove `public_aws_ecr` profile
 - [PR #1054](https://github.com/nf-core/rnaseq/pull/1054) - Template update to nf-core/tools v2.9
+- [PR #1058](https://github.com/nf-core/rnaseq/pull/1058) - Use `nf-validation` plugin for parameter and samplesheet validation
 
 ## [[3.12.0](https://github.com/nf-core/rnaseq/releases/tag/3.12.0)] - 2023-06-02
 

assets/schema_input.json

@@ -10,30 +10,35 @@
             "sample": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "errorMessage": "Sample name must be provided and cannot contain spaces",
+                "meta": ["id"]
             },
             "fastq_1": {
                 "type": "string",
+                "format": "file-path",
+                "exists": true,
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
                 "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
             "fastq_2": {
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+                "type": "string",
+                "format": "file-path",
+                "exists": true,
                 "anyOf": [
                     {
-                        "type": "string",
                         "pattern": "^\\S+\\.f(ast)?q\\.gz$"
                     },
                     {
-                        "type": "string",
                         "maxLength": 0
                     }
                 ]
             },
             "strandedness": {
                 "type": "string",
-                "errorMessage": "Strandedness must be provided and be one of 'forward', 'reverse' or 'unstranded'",
-                "enum": ["forward", "reverse", "unstranded"]
+                "errorMessage": "Strandedness must be provided and be one of 'auto', 'forward', 'reverse' or 'unstranded'",
+                "enum": ["forward", "reverse", "unstranded", "auto"],
+                "meta": ["strandedness"]
             }
         },
         "required": ["sample", "fastq_1", "strandedness"]

conf/modules.config

@@ -23,14 +23,6 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: 'SAMPLESHEET_CHECK' {
-        publishDir = [
-            path: { "${params.outdir}/pipeline_info" },
-            mode: params.publish_dir_mode,
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
     withName: 'CUSTOM_DUMPSOFTWAREVERSIONS' {
         publishDir = [
             path: { "${params.outdir}/pipeline_info" },

lib/WorkflowMain.groovy

@@ -44,11 +44,6 @@ class WorkflowMain {
 
         // Check AWS batch settings
         NfcoreTemplate.awsBatch(workflow, params)
-
-        // Check input has been provided
-        if (!params.input) {
-            Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'")
-        }
     }
 
     //

lib/WorkflowRnaseq.groovy

@@ -11,14 +11,9 @@ class WorkflowRnaseq {
     //
     // Check and validate parameters
     //
-    public static void initialise(params, log, valid_params) {
+    public static void initialise(params, log) {
         genomeExistsError(params, log)
 
-
-        if (!params.fasta) {
-            Nextflow.error("Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file.")
-        }
-
         if (!params.gtf && !params.gff) {
             Nextflow.error("No GTF or GFF3 annotation specified! The pipeline requires at least one of these files.")
         }
@@ -54,27 +49,13 @@ class WorkflowRnaseq {
             }
         }
 
-        if (!params.skip_trimming) {
-            if (!valid_params['trimmers'].contains(params.trimmer)) {
-                Nextflow.error("Invalid option: '${params.trimmer}'. Valid options for '--trimmer': ${valid_params['trimmers'].join(', ')}.")
-            }
-        }
-
-        if (!params.skip_alignment) {
-            if (!valid_params['aligners'].contains(params.aligner)) {
-                Nextflow.error("Invalid option: '${params.aligner}'. Valid options for '--aligner': ${valid_params['aligners'].join(', ')}.")
-            }
-        } else {
+        if (params.skip_alignment) {
             skipAlignmentWarn(log)
         }
 
         if (!params.skip_pseudo_alignment && params.pseudo_aligner) {
-            if (!valid_params['pseudoaligners'].contains(params.pseudo_aligner)) {
-                Nextflow.error("Invalid option: '${params.pseudo_aligner}'. Valid options for '--pseudo_aligner': ${valid_params['pseudoaligners'].join(', ')}.")
-            } else {
-                if (!(params.salmon_index || params.transcript_fasta || (params.fasta && (params.gtf || params.gff)))) {
-                    Nextflow.error("To use `--pseudo_aligner 'salmon'`, you must provide either --salmon_index or --transcript_fasta or both --fasta and --gtf / --gff.")
-                }
+            if (!(params.salmon_index || params.transcript_fasta || (params.fasta && (params.gtf || params.gff)))) {
+                Nextflow.error("To use `--pseudo_aligner 'salmon'`, you must provide either --salmon_index or --transcript_fasta or both --fasta and --gtf / --gff.")
             }
         }
 
@@ -109,12 +90,34 @@ class WorkflowRnaseq {
         }
 
         // Check which RSeQC modules we are running
+        def valid_rseqc_modules = ['bam_stat', 'inner_distance', 'infer_experiment', 'junction_annotation', 'junction_saturation', 'read_distribution', 'read_duplication', 'tin']
         def rseqc_modules = params.rseqc_modules ? params.rseqc_modules.split(',').collect{ it.trim().toLowerCase() } : []
-        if ((valid_params['rseqc_modules'] + rseqc_modules).unique().size() != valid_params['rseqc_modules'].size()) {
-            Nextflow.error("Invalid option: ${params.rseqc_modules}. Valid options for '--rseqc_modules': ${valid_params['rseqc_modules'].join(', ')}")
+        if ((valid_rseqc_modules + rseqc_modules).unique().size() != valid_rseqc_modules.size()) {
+            Nextflow.error("Invalid option: ${params.rseqc_modules}. Valid options for '--rseqc_modules': ${valid_rseqc_modules.join(', ')}")
         }
     }
 
+    //
+    // Function to validate channels from input samplesheet
+    //
+    public static ArrayList validateInput(input) {
+        def (metas, fastqs) = input[1..2]
+
+        // Check that multiple runs of the same sample are of the same strandedness
+        def strandedness_ok = metas.collect{ it.strandedness }.unique().size == 1
+        if (!strandedness_ok) {
+            Nextflow.error("Please check input samplesheet -> Multiple runs of a sample must have the same strandedness!: ${metas[0].id}")
+        }
+
+        // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end
+        def endedness_ok = metas.collect{ it.single_end }.unique().size == 1
+        if (!endedness_ok) {
+            Nextflow.error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}")
+        }
+
+        return [ metas[0], fastqs ]
+    }
+
     //
     // Function to check whether biotype field exists in GTF file
     //