Use nf-validation plugin for parameter and samplesheet validation

.nf-core.yml

@@ -2,4 +2,5 @@ repository_type: pipeline
 lint:
   files_unchanged:
     - .github/ISSUE_TEMPLATE/bug_report.yml
+    - pyproject.toml
   multiqc_config: false

CHANGELOG.md

@@ -10,17 +10,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#80](https://github.com/nf-core/proteinfold/pull/80) - Add `accelerator` directive to GPU processes when `params.use_gpu` is true.
 - [#81](https://github.com/nf-core/proteinfold/pull/81) - Support multiline fasta for colabfold multimer predictions.
 - [#89](https://github.com/nf-core/proteinfold/pull/89) - Fix issue with excessive symlinking in the pdb_mmcif database.
-- [#90](https://github.com/nf-core/proteinfold/pull/90) - Update pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8).
-- [#91](https://github.com/nf-core/proteinfold/pull/91) - Update ColabFold version to 1.5.2 and AlphaFold version to 2.3.2
-- [#92](https://github.com/nf-core/proteinfold/pull/92) - Add ESMFold workflow to the pipeline.
+- [PR #91](https://github.com/nf-core/proteinfold/pull/91) - Update ColabFold version to 1.5.2 and AlphaFold version to 2.3.2
+- [PR #92](https://github.com/nf-core/proteinfold/pull/92) - Add ESMFold workflow to the pipeline.
 - Update metro map to include ESMFold workflow.
 - Update modules to remove quay from container url.
 - [nf-core/tools#2286](https://github.com/nf-core/tools/issues/2286) - Set default container registry outside profile scope.
-- [#97](https://github.com/nf-core/proteinfold/pull/97) - Fix issue with uniref30 missing path when using the full BFD database in AlphaFold.
-- [#100](https://github.com/nf-core/proteinfold/pull/100) - Update containers for AlphaFold2 and ColabFold local modules.
-- [#105](https://github.com/nf-core/proteinfold/pull/105) - Update COLABFOLD_BATCH docker container, metro map figure and nextflow schema description.
-- [#106](https://github.com/nf-core/proteinfold/pull/106) - Add `singularity.registry = 'quay.io'` and bump NF version to 23.04.0
-- [#108](https://github.com/nf-core/proteinfold/pull/108) - Fix gunzip error when providing too many files when downloading PDBMMCIF database.
+- [PR #97](https://github.com/nf-core/proteinfold/pull/97) - Fix issue with uniref30 missing path when using the full BFD database in AlphaFold.
+- [PR #100](https://github.com/nf-core/proteinfold/pull/100) - Update containers for AlphaFold2 and ColabFold local modules.
+- [PR #105](https://github.com/nf-core/proteinfold/pull/105) - Update COLABFOLD_BATCH docker container, metro map figure and nextflow schema description.
+- [PR #106](https://github.com/nf-core/proteinfold/pull/106) - Add `singularity.registry = 'quay.io'` and bump NF version to 23.04.0
+- [PR #108](https://github.com/nf-core/proteinfold/pull/108) - Fix gunzip error when providing too many files when downloading PDBMMCIF database.
+- [PR #111](https://github.com/nf-core/proteinfold/pull/111) - Update pipeline template to [nf-core/tools 2.9](https://github.com/nf-core/tools/releases/tag/2.9).
+- [PR #112](https://github.com/nf-core/rnaseq/pull/112) - Use `nf-validation` plugin for parameter and samplesheet validation
 
 ## 1.0.0 - White Silver Reebok
 

assets/schema_input.json

@@ -7,28 +7,18 @@
     "items": {
         "type": "object",
         "properties": {
-            "sample": {
+            "sequence": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "errorMessage": "Sequence name must be provided and cannot contain spaces",
+                "meta": ["id"]
             },
-            "fastq_1": {
+            "fasta": {
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "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'",
-                "anyOf": [
-                    {
-                        "type": "string",
-                        "pattern": "^\\S+\\.f(ast)?q\\.gz$"
-                    },
-                    {
-                        "type": "string",
-                        "maxLength": 0
-                    }
-                ]
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.fa(sta)?$",
+                "errorMessage": "Fasta file must be provided, cannot contain spaces and must have extension '.fa' or '.fasta'"
             }
         },
         "required": ["sequence", "fasta"]

conf/modules.config

@@ -21,14 +21,6 @@ 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/WorkflowAlphafold2.groovy

@@ -10,8 +10,7 @@ class WorkflowAlphafold2 {
     //
     // Check and validate parameters
     //
-    public static void initialise(params, log) {
-    }
+    public static void initialise(params, log) { }
 
     //
     // Get workflow summary for MultiQC

lib/WorkflowColabfold.groovy

@@ -10,8 +10,7 @@ class WorkflowColabfold {
     //
     // Check and validate parameters
     //
-    public static void initialise(params, log) {
-    }
+    public static void initialise(params, log) { }
 
     //
     // Get workflow summary for MultiQC

lib/WorkflowEsmfold.groovy

@@ -10,8 +10,7 @@ class WorkflowEsmfold {
     //
     // Check and validate parameters
     //
-    public static void initialise(params, log) {
-    }
+    public static void initialise(params, log) { }
 
     //
     // Get workflow summary for MultiQC

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'")
-        }
     }
     //
     // Get attribute from genome config file e.g. fasta

modules/local/multifasta_to_singlefasta.nf

@@ -29,7 +29,7 @@ process MULTIFASTA_TO_SINGLEFASTA {
 
     stub:
     """
-    touch input.csv
+    touch ${meta.id}.fasta
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

nextflow.config

@@ -114,7 +114,7 @@ params {
     // Schema validation default options
     validationFailUnrecognisedParams = false
     validationLenientMode            = false
-    validationSchemaIgnoreParams     = 'genomes'
+    validationSchemaIgnoreParams     = ''
     validationShowHiddenParams       = false
     validate_params                  = true
 

nextflow_schema.json

@@ -18,6 +18,7 @@
                     "exists": true,
                     "mimetype": "text/csv",
                     "pattern": "^\\S+\\.csv$",
+                    "schema": "assets/schema_input.json",
                     "description": "Path to comma-separated file containing information about the samples in the experiment.",
                     "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/proteinfold/usage#samplesheet-input).",
                     "fa_icon": "fas fa-file-csv"
@@ -68,6 +69,8 @@
                 },
                 "alphafold2_db": {
                     "type": "string",
+                    "format": "path",
+                    "exists": true,
                     "description": "Specifies the DB and PARAMS path used by 'AlphaFold2' mode",
                     "fa_icon": "fas fa-database"
                 },
@@ -101,6 +104,8 @@
             "properties": {
                 "colabfold_db": {
                     "type": "string",
+                    "format": "path",
+                    "exists": true,
                     "description": "Specifies the PARAMS and DB path used by 'colabfold'  mode",
                     "fa_icon": "fas fa-folder-open"
                 },
@@ -170,6 +175,8 @@
             "properties": {
                 "esmfold_db": {
                     "type": "string",
+                    "format": "path",
+                    "exists": true,
                     "description": "Specifies the PARAMS path used by 'esmfold' mode",
                     "fa_icon": "fas fa-folder-open"
                 },
@@ -570,18 +577,26 @@
                 "multiqc_config": {
                     "type": "string",
                     "format": "file-path",
+                    "exists": true,
+                    "mimetype": "text/plain",
                     "description": "Custom config file to supply to MultiQC.",
                     "fa_icon": "fas fa-cog",
                     "hidden": true
                 },
                 "multiqc_logo": {
                     "type": "string",
+                    "format": "file-path",
+                    "exists": true,
+                    "mimetype": "text/plain",
                     "description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
                     "fa_icon": "fas fa-image",
                     "hidden": true
                 },
                 "multiqc_methods_description": {
                     "type": "string",
+                    "format": "file-path",
+                    "exists": true,
+                    "mimetype": "text/plain",
                     "description": "Custom MultiQC yaml file containing HTML including a methods description.",
                     "fa_icon": "fas fa-cog"
                 },

pyproject.toml

@@ -1,4 +1,4 @@
-# Config file for Python. Mostly used to configure linting of bin/check_samplesheet.py with Black.
+# Config file for Python. Mostly used to configure linting of bin/*.py with Black.
 # Should be kept the same as nf-core/tools to avoid fighting with template synchronisation.
 [tool.black]
 line-length = 120

workflows/alphafold2.nf

@@ -4,7 +4,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation'
+include { paramsSummaryLog; paramsSummaryMap; fromSamplesheet } from 'plugin/nf-validation'
 
 def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs)
 def citation = '\n' + WorkflowMain.citation(workflow) + '\n'
@@ -16,26 +16,16 @@ log.info logo + paramsSummaryLog(workflow) + citation
 // Validate input parameters
 WorkflowAlphafold2.initialise(params, log)
 
-// Check input path parameters to see if they exist
-def checkPathParamList = [
-    params.input,
-    params.alphafold2_db
-]
-for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
-
-// Check mandatory parameters
-if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input file not specified!' }
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     CONFIG FILES
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
 ch_multiqc_config          = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true)
-ch_multiqc_custom_config   = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty()
-ch_multiqc_logo            = params.multiqc_logo   ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty()
-ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
+ch_multiqc_custom_config   = params.multiqc_config ? Channel.fromPath( params.multiqc_config ) : Channel.empty()
+ch_multiqc_logo            = params.multiqc_logo   ? Channel.fromPath( params.multiqc_logo )   : Channel.empty()
+ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true)
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -46,7 +36,6 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil
 //
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
 //
-include { INPUT_CHECK } from '../subworkflows/local/input_check'
 include { PREPARE_ALPHAFOLD2_DBS } from '../subworkflows/local/prepare_alphafold2_dbs'
 
 //
@@ -82,28 +71,22 @@ workflow ALPHAFOLD2 {
     ch_versions = Channel.empty()
 
     //
-    // SUBWORKFLOW: Read in samplesheet, validate and stage input files
+    // Create input channel from input file provided through params.input
     //
-    if (params.alphafold2_model_preset != 'multimer') {
-        INPUT_CHECK (
-            ch_input
-        )
-        .fastas
-        .map {
-            meta, fasta ->
-            [ meta, fasta.splitFasta(file:true) ]
-        }
-        .transpose()
+    Channel
+        .fromSamplesheet("input")
         .set { ch_fasta }
-    } else {
-        INPUT_CHECK (
-            ch_input
-        )
-        .fastas
-        .set { ch_fasta }
-    }
-    ch_versions = ch_versions.mix(INPUT_CHECK.out.versions)
 
+    if (params.alphafold2_model_preset != 'multimer') {
+        ch_fasta
+            .map {
+                meta, fasta ->
+                [ meta, fasta.splitFasta(file:true) ]
+            }
+            .transpose()
+            .set { ch_fasta }
+    } 
+
     //
     // SUBWORKFLOW: Download databases and params for Alphafold2
     //