Merge branch 'dev' into start-qc

Author: jfy133

CHANGELOG.md

@@ -8,10 +8,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - [#290](https://github.com/nf-core/funcscan/pull/290) Merged pipeline template of nf-core/tools version 2.9, updated references. (by @jfy133)
+- [#285](https://github.com/nf-core/funcscan/pull/285) Use nf-validation for samplesheet checking and added support for `fna.gz` input FASTA files (by @louperelo, @mirpedrol, @jfy133)
+- [#295](https://github.com/nf-core/funcscan/pull/295) Add Prokka to MultiQC output (by @louperelo)
 
 ### `Fixed`
 
-- [#296](https://github.com/nf-core/funcscan/pull/296) Added check for empty annotation files prior going into screening. (❤️ to @alexhbnr for requesting, added by @jfy133)
+- [#296](https://github.com/nf-core/funcscan/pull/296) Fixed empty output when saving prodigal annotations. (reported by @louperelo, fix by @jasmezz)
+- [#297](https://github.com/nf-core/funcscan/pull/297) Added check for empty annotation files prior going into screening. (❤️ to @alexhbnr for requesting, added by @jfy133)
 
 ### `Dependencies`
 

assets/multiqc_config.yml

@@ -15,3 +15,6 @@ export_plots: true
 custom_logo: "nf-core-funcscan_logo_flat_light.png"
 custom_logo_url: https://nf-co.re/funcscan
 custom_logo_title: "nf-core/funcscan"
+
+## Tool specific configuration
+prokka_fn_snames: True

assets/schema_input.json

@@ -10,27 +10,19 @@
             "sample": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "errorMessage": "Sample name must be provided and cannot contain spaces",
+                "meta": ["id"],
+                "unique": true
             },
-            "fastq_1": {
+            "fasta": {
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "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$"
-                    },
-                    {
-                        "type": "string",
-                        "maxLength": 0
-                    }
-                ]
+                "format": "file-path",
+                "exists": true,
+                "pattern": "^\\S+\\.f(ast|n)?a\\.gz$",
+                "errorMessage": "Fasta file for reads must be provided, cannot contain spaces and must have extension '.fa.gz', '.fna.gz' or '.fasta.gz'",
+                "unique": true
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "fasta"]
     }
 }

bin/check_samplesheet.py

@@ -18,14 +18,6 @@ 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" },
@@ -57,7 +49,7 @@ process {
             enabled: false,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
-        ext.prefix = { "${meta.it}.fa" }
+        ext.prefix = { "${meta.id}.fa" }
     }
 
     withName: PROKKA {

conf/modules.config

@@ -0,0 +1,33 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Although in this case we turn everything off
+
+    Use as follows:
+        nextflow run nf-core/funcscan -profile test,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test nothing profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input                = 'https://raw.githubusercontent.com/nf-core/test-datasets/funcscan/samplesheet.csv'
+    amp_hmmsearch_models = 'https://raw.githubusercontent.com/nf-core/test-datasets/funcscan/hmms/mybacteriocin.hmm'
+
+    annotation_tool         = 'prodigal'
+
+    run_arg_screening       = false
+    run_amp_screening       = false
+    run_bgc_screening       = false
+}

conf/test_nothing.config

@@ -19,7 +19,6 @@ class WorkflowMain {
             "  https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md"
     }
 
-
     //
     // Validate parameters and print summary to screen
     //

lib/WorkflowMain.groovy

@@ -16,7 +16,7 @@ params {
     genome                     = null
     igenomes_base              = 's3://ngi-igenomes/igenomes'
     igenomes_ignore            = false
-    
+
 
     // Annotation options
     annotation_tool                         = 'pyrodigal'
@@ -329,6 +329,7 @@ profiles {
     test_bgc     { includeConfig 'conf/test_bgc.config'     }
     test_full    { includeConfig 'conf/test_full.config'    }
     test_deeparg { includeConfig 'conf/test_deeparg.config' }
+    test_nothing { includeConfig 'conf/test_nothing.config' }
 }
 
 // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile

modules/local/samplesheet_check.nf

@@ -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 sample names and paths to corresponding FASTA files.",
                     "help_text": "Before running the pipeline, you will need to create a design file with information about the samples to be scanned by nf-core/funcscan, containing `sample name` and `path/to/your/contigs.fasta`. Use this parameter to specify its location. It has to be a comma-separated file with 2 columns, and a header row (`sample, fasta`). See [usage docs](https://nf-co.re/funcscan/usage#samplesheet-input).",
                     "fa_icon": "fas fa-file-csv"