Merge pull request #9 from CenterForMedicalGeneticsGhent/dev

Release PR v1.1.0

.github/CONTRIBUTING.md

@@ -110,4 +110,3 @@ To get started:
 Devcontainer specs:
 
 - [DevContainer config](.devcontainer/devcontainer.json)
-- [Dockerfile](.devcontainer/Dockerfile)

.prettierignore

@@ -10,3 +10,4 @@ testing/
 testing*
 *.pyc
 bin/
+.nf-test/

CHANGELOG.md

@@ -3,6 +3,12 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.1.0 - Naive Junior - [19 June 2023]
+
+## New features
+
+1. Added a new parameter `--bin_sizes` that takes a comma-delimited list of bin sizes to create references for. This will make it possible to create references for multiple bin sizes at once.
+
 ## v1.0.1 - Helpful Apprentice - [19 June 2023]
 
 ### New features

conf/modules.config

@@ -17,6 +17,8 @@ process {
     ]
 
     withName: WISECONDORX_NEWREF {
+        ext.prefix = {"${meta.id}_${meta.bin_size as Integer > 1000 ? meta.bin_size as Integer/1000 : meta.bin_size}${meta.bin_size as Integer > 1000 ? "k" : ""}bp"}
+        ext.args = { "--binsize ${meta.bin_size}" }
         publishDir = [
             enabled: true,
             path: { "${params.outdir}" },

conf/test.config

@@ -21,6 +21,8 @@ params {
 
     genomes_ignore = true
 
+    bin_sizes       = "10000,5"
+
     fasta           = params.test_data["homo_sapiens"]["genome"]["genome_fasta"]
     fai             = null //params.test_data["homo_sapiens"]["genome"]["genome_fasta_fai"]
 

lib/NfcoreTemplate.groovy

@@ -128,7 +128,7 @@ class NfcoreTemplate {
         def email_html    = html_template.toString()
 
         // Render the sendmail template
-        def max_multiqc_email_size = params.max_multiqc_email_size as nextflow.util.MemoryUnit
+        def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit
         def smail_fields           = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ]
         def sf                     = new File("$projectDir/assets/sendmail_template.txt")
         def sendmail_template      = engine.createTemplate(sf).make(smail_fields)

modules.json

@@ -7,12 +7,12 @@
                 "nf-core": {
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
-                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "git_sha": "05c280924b6c768d484c7c443dad5e605c4ff4b4",
                         "installed_by": ["modules"]
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "git_sha": "a6e11ac655e744f7ebc724be669dd568ffdc0e80",
                         "installed_by": ["modules"]
                     },
                     "ngsbits/samplegender": {
@@ -23,7 +23,7 @@
                     },
                     "samtools/faidx": {
                         "branch": "master",
-                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "git_sha": "fd742419940e01ba1c5ecb172c3e32ec840662fe",
                         "installed_by": ["modules"]
                     },
                     "samtools/index": {

nextflow.config

@@ -15,6 +15,7 @@ params {
 
     // Other options
     no_metrics                 = false
+    bin_sizes                  = "1000000,500000,50000,30000,15000,10000,5000,1000"
 
     // References
     genome                     = "GRCh38"
@@ -42,10 +43,9 @@ params {
     help                       = false
     version                    = false
     validate_params            = true
-    show_hidden_params         = false
-    validationSchemaIgnoreParams = 'genomes,test_data,schema_ignore_params'
-    schema_ignore_params       = 'genomes,test_data'
-
+    validationSchemaIgnoreParams     = 'genomes,test_data,igenomes_base'
+    validationShowHiddenParams       = false
+    validate_params                  = true
 
     // Config options
     custom_config_version      = 'master'
@@ -234,7 +234,7 @@ manifest {
     description     = """A nextflow pipeline for creating references for WisecondorX"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=22.10.1'
-    version = '1.0.1'
+    version = '1.1.0'
     doi             = ''
 }
 

nextflow_schema.json

@@ -56,6 +56,11 @@
                 "no_metrics": {
                     "type": "boolean",
                     "description": "Don't create the metrics text file"
+                },
+                "bin_sizes": {
+                    "type": "string",
+                    "description": "A comma-delimited list of bin sizes to use for the analysis",
+                    "default": "1000000,500000,50000,30000,15000,10000,5000,1000"
                 }
             }
         },
@@ -296,17 +301,31 @@
                     "fa_icon": "fas fa-check-square",
                     "hidden": true
                 },
-                "show_hidden_params": {
+                "validationSchemaIgnoreParams": {
+                    "type": "string",
+                    "default": "genomes,test_data",
+                    "hidden": true
+                },
+                "validationShowHiddenParams": {
                     "type": "boolean",
                     "fa_icon": "far fa-eye-slash",
                     "description": "Show all params when using `--help`",
                     "hidden": true,
                     "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
                 },
-                "validationSchemaIgnoreParams": {
-                    "type": "string",
-                    "default": "genomes,test_data,schema_ignore_params",
-                    "hidden": true
+                "validationFailUnrecognisedParams": {
+                    "type": "boolean",
+                    "fa_icon": "far fa-check-circle",
+                    "description": "Validation of parameters fails when an unrecognised parameter is found.",
+                    "hidden": true,
+                    "help_text": "By default, when an unrecognised parameter is found, it returns a warinig."
+                },
+                "validationLenientMode": {
+                    "type": "boolean",
+                    "fa_icon": "far fa-check-circle",
+                    "description": "Validation of parameters in lenient more.",
+                    "hidden": true,
+                    "help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)."
                 }
             }
         }

tests/main.nf.test

@@ -9,12 +9,14 @@ nextflow_pipeline {
         when {
             params {
                 prefix = "test_reference"
+                bin_sizes = "10000,5"
             }
         }
 
         then {
             assert workflow.success
-            assert file("${outputDir}/test_reference.npz").exists()
+            assert file("${outputDir}/test_reference_10kbp.npz").exists()
+            assert file("${outputDir}/test_reference_5bp.npz").exists()
             assert file("${outputDir}/metrics.txt").exists()
             assert file("${outputDir}/multiqc_reports/multiqc_report.html").exists()
         }

workflows/cmgg-wisecondorx.nf

@@ -76,7 +76,10 @@ workflow CMGGWISECONDORX {
         .collect()
 
     if(!params.fai) {
-        SAMTOOLS_FAIDX(ch_fasta)
+        SAMTOOLS_FAIDX(
+            ch_fasta,
+            [[],[]]
+        )
         ch_versions = ch_versions.mix(SAMTOOLS_FAIDX.out.versions)
 
         SAMTOOLS_FAIDX.out.fai
@@ -184,6 +187,11 @@ workflow CMGGWISECONDORX {
             [ new_meta, npz ]
         }
         .groupTuple() // All files should be present here, so no size is needed
+        .combine(params.bin_sizes.split(","))
+        .map { meta, npz, bin_size ->
+            new_meta = meta + [bin_size:bin_size]
+            [ new_meta, npz ]
+        }
         .set { ch_newref_input }
 
     WISECONDORX_NEWREF(ch_newref_input)