Merge pull request #317 from christopher-mohr/fix_bowtie_index_issue

Fix bowtie index issue

.github/workflows/ci.yml

@@ -30,6 +30,7 @@ jobs:
           - "test"
           - "test_no_genome"
           - "test_umi"
+          - "test_index"
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v4

conf/test_index.config

@@ -0,0 +1,35 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/smrnaseq -profile test_index,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test index profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function with bowtie index'
+
+    // 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://github.com/nf-core/test-datasets/raw/smrnaseq/samplesheet/v2.0/samplesheet.csv'
+    fasta            = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/genome.fa'
+    bowtie_index     = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/bowtie_index.tar.gz'
+
+    mirtrace_species         = 'hsa'
+    protocol                 = 'illumina'
+    skip_mirdeep             = true
+    save_merged              = false
+    save_aligned_mirna_quant = false
+
+    cleanup                  = true //Otherwise tests dont run through properly.
+}

conf/test_no_genome.config

@@ -21,9 +21,9 @@ params {
 
     // Input data
     input            = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/samplesheet/v2.0/samplesheet.csv'
-    mature           = 'https://github.com/nf-core/test-datasets/raw/smrnaseq-better-input/reference/mature.fa'
-    hairpin          = 'https://github.com/nf-core/test-datasets/raw/smrnaseq-better-input/reference/hairpin.fa'
-    mirna_gtf        = 'https://github.com/nf-core/test-datasets/raw/smrnaseq-better-input/reference/hsa.gff3'
+    mature           = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/mature.fa'
+    hairpin          = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/hairpin.fa'
+    mirna_gtf        = 'https://github.com/nf-core/test-datasets/raw/smrnaseq/reference/hsa.gff3'
     mirtrace_species = 'hsa'
     skip_mirdeep     = true
     protocol         = 'illumina'

modules.json

@@ -69,6 +69,11 @@
                         "branch": "master",
                         "git_sha": "9e56d7a647fbf6f7e45ef123bc916ad66b6f7c9d",
                         "installed_by": ["fastq_fastqc_umitools_fastp", "modules"]
+                    },
+                    "untarfiles": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
                     }
                 }
             },

nextflow.config

@@ -233,6 +233,7 @@ profiles {
     test_umi       { includeConfig 'conf/test_umi.config' }
     test_no_genome { includeConfig 'conf/test_no_genome.config' }
     test_full      { includeConfig 'conf/test_full.config' }
+    test_index     { includeConfig 'conf/test_index.config' }
 }
 
 // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile

workflows/smrnaseq.nf

@@ -68,6 +68,7 @@ if (!params.mirgenedb) {
 include { INPUT_CHECK                               } from '../subworkflows/local/input_check'
 include { FASTQ_FASTQC_UMITOOLS_FASTP               } from '../subworkflows/nf-core/fastq_fastqc_umitools_fastp'
 include { FASTP as FASTP_LENGTH_FILTER              } from '../modules/nf-core/fastp'
+include { UNTARFILES as UNTAR_BOWTIE_INDEX          } from '../modules/nf-core/untarfiles'
 include { CONTAMINANT_FILTER                        } from '../subworkflows/local/contaminant_filter'
 include { MIRNA_QUANT                               } from '../subworkflows/local/mirna_quant'
 include { GENOME_QUANT                              } from '../subworkflows/local/genome_quant'
@@ -154,7 +155,7 @@ workflow SMRNASEQ {
     )
     ch_versions = ch_versions.mix(FASTQ_FASTQC_UMITOOLS_FASTP.out.versions)
 
-    ch_fasta = params.fasta ? file(params.fasta): []
+    ch_fasta = params.fasta ? file(params.fasta) : []
     ch_reads_for_mirna = FASTQ_FASTQC_UMITOOLS_FASTP.out.reads
 
     // even if bowtie index is specified, there still needs to be a fasta.
@@ -163,7 +164,13 @@ workflow SMRNASEQ {
         //Prepare bowtie index, unless specified
         //This needs to be done here as the index is used by GENOME_QUANT
         if(params.bowtie_index) {
-            ch_bowtie_index  = Channel.fromPath("${index}**ebwt", checkIfExists: true).ifEmpty { error "Bowtie1 index directory not found: ${index}" }
+            ch_fasta = Channel.fromPath(params.fasta)
+            if (params.bowtie_index.endsWith(".tar.gz")) {
+                UNTAR_BOWTIE_INDEX ( [ [], params.bowtie_index ]).files.map { it[1] }.set {ch_bowtie_index}
+                ch_versions  = ch_versions.mix(UNTAR_BOWTIE_INDEX.out.versions)
+            } else {
+                Channel.fromPath("${params.bowtie_index}**ebwt", checkIfExists: true).ifEmpty{ error "Bowtie1 index directory not found: ${params.bowtie_index}" }.filter { it != null }.set { ch_bowtie_index }
+            }
         } else {
             INDEX_GENOME ( [ [:], ch_fasta ] )
             ch_versions = ch_versions.mix(INDEX_GENOME.out.versions)