Merge pull request #280 from nf-core/dev

Patch Release PR 2.2.3

Author: apeltzer

CHANGELOG.md

@@ -3,6 +3,10 @@
 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).
 
+## [v2.2.3](https://github.com/nf-core/smrnaseq/releases/tag/2.2.3) - 2023-09-06
+
+- [[#271]](https://github.com/nf-core/smrnaseq/issues/271) - Bugfix for parsing hairpin and mature fasta files
+
 ## [v2.2.2](https://github.com/nf-core/smrnaseq/releases/tag/2.2.2) - 2023-09-04
 
 - [[#253]](https://github.com/nf-core/smrnaseq/pull/253) - Remove globs from process alias when using ECR containers

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/smrnaseq/2.2.2" target="_blank">nf-core/smrnaseq</a>
+  This report has been generated by the <a href="https://github.com/nf-core/smrnaseq/2.2.3" target="_blank">nf-core/smrnaseq</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/smrnaseq/2.2.2/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/smrnaseq/2.2.3/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-smrnaseq-methods-description":
     order: -1000

conf/test.config

@@ -23,9 +23,9 @@ params {
 
     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'
-    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'
+    mature           = 'https://mirbase.org/download/CURRENT/mature.fa'
+    hairpin          = 'https://mirbase.org/download/CURRENT/hairpin.fa'
+    mirna_gtf        = 'https://mirbase.org/download/hsa.gff3'
     mirtrace_species = 'hsa'
     protocol         = 'illumina'
     skip_mirdeep     = true

modules/local/parse_fasta_mirna.nf

@@ -25,10 +25,9 @@ process PARSE_FASTA_MIRNA {
         gunzip -f \$FASTA
         FASTA=\${FASTA%%.gz}
     fi
+    sed 's/&gt;/>/g' \$FASTA | sed 's#<br>#\\n#g' | sed 's#</p>##g' | sed 's#<p>##g' > \${FASTA}_html_cleaned.fa
     # Remove spaces from miRBase FASTA files
-    # sed -i 's, ,_,g' \$FASTA
-    sed '#^[^>]#s#[^AUGCaugc]#N#g' \$FASTA > \${FASTA}_parsed.fa
-    # TODO perl -ane 's/[ybkmrsw]/N/ig;print;' \${FASTA}_parsed_tmp.fa > \${FASTA}_parsed.fa
+    sed '#^[^>]#s#[^AUGCaugc]#N#g' \${FASTA}_html_cleaned.fa > \${FASTA}_parsed.fa
 
     sed -i 's#\s.*##' \${FASTA}_parsed.fa
     seqkit grep -r --pattern \".*${filter_species}-.*\" \${FASTA}_parsed.fa > \${FASTA}_sps.fa

nextflow.config

@@ -272,7 +272,7 @@ manifest {
     description     = """Small RNA-Seq Best Practice Analysis Pipeline."""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version = '2.2.2'
+    version = '2.2.3'
     doi             = ''
 }