Merge pull request #281 from nf-core/fix-mirtop-gff

Bugfix release 2.2.4 for mirtop gff issues
nf-core · Oct 23, 2023 · ed3d869 · ed3d869
2 parents 1aeb518 + 4c27e8c
commit ed3d869
Show file tree

Hide file tree

Showing 9 changed files with 22 additions and 18 deletions.
diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
@@ -15,9 +15,6 @@ jobs:
     steps:
       - name: Launch workflow via tower
         uses: seqeralabs/action-tower-launch@v2
-        # TODO nf-core: You can customise AWS full pipeline tests as required
-        # Add full size test data (but still relatively small datasets for few samples)
-        # on the `test_full.config` test runs with only one set of parameters
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}

diff --git a/CHANGELOG.md b/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).
 
+## [v2.2.4](https://github.com/nf-core/smrnaseq/releases/tag/2.2.4) - 2023-09-07
+
+- Update template to 2.10
+- Bugfix for issue with mirdeep2 channels [#289](https://github.com/nf-core/smrnaseq/issues/289)
+- Bugfix for issue with handling malformed GFF3 from mirbase (was forgotten in 2.2.3)
+
 ## [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

diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 # ![nf-core/smrnaseq](docs/images/nf-core-smrnaseq_logo_light.png#gh-light-mode-only) ![nf-core/smrnaseq](docs/images/nf-core-smrnaseq_logo_dark.png#gh-dark-mode-only)
 
 [![GitHub Actions CI Status](https://github.com/nf-core/smrnaseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/smrnaseq/actions?query=workflow%3A%22nf-core+CI%22)
-[![GitHub Actions Linting Status](https://github.com/nf-core/smrnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/smrnaseq/actions?query=workflow%3A%22nf-core+linting%22)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/smrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
+[![GitHub Actions Linting Status](https://github.com/nf-core/smrnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/smrnaseq/actions?query=workflow%3A%22nf-core+linting%22)
 [![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/smrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.3456879-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.3456879)
 [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,9 +1,7 @@
 report_comment: >
-
-  This report has been generated by the <a href="https://github.com/nf-core/smrnaseq/releases/tag/2.2.3" target="_blank">nf-core/smrnaseq</a>
+  This report has been generated by the <a href="https://github.com/nf-core/smrnaseq/releases/tag/dev" 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/2.2.3/docs/output" target="_blank">documentation</a>.
-
+  <a href="https://nf-co.re/smrnaseq/dev/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-smrnaseq-methods-description":
     order: -1000

diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py
@@ -67,8 +67,8 @@ def check_samplesheet(file_in, file_out):
             # Check valid number of columns per row
             if len(lspl) != len(header):
                 print_error(
-                    "Invalid number of columns: found {} columns (header has {})".format(
-                        line_number, len(lspl), len(header)
+                    "Invalid number of columns found - header has {} columns, content has {}. Number of rows {})".format(
+                        len(header), len(lspl), line_number
                     ),
                     f"Line #{line_number+2}",
                     line,

diff --git a/modules/local/mirdeep2_run.nf b/modules/local/mirdeep2_run.nf
@@ -10,10 +10,10 @@ process MIRDEEP2_RUN {
         'biocontainers/mirdeep2:2.0.1.3--hdfd78af_1' }"
 
     input:
-    tuple val(meta2), path(fasta)
+    path(fasta)
     tuple path(reads), path(arf)
-    path hairpin
-    path mature
+    tuple val(meta2), path(hairpin)
+    tuple val(meta2), path(mature)
 
     output:
     path 'result*.{bed,csv,html}', emit: result

diff --git a/modules/local/mirtop_quant.nf b/modules/local/mirtop_quant.nf
@@ -24,9 +24,12 @@ process MIRTOP_QUANT {
     script:
     def filter_species = params.mirgenedb ? params.mirgenedb_species : params.mirtrace_species
     """
-    mirtop gff --hairpin $hairpin --gtf $gtf -o mirtop --sps $filter_species ./bams/*
-    mirtop counts --hairpin $hairpin --gtf $gtf -o mirtop --sps $filter_species --add-extra --gff mirtop/mirtop.gff
-    mirtop export --format isomir --hairpin $hairpin --gtf $gtf --sps $filter_species -o mirtop mirtop/mirtop.gff
+    #Cleanup the GTF if mirbase html form is broken
+    GTF="$gtf"
+    sed 's/&gt;/>/g' \$GTF | sed 's#<br>#\\n#g' | sed 's#</p>##g' | sed 's#<p>##g' | sed -e :a -e '/^\\n*\$/{\$d;N;};/\\n\$/ba' > \${GTF}_html_cleaned.gtf
+    mirtop gff --hairpin $hairpin --gtf \${GTF}_html_cleaned.gtf -o mirtop --sps $filter_species ./bams/*
+    mirtop counts --hairpin $hairpin --gtf \${GTF}_html_cleaned.gtf -o mirtop --sps $filter_species --add-extra --gff mirtop/mirtop.gff
+    mirtop export --format isomir --hairpin $hairpin --gtf \${GTF}_html_cleaned.gtf --sps $filter_species -o mirtop mirtop/mirtop.gff
     mirtop stats mirtop/mirtop.gff --out mirtop/stats
     mv mirtop/stats/mirtop_stats.log mirtop/stats/full_mirtop_stats.log
 

diff --git a/modules/local/parse_fasta_mirna.nf b/modules/local/parse_fasta_mirna.nf
@@ -25,7 +25,7 @@ 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
+    sed 's/&gt;/>/g' \$FASTA | sed 's#<br>#\\n#g' | sed 's#</p>##g' | sed 's#<p>##g' | sed -e :a -e '/^\\n*\$/{\$d;N;};/\\n\$/ba' > \${FASTA}_html_cleaned.fa
     # Remove spaces from miRBase FASTA files
     sed '#^[^>]#s#[^AUGCaugc]#N#g' \${FASTA}_html_cleaned.fa > \${FASTA}_parsed.fa
 

diff --git a/nextflow.config b/nextflow.config
@@ -287,7 +287,7 @@ manifest {
     description     = """Small RNA-Seq Best Practice Analysis Pipeline."""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '2.2.3'
+    version = '2.2.4dev'
     doi             = ''
 }