Merge pull request #826 from nf-core/dev

Release PR for 2.4.2 patch

.github/workflows/ci.yml

@@ -37,13 +37,13 @@ jobs:
 
       - name: Build new docker image
         if: env.MATCHED_FILES
-        run: docker build --no-cache . -t nfcore/eager:2.4.1
+        run: docker build --no-cache . -t nfcore/eager:2.4.2
 
       - name: Pull docker image
         if: ${{ !env.MATCHED_FILES }}
         run: |
           docker pull nfcore/eager:dev
-          docker tag nfcore/eager:dev nfcore/eager:2.4.1
+          docker tag nfcore/eager:dev nfcore/eager:2.4.2
 
       - name: Install Nextflow
         env:

CHANGELOG.md

@@ -3,6 +3,20 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [2.4.2] - 2022-01-24
+
+### `Added`
+
+### `Fixed`
+
+- [#824](https://github.com/nf-core/eager/issues/824) Fixes large memory footprint of bedtools coverage calculation.
+- [#822](https://github.com/nf-core/eager/issues/822) Fixed post-adapterremoval trimmed files not being lane-merged and included in downstream analyses
+- Fixed a couple of software version reporting commands
+
+### `Dependencies`
+
+### `Deprecated`
+
 ## [2.4.1] - 2021-11-30
 
 ### `Added`

Dockerfile

@@ -7,7 +7,7 @@ COPY environment.yml /
 RUN conda env create --quiet -f /environment.yml && conda clean -a
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-eager-2.4.1/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-eager-2.4.2/bin:$PATH
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-eager-2.4.1 > nf-core-eager-2.4.1.yml
+RUN conda env export --name nf-core-eager-2.4.2 > nf-core-eager-2.4.2.yml

README.md

@@ -171,9 +171,10 @@ Those who have provided conceptual guidance, suggestions, bug reports etc.
 * [Işın Altınkaya](https://github.com/isinaltinkaya)
 * [Johan Nylander](https://github.com/nylander)
 * [Katerine Eaton](https://github.com/ktmeaton)
-* [Katrin Nägele](https://github.com/KathrinNaegele)
+* [Kathrin Nägele](https://github.com/KathrinNaegele)
 * [Luc Venturini](https://github.com/lucventurini)
 * [Marcel Keller](https://github.com/marcel-keller)
+* [Megan Michel](https://github.com/meganemichel)
 * [Pierre Lindenbaum](https://github.com/lindenb)
 * [Pontus Skoglund](https://github.com/pontussk)
 * [Raphael Eisenhofer](https://github.com/EisenRa)

bin/scrape_software_versions.py

@@ -9,13 +9,13 @@
     "FastQC": ["v_fastqc.txt", r"FastQC v(\S+)"],
     "MultiQC": ["v_multiqc.txt", r"multiqc, version (\S+)"],
     'AdapterRemoval':['v_adapterremoval.txt', r"AdapterRemoval ver. (\S+)"],
-    'Picard MarkDuplicates': ['v_markduplicates.txt', r"(\S+)"],
+    'Picard MarkDuplicates': ['v_markduplicates.txt', r"Version:(\S+)"],
     'Samtools': ['v_samtools.txt', r"samtools (\S+)"],
     'Preseq': ['v_preseq.txt', r"Version: (\S+)"],
     'BWA': ['v_bwa.txt', r"Version: (\S+)"], 
     'Bowtie2': ['v_bowtie2.txt', r"bowtie2-([0-9]+\.[0-9]+\.[0-9]+) -fdebug"],
     'Qualimap': ['v_qualimap.txt', r"QualiMap v.(\S+)"],
-    'GATK HaplotypeCaller': ['v_gatk.txt', r" v(\S+)"],
+    'GATK HaplotypeCaller': ['v_gatk.txt', r"The Genome Analysis Toolkit \(GATK\) v(\S+)"],
     'GATK UnifiedGenotyper': ['v_gatk3.txt', r"(\S+)"],
     'bamUtil' : ['v_bamutil.txt', r"Version: (\S+);"],
     'fastP': ['v_fastp.txt', r"([\d\.]+)"],

environment.yml

@@ -1,6 +1,6 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
-name: nf-core-eager-2.4.1
+name: nf-core-eager-2.4.2
 channels:
   - conda-forge
   - bioconda

lib/NfcoreSchema.groovy

@@ -259,7 +259,7 @@ class NfcoreSchema {
         return new_params
     }
 
-    /*
+     /*
      * This method tries to read a JSON params file
      */
     private static LinkedHashMap params_load(String json_schema) {

main.nf

@@ -1039,8 +1039,7 @@ if ( params.skip_collapse ){
 
 // Inline barcode removal bypass when not running it 
 if (params.run_post_ar_trimming) {
-    ch_adapterremoval_for_skip_post_ar_trimming
-        .dump(tag: "inline_removal_bypass")
+    ch_post_ar_trimming_for_lanemerge
         .into { ch_inlinebarcoderemoval_for_fastqc_after_clipping; ch_inlinebarcoderemoval_for_lanemerge; } 
 } else {
     ch_adapterremoval_for_skip_post_ar_trimming
@@ -2055,8 +2054,12 @@ process bedtools {
 
   script:
   """
-  bedtools coverage -nonamecheck -a ${anno_file} -b $bam | pigz -p ${task.cpus - 1} > "${bam.baseName}".breadth.gz
-  bedtools coverage -nonamecheck -a ${anno_file} -b $bam -mean | pigz -p ${task.cpus - 1} > "${bam.baseName}".depth.gz
+  ## Create genome file from bam header
+  samtools view -H ${bam} | grep '@SQ' | sed 's#@SQ\tSN:\\|LN:##g' > genome.txt
+  
+  ##  Run bedtools
+  bedtools coverage -nonamecheck -g genome.txt -sorted -a ${anno_file} -b ${bam} | pigz -p ${task.cpus - 1} > "${bam.baseName}".breadth.gz
+  bedtools coverage -nonamecheck -g genome.txt -sorted -a ${anno_file} -b ${bam} -mean | pigz -p ${task.cpus - 1} > "${bam.baseName}".depth.gz
   """
 }
 
@@ -3085,7 +3088,7 @@ process get_software_versions {
     ( exec 7>&1; picard MarkDuplicates --version 2>&1 >&7 | grep -v '/' >&2 ) 2> v_markduplicates.txt || true
     qualimap --version &> v_qualimap.txt 2>&1 || true
     preseq &> v_preseq.txt 2>&1 || true
-    gatk --version 2>&1 | head -n 1 > v_gatk.txt 2>&1 || true
+    gatk --version 2>&1 | grep '(GATK)' > v_gatk.txt 2>&1 || true
     gatk3 --version 2>&1 | head -n 1 > v_gatk3.txt 2>&1 || true
     freebayes --version &> v_freebayes.txt 2>&1 || true
     bedtools --version &> v_bedtools.txt 2>&1 || true

nextflow.config

@@ -284,7 +284,7 @@ params {
 
 // Container slug. Stable releases should specify release tag!
 // Developmental code should specify :dev
-process.container = 'nfcore/eager:2.4.1'
+process.container = 'nfcore/eager:2.4.2'
 
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
@@ -414,7 +414,7 @@ manifest {
   description = 'A fully reproducible and state-of-the-art ancient DNA analysis pipeline'
   mainScript = 'main.nf'
   nextflowVersion = '>=20.07.1'
-  version = '2.4.1'
+  version = '2.4.2'
 }
 
 // Function to ensure that resource requirements don't go beyond