Merge pull request #16 from avantonder/apha

Apha

CHANGELOG.md

@@ -3,6 +3,18 @@
 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 - [26/10/22]
+
+- Fix masking bug
+- Output Picard MARKDUPLICATES metrics for multiQC
+- Delete unnecessary subworkflows and modules
+- Correct samtools index version from 1.14 to 1.15.1
+- Edit documentation
+- Standardise old modules to current syntax
+- Add skip_alignment option to make alignment creation optional
+- Edit modules.config to output low_quality_pseudogenomes.tsv
+- Update spoligotype database
+
 ## v1.0 - [21/10/22]
 
 First release version of avantonder/bovisanalyzer.

CITATIONS.md

@@ -37,6 +37,8 @@
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [picard-tools](https://broadinstitute.github.io/picard/)
+
 - [Rasusa](https://github.com/mbhall88/rasusa)
   > Hall MB. Rasusa: Randomly subsample sequencing reads to a specified coverage. 2019. doi:10.5281/zenodo.3731394
 

README.md

@@ -30,7 +30,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
     2. Sort and index alignments ([`SAMtools`](https://sourceforge.net/projects/samtools/files/samtools/))
     3. Duplicate read marking ([`picard`](https://broadinstitute.github.io/picard/))
     4. Call and filter variants ([`BCFtools`](http://samtools.github.io/bcftools/bcftools.html))
-    5. Convert filtered bcf to pseudogenome fasta ([`vcf2pseudogenome.py`](https://github.com/nf-core/bactmap/blob/dev/bin/vcf2pseudogenome.py))
+    5. Convert filtered vcf to pseudogenome fasta ([`BCFtools`](http://samtools.github.io/bcftools/bcftools.html))
     6. Mask each pseudogenome with zero-coverage, low coverage and poorly mapped regions ([`BCFtools`](http://samtools.github.io/bcftools/bcftools.html))
     7. Calculate the percentage of the reference mapped in each pseudogenome fasta ([`seqtk`](https://github.com/lh3/seqtk))
 12. Create alignment from pseudogenome by concatenating fasta files having first checked that the sample sequences are high quality([`calculate_fraction_of_non_GATC_bases.py`](https://github.com/nf-core/bactmap/blob/dev/bin/))

assets/multiqc_config.yml

@@ -38,7 +38,7 @@ module_order:
   - picard:
         name: 'METRICS: Picard (raw)'
         anchor: 'picard'
-        info: 'This section of the report shows Picard CollectMultipleMetrics after mapping with BWA.'
+        info: 'This section of the report shows the results of removing duplicate reads with Picard.'
         path_filters:
             - './picard_metrics/*'
   - samtools:

assets/spoligotype_db.tsv

@@ -2218,4 +2218,10 @@
 476773477777200	SB2794 1001111101111110111001111111111111110100000 
 676773677003600	SB2795 1101111101111110111101111110000000111100000 
 676763675737600	SB2796 1101111101111100111101111011110111111100000 
-660773677777600	SB2797 1101100001111110111101111111111111111100000  
+660773677777600	SB2797 1101100001111110111101111111111111111100000
+276773617777600 SB2798 0101111101111110111100011111111111111100000 
+076771777777600 SB2799 0001111101111110011111111111111111111100000 
+276773677775600 SB2800 0101111101111110111101111111111111011100000 
+436733777774600 SB2801 1000111101110110111111111111111111001100000 
+676773177777600 SB2802 1101111101111110110011111111111111111100000 
+676773637777400 SB2803 1101111101111110111100111111111111111000000

conf/modules.config

@@ -267,7 +267,7 @@ process {
         ext.prefix = { "${meta.id}.markduplicates.sorted" }
         publishDir = [
             [
-                path: { "${params.outdir}/variants/picard_metrics" },
+                path: { "${params.outdir}/picard_metrics" },
                 mode: params.publish_dir_mode,
                 pattern: '*metrics.txt'
             ],
@@ -437,7 +437,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/pseudogenomes" },
             mode: params.publish_dir_mode,
-            pattern: '*.fas'
+            pattern: '*.{fas,tsv}'
         ]
     }
 

modules/local/alignpseudogenomes.nf

@@ -1,21 +1,10 @@
-// Import generic module functions
-include { initOptions; saveFiles; getSoftwareName } from './functions'
-
-params.options = [:]
-options        = initOptions(params.options)
-
 process ALIGNPSEUDOGENOMES {
-    label 'process_low'
-    publishDir "${params.outdir}",
-        mode: params.publish_dir_mode,
-        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+    label 'process_medium'
 
     conda (params.enable_conda ? "conda-forge::biopython=1.78" : null)
-    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/biopython:1.78"
-    } else {
-        container "quay.io/biocontainers/biopython:1.78"
-    }
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/biopython:1.78' :
+        'quay.io/biocontainers/biopython:1.78' }"
 
     input:
     path pseudogenomes

modules/local/fastqscanparse.nf

@@ -1,15 +1,10 @@
 process FASTQSCANPARSE {
     label 'process_low'
-    publishDir "${params.outdir}",
-        mode: params.publish_dir_mode,
-        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
 
-    conda (params.enable_conda ? 'conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1' : null)
-    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    } else {
-        container "quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    }
+    conda (params.enable_conda ? "conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' :
+        'quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' }"
 
     input:
     path json

modules/local/krakenparse.nf

@@ -1,21 +1,10 @@
-// Import generic module functions
-include { initOptions; saveFiles; getSoftwareName } from './functions'
-
-params.options = [:]
-options        = initOptions(params.options)
-
 process KRAKENPARSE {
-    label 'process_medium'
-    publishDir "${params.outdir}",
-        mode: params.publish_dir_mode,
-        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
+    label 'process_high'
 
-    conda (params.enable_conda ? 'conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1' : null)
-    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    } else {
-        container "quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    }
+    conda (params.enable_conda ? "conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' :
+        'quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' }"
 
     input:
     path txt

modules/local/read_stats.nf

@@ -1,17 +1,11 @@
 process READ_STATS {
     label 'process_low'
     tag "$meta.id"
-
-    publishDir "${params.outdir}",
-        mode: params.publish_dir_mode,
-        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
-
-    conda (params.enable_conda ? 'conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1' : null)
-    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    } else {
-        container "quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0"
-    }
+
+    conda (params.enable_conda ? "conda-forge::numpy=1.15.2 conda-forge::pandas=0.23.4 conda-forge::scipy=1.2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' :
+        'quay.io/biocontainers/mulled-v2-9adca5a7d3b24119897cfc20386da6c7fa47bdab:77c1885b47edc369aceb4cccf161a549bdac3d4b-0' }"
 
     input:
     tuple val(meta), path(json), path(json), path(depth), path(mapreads)