From 56733ffe0e96caee6904d07e7a13327fa506f835 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 09:35:10 +0200 Subject: [PATCH 01/20] remove unused modules/subworkflows --- modules/local/samplesheet_check.nf | 31 --------------------- subworkflows/local/input_check.nf | 44 ------------------------------ 2 files changed, 75 deletions(-) delete mode 100644 modules/local/samplesheet_check.nf delete mode 100644 subworkflows/local/input_check.nf diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index 7ae3540..0000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,31 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$samplesheet" - label 'process_single' - - conda "conda-forge::python=3.8.3" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'biocontainers/python:3.8.3' }" - - input: - path samplesheet - - output: - path '*.csv' , emit: csv - path "versions.yml", emit: versions - - when: - task.ext.when == null || task.ext.when - - script: // This script is bundled with the pipeline, in nf-core/createpanelrefs/bin/ - """ - check_samplesheet.py \\ - $samplesheet \\ - samplesheet.valid.csv - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - python: \$(python --version | sed 's/Python //g') - END_VERSIONS - """ -} diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf deleted file mode 100644 index 0aecf87..0000000 --- a/subworkflows/local/input_check.nf +++ /dev/null @@ -1,44 +0,0 @@ -// -// Check input samplesheet and get read channels -// - -include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' - -workflow INPUT_CHECK { - take: - samplesheet // file: /path/to/samplesheet.csv - - main: - SAMPLESHEET_CHECK ( samplesheet ) - .csv - .splitCsv ( header:true, sep:',' ) - .map { create_fastq_channel(it) } - .set { reads } - - emit: - reads // channel: [ val(meta), [ reads ] ] - versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ] -} - -// Function to get list of [ meta, [ fastq_1, fastq_2 ] ] -def create_fastq_channel(LinkedHashMap row) { - // create meta map - def meta = [:] - meta.id = row.sample - meta.single_end = row.single_end.toBoolean() - - // add path(s) of the fastq file(s) to the meta map - def fastq_meta = [] - if (!file(row.fastq_1).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}" - } - if (meta.single_end) { - fastq_meta = [ meta, [ file(row.fastq_1) ] ] - } else { - if (!file(row.fastq_2).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}" - } - fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ] - } - return fastq_meta -} From 3e4c7c9797a8f029944fd25b6a52c94693b5131a Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 09:35:45 +0200 Subject: [PATCH 02/20] add cnvkit --- modules.json | 5 ++ modules/nf-core/cnvkit/batch/main.nf | 105 ++++++++++++++++++++++++++ modules/nf-core/cnvkit/batch/meta.yml | 86 +++++++++++++++++++++ 3 files changed, 196 insertions(+) create mode 100644 modules/nf-core/cnvkit/batch/main.nf create mode 100644 modules/nf-core/cnvkit/batch/meta.yml diff --git a/modules.json b/modules.json index fa09921..89ff874 100644 --- a/modules.json +++ b/modules.json @@ -5,6 +5,11 @@ "https://github.com/nf-core/modules.git": { "modules": { "nf-core": { + "cnvkit/batch": { + "branch": "master", + "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220", + "installed_by": ["modules"] + }, "custom/dumpsoftwareversions": { "branch": "master", "git_sha": "76cc4938c1f6ea5c7d83fed1eeffc146787f9543", diff --git a/modules/nf-core/cnvkit/batch/main.nf b/modules/nf-core/cnvkit/batch/main.nf new file mode 100644 index 0000000..1e4d81e --- /dev/null +++ b/modules/nf-core/cnvkit/batch/main.nf @@ -0,0 +1,105 @@ +process CNVKIT_BATCH { + tag "$meta.id" + label 'process_low' + + conda "bioconda::cnvkit=0.9.9 bioconda::samtools=1.16.1" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:3bdd798e4b9aed6d3e1aaa1596c913a3eeb865cb-0' : + 'biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:3bdd798e4b9aed6d3e1aaa1596c913a3eeb865cb-0' }" + + input: + tuple val(meta), path(tumor), path(normal) + path fasta + path fasta_fai + path targets + path reference + val panel_of_normals + + output: + tuple val(meta), path("*.bed"), emit: bed + tuple val(meta), path("*.cnn"), emit: cnn, optional: true + tuple val(meta), path("*.cnr"), emit: cnr, optional: true + tuple val(meta), path("*.cns"), emit: cns, optional: true + tuple val(meta), path("*.pdf"), emit: pdf, optional: true + tuple val(meta), path("*.png"), emit: png, optional: true + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + + def tumor_exists = tumor ? true : false + def normal_exists = normal ? true : false + + // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow + def tumor_cram = tumor_exists && tumor.Extension == "cram" ? true : false + def normal_cram = normal_exists && normal.Extension == "cram" ? true : false + def tumor_bam = tumor_exists && tumor.Extension == "bam" ? true : false + def normal_bam = normal_exists && normal.Extension == "bam" ? true : false + + def tumor_out = tumor_cram ? tumor.BaseName + ".bam" : "${tumor}" + + // tumor_only mode does not need fasta & target + // instead it requires a pre-computed reference.cnn which is built from fasta & target + def (normal_out, normal_args, fasta_args) = ["", "", ""] + def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : "" + + if (normal_exists){ + def normal_prefix = normal.BaseName + normal_out = normal_cram ? "${normal_prefix}" + ".bam" : "${normal}" + fasta_args = fasta ? "--fasta $fasta" : "" + + // germline mode + // normal samples must be input without a flag + // requires flag --normal to be empty [] + if(!tumor_exists){ + tumor_out = "${normal_prefix}" + ".bam" + normal_args = "--normal " + } + // somatic mode + else { + normal_args = normal_prefix ? "--normal $normal_out" : "" + } + } + + // generation of panel of normals + def generate_pon = panel_of_normals ? true : false + + if (generate_pon && !tumor_exists){ + def pon_input = normal.join(' ') + normal_args = "--normal $pon_input" + tumor_out = "" + } + + def target_args = targets ? "--targets $targets" : "" + def reference_args = reference ? "--reference $reference" : "" + + def samtools_cram_convert = '' + samtools_cram_convert += normal_cram ? " samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $normal_out\n" : '' + samtools_cram_convert += normal_cram ? " samtools index $normal_out\n" : '' + samtools_cram_convert += tumor_cram ? " samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out\n" : '' + samtools_cram_convert += tumor_cram ? " samtools index $tumor_out\n" : '' + def versions = normal_cram || tumor_cram ? + "samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')\n cnvkit: \$(cnvkit.py version | sed -e 's/cnvkit v//g')" : + "cnvkit: \$(cnvkit.py version | sed -e 's/cnvkit v//g')" + """ + $samtools_cram_convert + + cnvkit.py \\ + batch \\ + $tumor_out \\ + $normal_args \\ + $fasta_args \\ + $reference_args \\ + $target_args \\ + --processes $task.cpus \\ + $args + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + ${versions} + END_VERSIONS + """ +} diff --git a/modules/nf-core/cnvkit/batch/meta.yml b/modules/nf-core/cnvkit/batch/meta.yml new file mode 100644 index 0000000..3fc00f1 --- /dev/null +++ b/modules/nf-core/cnvkit/batch/meta.yml @@ -0,0 +1,86 @@ +name: cnvkit_batch +description: Copy number variant detection from high-throughput sequencing data +keywords: + - cnvkit + - bam + - fasta + - copy number +tools: + - cnvkit: + description: | + CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data. It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent. + homepage: https://cnvkit.readthedocs.io/en/stable/index.html + documentation: https://cnvkit.readthedocs.io/en/stable/index.html + licence: ["Apache-2.0"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - tumour: + type: file + description: | + Input tumour sample bam file (or cram) + - normal: + type: file + description: | + Input normal sample bam file (or cram) + - fasta: + type: file + description: | + Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided) + - fasta_fai: + type: file + description: | + Input reference genome fasta index (optional, but recommended for cram_input) + - targetfile: + type: file + description: | + Input target bed file + - reference: + type: file + description: | + Input reference cnn-file (only for germline and tumor-only running) +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bed: + type: file + description: File containing genomic regions + pattern: "*.{bed}" + - cnn: + type: file + description: File containing coverage information + pattern: "*.{cnn}" + - cnr: + type: file + description: File containing copy number ratio information + pattern: "*.{cnr}" + - cns: + type: file + description: File containing copy number segment information + pattern: "*.{cns}" + - pdf: + type: file + description: File with plot of copy numbers or segments on chromosomes + pattern: "*.{pdf}" + - png: + type: file + description: File with plot of bin-level log2 coverages and segmentation calls + pattern: "*.{png}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@kaurravneet4123" + - "@KevinMenden" + - "@MaxUlysse" + - "@drpatelh" + - "@fbdtemme" + - "@lassefolkersen" + - "@SusiJo" From fa5b1799c2e90e32de2d5cf732692ac06ae26065 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:20:57 +0200 Subject: [PATCH 03/20] update CHANGELOG --- CHANGELOG.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 92e5780..f1f6bc8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,9 @@ Initial release of nf-core/createpanelrefs, created with the [nf-core](https://n ### `Added` +- `CNVKIT` can be used to create a PON +- Usage of nf-validation + ### `Fixed` ### `Dependencies` From 95806eb5ddbfcb229f2cbbe8f209ba90aea6b66a Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:21:14 +0200 Subject: [PATCH 04/20] update CITATIONS --- CITATIONS.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/CITATIONS.md b/CITATIONS.md index 9b55cf7..7d9a92a 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -10,9 +10,9 @@ ## Pipeline tools -- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) +- [CNVKIT](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004873) - > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online]. Available online https://www.bioinformatics.babraham.ac.uk/projects/fastqc/. + > Talevich E, Shain AH, Botton T, Bastian BC (2016) CNVkit: Genome-Wide Copy Number Detection and Visualization from Targeted DNA Sequencing. PLoS Comput Biol 12(4): e1004873. doi: 10.1371/journal.pcbi.1004873. PubMed PMID: 27100738. PubMed Central PMCID: PMC4839673. - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/) From 623601bf49c018fd226b27813d4e4e6f6d36e7c6 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:21:35 +0200 Subject: [PATCH 05/20] update README --- README.md | 28 ++++++---------------------- 1 file changed, 6 insertions(+), 22 deletions(-) diff --git a/README.md b/README.md index e053d15..70f8911 100644 --- a/README.md +++ b/README.md @@ -12,20 +12,11 @@ ## Introduction -**nf-core/createpanelrefs** is a bioinformatics pipeline that ... - - - - - +**nf-core/createpanelrefs** is a bioinformatics helper pipeline that will help in creating panel of normals and other models. 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) -2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) +2. Build Panel of Normals for [`CNVKIT`](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004873) +3. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) ## Usage @@ -34,9 +25,6 @@ > to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) > with `-profile test` before running the workflow on actual data. - - Now, you can run the pipeline using: - - ```bash nextflow run nf-core/createpanelrefs \ -profile \ @@ -77,6 +61,9 @@ For more details about the output files and reports, please refer to the ## Credits nf-core/createpanelrefs was originally written by @maxulysse. +@marrip contributed in the idea that started it all. +@matthdsm and @FriederikeHanssen contributed in the actual design. +@ramprasadn's interest was the final push that led to the creation. We thank the following people for their extensive assistance in the development of this pipeline: @@ -90,11 +77,8 @@ For further information or help, don't hesitate to get in touch on the [Slack `# ## Citations - - - An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file. You can cite the `nf-core` publication as follows: From 827ec0cd6ed27883d8ed7a017b68a7fbb39dd37b Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:21:48 +0200 Subject: [PATCH 06/20] better igenomes.config --- conf/igenomes.config | 98 +++++++++++++++++++++++++++++--------------- 1 file changed, 65 insertions(+), 33 deletions(-) diff --git a/conf/igenomes.config b/conf/igenomes.config index 3f11437..6464acf 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -11,51 +11,86 @@ params { // illumina iGenomes reference file paths genomes { - 'GRCh37' { - fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" + 'GATK.GRCh37' { + bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/BWAIndex/" + dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz.tbi" + dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.dict" + fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta" + fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta.fai" + intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/intervals/wgs_calling_regions_Sarek.list" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi" + known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz.tbi" + } + 'GATK.GRCh38' { + bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAmem2Index/" + dragmap = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/" + cf_chrom_len = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/Length/Homo_sapiens_assembly38.len" + dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz.tbi" + dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.dict" + fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta" + fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta.fai" + intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/intervals/wgs_calling_regions_noseconds.hg38.bed" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz.tbi" + known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz.tbi" + pon = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz" + pon_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi" + } + 'Ensembl.GRCh37' { + bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" - mito_name = "MT" macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed" + mito_name = "MT" + readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" + star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" } - 'GRCh38' { - fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" + 'NCBI.GRCh38' { + bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" - mito_name = "chrM" macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" + mito_name = "chrM" + star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" } 'CHM13' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" + gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2TCHM13v2.0/GCF_009914755.1_T2TCHM13v2.0_genomic.gff.gz" gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" - gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz" mito_name = "chrM" } 'GRCm38' { - fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed" + bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" + dbsnp = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz.tbi" + dict = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.dict" + fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" + fasta_fai = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa.fai" + gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" + intervals = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/intervals/GRCm38_calling_list.bed" + known_indels = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz.tbi" + macs_gsize = "1.87e9" + mito_name = "MT" + readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" + star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" } 'TAIR10' { fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" @@ -289,7 +324,6 @@ params { bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" mito_name = "chrM" macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" } 'hg19' { fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" @@ -302,7 +336,6 @@ params { readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" mito_name = "chrM" macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg19-blacklist.bed" } 'mm10' { fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" @@ -315,7 +348,6 @@ params { readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" mito_name = "chrM" macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/mm10-blacklist.bed" } 'bosTau8' { fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" From 980a041d0ade4e5451d03d046237e50311db5afa Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:22:04 +0200 Subject: [PATCH 07/20] remove fastqc --- modules/nf-core/fastqc/main.nf | 51 -------------------------------- modules/nf-core/fastqc/meta.yml | 52 --------------------------------- 2 files changed, 103 deletions(-) delete mode 100644 modules/nf-core/fastqc/main.nf delete mode 100644 modules/nf-core/fastqc/meta.yml diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf deleted file mode 100644 index 9ae5838..0000000 --- a/modules/nf-core/fastqc/main.nf +++ /dev/null @@ -1,51 +0,0 @@ -process FASTQC { - tag "$meta.id" - label 'process_medium' - - conda "bioconda::fastqc=0.11.9" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0' : - 'quay.io/biocontainers/fastqc:0.11.9--0' }" - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.html"), emit: html - tuple val(meta), path("*.zip") , emit: zip - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - def prefix = task.ext.prefix ?: "${meta.id}" - // Make list of old name and new name pairs to use for renaming in the bash while loop - def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${prefix}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}.${entry.extension}" ] } - def rename_to = old_new_pairs*.join(' ').join(' ') - def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ') - """ - printf "%s %s\\n" $rename_to | while read old_name new_name; do - [ -f "\${new_name}" ] || ln -s \$old_name \$new_name - done - fastqc $args --threads $task.cpus $renamed_files - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ - - stub: - def prefix = task.ext.prefix ?: "${meta.id}" - """ - touch ${prefix}.html - touch ${prefix}.zip - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ -} diff --git a/modules/nf-core/fastqc/meta.yml b/modules/nf-core/fastqc/meta.yml deleted file mode 100644 index 4da5bb5..0000000 --- a/modules/nf-core/fastqc/meta.yml +++ /dev/null @@ -1,52 +0,0 @@ -name: fastqc -description: Run FastQC on sequenced reads -keywords: - - quality control - - qc - - adapters - - fastq -tools: - - fastqc: - description: | - FastQC gives general quality metrics about your reads. - It provides information about the quality score distribution - across your reads, the per base sequence content (%A/C/G/T). - You get information about adapter contamination and other - overrepresented sequences. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ - documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ - licence: ["GPL-2.0-only"] -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - html: - type: file - description: FastQC report - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive - pattern: "*_{fastqc.zip}" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" From 8f90e32baf177563590ad8925db3366839bf25ea Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:22:33 +0200 Subject: [PATCH 08/20] update workflow --- workflows/createpanelrefs.nf | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) diff --git a/workflows/createpanelrefs.nf b/workflows/createpanelrefs.nf index 4ab6d8b..49c553e 100644 --- a/workflows/createpanelrefs.nf +++ b/workflows/createpanelrefs.nf @@ -35,7 +35,6 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil // // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules // -include { INPUT_CHECK } from '../subworkflows/local/input_check' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -46,7 +45,8 @@ include { INPUT_CHECK } from '../subworkflows/local/input_check' // // MODULE: Installed directly from nf-core/modules // -include { FASTQC } from '../modules/nf-core/fastqc/main' + +include { CNVKIT_BATCH } from '../modules/nf-core/cnvkit/batch/main' include { MULTIQC } from '../modules/nf-core/multiqc/main' include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' @@ -63,32 +63,13 @@ workflow CREATEPANELREFS { ch_versions = Channel.empty() - // - // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // - INPUT_CHECK ( - file(params.input) - ) - ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) - // TODO: OPTIONAL, you can use nf-validation plugin to create an input channel from the samplesheet with Channel.fromSamplesheet("input") - // See the documentation https://nextflow-io.github.io/nf-validation/samplesheets/fromSamplesheet/ - // ! There is currently no tooling to help you write a sample sheet schema - - // - // MODULE: Run FastQC - // - FASTQC ( - INPUT_CHECK.out.reads - ) - ch_versions = ch_versions.mix(FASTQC.out.versions.first()) + CUSTOM_DUMPSOFTWAREVERSIONS ( ch_versions.unique().collectFile(name: 'collated_versions.yml') ) - // - // MODULE: MultiQC - // + // MULTIQC workflow_summary = WorkflowCreatepanelrefs.paramsSummaryMultiqc(workflow, summary_params) ch_workflow_summary = Channel.value(workflow_summary) From 871d63da3e731709dab6834d611ae33674a4ff45 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:22:48 +0200 Subject: [PATCH 09/20] update samplesheet schema --- assets/schema_input.json | 60 ++++++++++++++++++++++++++++++++++------ 1 file changed, 51 insertions(+), 9 deletions(-) diff --git a/assets/schema_input.json b/assets/schema_input.json index 95a560d..2c1a025 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -12,25 +12,67 @@ "pattern": "^\\S+$", "errorMessage": "Sample name must be provided and cannot contain spaces" }, - "fastq_1": { - "type": "string", - "pattern": "^\\S+\\.f(ast)?q\\.gz$", - "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" + "bam": { + "errorMessage": "BAM file cannot contain spaces and must have extension '.bam'", + "anyOf": [ + { + "type": "string", + "pattern": "^\\S+\\.bam$" + }, + { + "type": "string", + "maxLength": 0 + } + ], + "format": "file-path", + "exists": true + }, + "bai": { + "errorMessage": "BAM index file cannot contain spaces and must have extension '.bai'", + "anyOf": [ + { + "type": "string", + "pattern": "^\\S+\\.bai$" + }, + { + "type": "string", + "maxLength": 0 + } + ], + "format": "file-path", + "exists": true + }, + "cram": { + "errorMessage": "CRAM file cannot contain spaces and must have extension '.cram'", + "anyOf": [ + { + "type": "string", + "pattern": "^\\S+\\.cram$" + }, + { + "type": "string", + "maxLength": 0 + } + ], + "format": "file-path", + "exists": true }, - "fastq_2": { - "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'", + "crai": { + "errorMessage": "CRAM index file cannot contain spaces and must have extension '.crai'", "anyOf": [ { "type": "string", - "pattern": "^\\S+\\.f(ast)?q\\.gz$" + "pattern": "^\\S+\\.crai$" }, { "type": "string", "maxLength": 0 } - ] + ], + "format": "file-path", + "exists": true } }, - "required": ["sample", "fastq_1"] + "required": ["sample"] } } From 15f4570d8c4ed8bceddd2fc5cbdcbe53c3faccb3 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:28:13 +0200 Subject: [PATCH 10/20] sort params --- conf/igenomes.config | 414 +++++++++++++++++++++---------------------- 1 file changed, 207 insertions(+), 207 deletions(-) diff --git a/conf/igenomes.config b/conf/igenomes.config index 6464acf..1121cde 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -19,26 +19,26 @@ params { fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta" fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta.fai" intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/intervals/wgs_calling_regions_Sarek.list" - known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz" - known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi" known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz" known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz.tbi" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi" } 'GATK.GRCh38' { bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAIndex/" bwamem2 = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAmem2Index/" - dragmap = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/" cf_chrom_len = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/Length/Homo_sapiens_assembly38.len" dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz" dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz.tbi" dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.dict" + dragmap = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/" fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta" fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta.fai" intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/intervals/wgs_calling_regions_noseconds.hg38.bed" - known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz" - known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz.tbi" known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz" known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz.tbi" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz.tbi" pon = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz" pon_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi" } @@ -93,380 +93,380 @@ params { star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" } 'TAIR10' { - fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" mito_name = "Mt" + readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" + star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" } 'EB2' { - fasta = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" readme = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt" + star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" } 'UMD3.1' { - fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" + star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" } 'WBcel235' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" - mito_name = "MtDNA" macs_gsize = "9e7" + mito_name = "MtDNA" + star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" } 'CanFam3.1' { - fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" + star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" } 'GRCz10' { - fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" mito_name = "MT" + star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" } 'BDGP6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" - mito_name = "M" macs_gsize = "1.2e8" + mito_name = "M" + star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" } 'EquCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" + star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" } 'EB1' { - fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" + star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" } 'Galgal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" mito_name = "MT" + star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" } 'Gm01' { - fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" readme = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt" + star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" } 'Mmul_1' { - fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" + star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" } 'IRGSP-1.0' { - fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" mito_name = "Mt" + star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" } 'CHIMP2.1.4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" + star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" } 'Rnor_5.0' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed" mito_name = "MT" + star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/" } 'Rnor_6.0' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" mito_name = "MT" + star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" } 'R64-1-1' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" - mito_name = "MT" macs_gsize = "1.2e7" + mito_name = "MT" + star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" } 'EF2' { - fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" - mito_name = "MT" macs_gsize = "1.21e7" + mito_name = "MT" + readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" + star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" } 'Sbi1' { - fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" readme = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt" + star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" } 'Sscrofa10.2' { - fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" mito_name = "MT" + readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" + star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" } 'AGPv3' { - fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" mito_name = "Mt" + star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" } 'hg38' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" - mito_name = "chrM" macs_gsize = "2.7e9" + mito_name = "chrM" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" } 'hg19' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" - mito_name = "chrM" macs_gsize = "2.7e9" + mito_name = "chrM" + readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" } 'mm10' { - fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" - mito_name = "chrM" macs_gsize = "1.87e9" + mito_name = "chrM" + readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" + star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" } 'bosTau8' { - fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" mito_name = "chrM" + star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" } 'ce10' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" - mito_name = "chrM" macs_gsize = "9e7" + mito_name = "chrM" + readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" + star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" } 'canFam3' { - fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" mito_name = "chrM" + readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" + star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" } 'danRer10' { - fasta = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" - mito_name = "chrM" macs_gsize = "1.37e9" + mito_name = "chrM" + star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" } 'dm6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" - mito_name = "chrM" macs_gsize = "1.2e8" + mito_name = "chrM" + star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" } 'equCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" mito_name = "chrM" + readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" + star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" } 'galGal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" mito_name = "chrM" + readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" + star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" } 'panTro4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" mito_name = "chrM" + readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" + star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" } 'rn6' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" mito_name = "chrM" + star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" } 'sacCer3' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/" - readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" - mito_name = "chrM" + bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa" macs_gsize = "1.2e7" + mito_name = "chrM" + readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" + star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" } 'susScr3' { - fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/" + bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa" gtf = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt" mito_name = "chrM" + readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt" + star = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/" } } } From 80aa57055f9ce7b7ea044df476ba94823737223c Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 12:42:59 +0200 Subject: [PATCH 11/20] better keys --- conf/igenomes.config | 512 +++++++++++++++++++++---------------------- 1 file changed, 256 insertions(+), 256 deletions(-) diff --git a/conf/igenomes.config b/conf/igenomes.config index 1121cde..614ef61 100644 --- a/conf/igenomes.config +++ b/conf/igenomes.config @@ -11,99 +11,60 @@ params { // illumina iGenomes reference file paths genomes { - 'GATK.GRCh37' { - bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/BWAIndex/" - dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz" - dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz.tbi" - dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.dict" - fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta" - fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta.fai" - intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/intervals/wgs_calling_regions_Sarek.list" - known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz" - known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz.tbi" - known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz" - known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi" + 'Ensembl.AGPv3' { + bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" + mito_name = "Mt" + star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" } - 'GATK.GRCh38' { - bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAIndex/" - bwamem2 = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAmem2Index/" - cf_chrom_len = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/Length/Homo_sapiens_assembly38.len" - dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz" - dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz.tbi" - dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.dict" - dragmap = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/" - fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta" - fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta.fai" - intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/intervals/wgs_calling_regions_noseconds.hg38.bed" - known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz" - known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz.tbi" - known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz" - known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz.tbi" - pon = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz" - pon_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi" + 'Ensembl.BDGP6' { + bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" + macs_gsize = "1.2e8" + mito_name = "M" + star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" } - 'Ensembl.GRCh37' { - bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" - macs_gsize = "2.7e9" + 'Ensembl.CanFam3.1' { + bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" mito_name = "MT" - readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" - star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" - } - 'NCBI.GRCh38' { - bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" - macs_gsize = "2.7e9" - mito_name = "chrM" - star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" - } - 'CHM13' { - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" - bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" - gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2TCHM13v2.0/GCF_009914755.1_T2TCHM13v2.0_genomic.gff.gz" - gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" - mito_name = "chrM" + readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" + star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" } - 'GRCm38' { - bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" - dbsnp = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz" - dbsnp_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz.tbi" - dict = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.dict" - fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" - fasta_fai = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa.fai" - gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" - intervals = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/intervals/GRCm38_calling_list.bed" - known_indels = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz" - known_indels_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz.tbi" - macs_gsize = "1.87e9" - mito_name = "MT" - readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" - star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" + 'Ensembl.CHIMP2.1.4' { + bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" + mito_name = "MT" + readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" + star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" } - 'TAIR10' { - bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" - mito_name = "Mt" - readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" - star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" + 'Ensembl.EB1' { + bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" + readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" + star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" } - 'EB2' { + 'Ensembl.EB2' { bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" @@ -113,61 +74,19 @@ params { readme = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt" star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" } - 'UMD3.1' { - bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" - mito_name = "MT" - readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" - star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" - } - 'WBcel235' { - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" - macs_gsize = "9e7" - mito_name = "MtDNA" - star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" - } - 'CanFam3.1' { - bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" - mito_name = "MT" - readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" - star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" - } - 'GRCz10' { - bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" + 'Ensembl.EF2' { + bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" + macs_gsize = "1.21e7" mito_name = "MT" - star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" - } - 'BDGP6' { - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" - macs_gsize = "1.2e8" - mito_name = "M" - star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" + readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" + star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" } - 'EquCab2' { + 'Ensembl.EquCab2' { bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" @@ -178,17 +97,7 @@ params { readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" } - 'EB1' { - bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" - readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" - star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" - } - 'Galgal4' { + 'Ensembl.Galgal4' { bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" @@ -198,7 +107,7 @@ params { mito_name = "MT" star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" } - 'Gm01' { + 'Ensembl.Gm01' { bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" @@ -208,18 +117,48 @@ params { readme = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt" star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" } - 'Mmul_1' { - bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" + 'Ensembl.GRCh37' { + bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" + macs_gsize = "2.7e9" mito_name = "MT" - readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" - star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" + readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" + star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" + } + 'Ensembl.GRCm38' { + bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" + dbsnp = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.snps_all.dbSNP142.vcf.gz.tbi" + dict = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.dict" + fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" + fasta_fai = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa.fai" + gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" + intervals = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/intervals/GRCm38_calling_list.bed" + known_indels = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz.tbi" + macs_gsize = "1.87e9" + mito_name = "MT" + readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" + star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" + } + 'Ensembl.GRCz10' { + bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" + mito_name = "MT" + star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" } - 'IRGSP-1.0' { + 'Ensembl.IRGSP-1.0' { bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" @@ -229,18 +168,29 @@ params { mito_name = "Mt" star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" } - 'CHIMP2.1.4' { - bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" + 'Ensembl.Mmul_1' { + bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" mito_name = "MT" - readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" - star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" + readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" + star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" + } + 'Ensembl.R64-1-1' { + bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" + macs_gsize = "1.2e7" + mito_name = "MT" + star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" } - 'Rnor_5.0' { + 'Ensembl.Rnor_5.0' { bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/" @@ -250,7 +200,7 @@ params { mito_name = "MT" star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/" } - 'Rnor_6.0' { + 'Ensembl.Rnor_6.0' { bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" @@ -260,30 +210,7 @@ params { mito_name = "MT" star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" } - 'R64-1-1' { - bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" - macs_gsize = "1.2e7" - mito_name = "MT" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" - } - 'EF2' { - bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" - macs_gsize = "1.21e7" - mito_name = "MT" - readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" - star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" - } - 'Sbi1' { + 'Ensembl.Sbi1' { bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" @@ -293,7 +220,7 @@ params { readme = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt" star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" } - 'Sscrofa10.2' { + 'Ensembl.Sscrofa10.2' { bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" @@ -304,52 +231,82 @@ params { readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" } - 'AGPv3' { - bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" + 'Ensembl.TAIR10' { + bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" mito_name = "Mt" - star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" + readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" + star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" } - 'hg38' { - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" - macs_gsize = "2.7e9" - mito_name = "chrM" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" + 'Ensembl.UMD3.1' { + bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" + mito_name = "MT" + readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" + star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" } - 'hg19' { - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" - macs_gsize = "2.7e9" - mito_name = "chrM" - readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" + 'Ensembl.WBcel235' { + bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" + macs_gsize = "9e7" + mito_name = "MtDNA" + star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" } - 'mm10' { - bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" - macs_gsize = "1.87e9" + 'GATK.GRCh37' { + bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/BWAIndex/" + dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/dbsnp_138.b37.vcf.gz.tbi" + dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.dict" + fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta" + fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Sequence/WholeGenomeFasta/human_g1k_v37_decoy.fasta.fai" + intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/intervals/wgs_calling_regions_Sarek.list" + known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz.tbi" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/1000G_phase1.snps.high_confidence.b37.vcf.gz.tbi" + } + 'GATK.GRCh38' { + bwa = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/BWAmem2Index/" + cf_chrom_len = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/Length/Homo_sapiens_assembly38.len" + dbsnp = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz" + dbsnp_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/dbsnp_146.hg38.vcf.gz.tbi" + dict = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.dict" + dragmap = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/dragmap/" + fasta = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta" + fasta_fai = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta.fai" + intervals = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/intervals/wgs_calling_regions_noseconds.hg38.bed" + known_indels = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz" + known_indels_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz.tbi" + known_snps = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz" + known_snps_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000G_omni2.5.hg38.vcf.gz.tbi" + pon = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz" + pon_tbi = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi" + } + 'NCBI.GRCh38' { + bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" + macs_gsize = "2.7e9" mito_name = "chrM" - readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" - star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" + star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" } - 'bosTau8' { + 'UCSC.bosTau8' { bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" @@ -359,7 +316,18 @@ params { mito_name = "chrM" star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" } - 'ce10' { + 'UCSC.canFam3' { + bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" + mito_name = "chrM" + readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" + star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" + } + 'UCSC.ce10' { bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" @@ -371,18 +339,15 @@ params { readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" } - 'canFam3' { - bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" - bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" - bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/" - fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" - gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" + 'UCSC.CHM13' { + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" + bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" + gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2TCHM13v2.0/GCF_009914755.1_T2TCHM13v2.0_genomic.gff.gz" + gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" mito_name = "chrM" - readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" - star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" } - 'danRer10' { + 'UCSC.danRer10' { bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" @@ -393,7 +358,7 @@ params { mito_name = "chrM" star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" } - 'dm6' { + 'UCSC.dm6' { bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" @@ -404,7 +369,7 @@ params { mito_name = "chrM" star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" } - 'equCab2' { + 'UCSC.equCab2' { bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" @@ -415,7 +380,7 @@ params { readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" } - 'galGal4' { + 'UCSC.galGal4' { bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" @@ -426,7 +391,42 @@ params { readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" } - 'panTro4' { + 'UCSC.hg19' { + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" + macs_gsize = "2.7e9" + mito_name = "chrM" + readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" + } + 'UCSC.hg38' { + bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" + macs_gsize = "2.7e9" + mito_name = "chrM" + star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" + } + 'UCSC.mm10' { + bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" + bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" + bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" + bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/" + fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" + gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" + macs_gsize = "1.87e9" + mito_name = "chrM" + readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" + star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" + } + 'UCSC.panTro4' { bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" @@ -437,7 +437,7 @@ params { readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" } - 'rn6' { + 'UCSC.rn6' { bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" @@ -447,7 +447,7 @@ params { mito_name = "chrM" star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" } - 'sacCer3' { + 'UCSC.sacCer3' { bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/version0.6.0/" @@ -457,7 +457,7 @@ params { readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" } - 'susScr3' { + 'UCSC.susScr3' { bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" bismark = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/" bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" From 393c75082f5faba0880db1b2cb1678bd63eedc52 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 15:38:11 +0200 Subject: [PATCH 12/20] start working on tests --- conf/{modules.config => modules/base.config} | 12 ------------ conf/modules/cnvkit.config | 19 +++++++++++++++++++ conf/test.config | 10 +++++----- nextflow.config | 6 +++--- tests/csv/1.0.0/cram.csv | 3 +++ workflows/createpanelrefs.nf | 1 - 6 files changed, 30 insertions(+), 21 deletions(-) rename conf/{modules.config => modules/base.config} (79%) create mode 100644 conf/modules/cnvkit.config create mode 100644 tests/csv/1.0.0/cram.csv diff --git a/conf/modules.config b/conf/modules/base.config similarity index 79% rename from conf/modules.config rename to conf/modules/base.config index da58a5d..b4a9878 100644 --- a/conf/modules.config +++ b/conf/modules/base.config @@ -18,18 +18,6 @@ process { saveAs: { filename -> filename.equals('versions.yml') ? null : filename } ] - withName: SAMPLESHEET_CHECK { - publishDir = [ - path: { "${params.outdir}/pipeline_info" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - } - - withName: FASTQC { - ext.args = '--quiet' - } - withName: CUSTOM_DUMPSOFTWAREVERSIONS { publishDir = [ path: { "${params.outdir}/pipeline_info" }, diff --git a/conf/modules/cnvkit.config b/conf/modules/cnvkit.config new file mode 100644 index 0000000..9955a74 --- /dev/null +++ b/conf/modules/cnvkit.config @@ -0,0 +1,19 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Config file for defining DSL2 per module options and publishing paths +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Available keys to override module options: + ext.args = Additional arguments appended to command in module. + ext.args2 = Second set of arguments appended to command in module (multi-tool modules). + ext.args3 = Third set of arguments appended to command in module (multi-tool modules). + ext.prefix = File name prefix for output files. +---------------------------------------------------------------------------------------- +*/ + +process { + + withName: CNVKIT_BATCH { + ext.args = '--method wgs --output-reference panel_of_normals.cnn' + } + +} diff --git a/conf/test.config b/conf/test.config index e307fb2..0aa4720 100644 --- a/conf/test.config +++ b/conf/test.config @@ -20,10 +20,10 @@ params { max_time = '6.h' // Input data - // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets - // TODO nf-core: Give any required params for the test so that command line flags are not needed - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' + input = "${projectDir}/tests/csv/1.0.0/cram.csv" - // Genome references - genome = 'R64-1-1' + // Small reference genome + genome = null + igenomes_ignore = true + fasta = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta" } diff --git a/nextflow.config b/nextflow.config index 1c2fc1c..1673598 100644 --- a/nextflow.config +++ b/nextflow.config @@ -16,7 +16,7 @@ params { genome = null igenomes_base = 's3://ngi-igenomes/igenomes' igenomes_ignore = false - + // MultiQC options multiqc_config = null @@ -43,7 +43,6 @@ params { custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" config_profile_contact = null config_profile_url = null - // Max resource options // Defaults only, expecting to be overwritten @@ -233,7 +232,8 @@ manifest { } // Load modules.config for DSL2 module specific options -includeConfig 'conf/modules.config' +includeConfig 'conf/modules/base.config' +includeConfig 'conf/modules/cnvkit.config' // Function to ensure that resource requirements don't go beyond // a maximum limit diff --git a/tests/csv/1.0.0/cram.csv b/tests/csv/1.0.0/cram.csv new file mode 100644 index 0000000..a4531dc --- /dev/null +++ b/tests/csv/1.0.0/cram.csv @@ -0,0 +1,3 @@ +sample,cram +sample1,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram +sample2,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram diff --git a/workflows/createpanelrefs.nf b/workflows/createpanelrefs.nf index 49c553e..e86b5e7 100644 --- a/workflows/createpanelrefs.nf +++ b/workflows/createpanelrefs.nf @@ -80,7 +80,6 @@ workflow CREATEPANELREFS { ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml')) ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect()) - ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([])) MULTIQC ( ch_multiqc_files.collect(), From 5688b341f9d477cb8bb516a4a7cc379b22ad0b64 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 16:08:58 +0200 Subject: [PATCH 13/20] add params.tools + use nf-validation --- conf/test.config | 3 +++ nextflow.config | 3 ++- nextflow_schema.json | 39 +++++++++++++++++++++++++++++------- workflows/createpanelrefs.nf | 12 ++++++++--- 4 files changed, 46 insertions(+), 11 deletions(-) diff --git a/conf/test.config b/conf/test.config index 0aa4720..cd90561 100644 --- a/conf/test.config +++ b/conf/test.config @@ -22,6 +22,9 @@ params { // Input data input = "${projectDir}/tests/csv/1.0.0/cram.csv" + // Main options + tools = 'cnvkit' + // Small reference genome genome = null igenomes_ignore = true diff --git a/nextflow.config b/nextflow.config index 1673598..8c77ab9 100644 --- a/nextflow.config +++ b/nextflow.config @@ -9,7 +9,6 @@ // Global default params, used in configs params { - // TODO nf-core: Specify your pipeline's command line flags // Input options input = null // References @@ -17,6 +16,8 @@ params { igenomes_base = 's3://ngi-igenomes/igenomes' igenomes_ignore = false + // Building Panel of Normals and models + tools = null // No default, must be specified // MultiQC options multiqc_config = null diff --git a/nextflow_schema.json b/nextflow_schema.json index 1972341..5f110e5 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -13,14 +13,23 @@ "required": ["input", "outdir"], "properties": { "input": { - "type": "string", - "format": "file-path", - "exists": true, - "mimetype": "text/csv", - "pattern": "^\\S+\\.csv$", "description": "Path to comma-separated file containing information about the samples in the experiment.", - "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/createpanelrefs/usage#samplesheet-input).", - "fa_icon": "fas fa-file-csv" + "help_text": "A design file with information about the samples in your experiment. Use this parameter to specify the location of the input files. It has to be a comma-separated file with a header row. See [usage docs](https://nf-co.re/sarek/usage#input).\n\nIf no input file is specified, sarek will attempt to locate one in the `{outdir}` directory.", + "fa_icon": "fas fa-file-csv", + "schema": "assets/schema_input.json", + "anyOf": [ + { + "type": "string", + "format": "file-path", + "exists": true, + "mimetype": "text/csv", + "pattern": "^\\S+\\.csv$" + }, + { + "type": "string", + "maxLength": 0 + } + ] }, "outdir": { "type": "string", @@ -42,6 +51,22 @@ } } }, + "main_options": { + "title": "Main options", + "type": "object", + "description": "Most common options used for the pipeline", + "default": "", + "properties": { + "tools": { + "type": "string", + "fa_icon": "fas fa-toolbox", + "description": "Tools to use for building Panel of Normals or models.", + "help_text": "Multiple tools separated with commas.\n\nTools available: CNVKIT.", + "pattern": "^((cnvkit)?,?)*(? Date: Sat, 8 Jul 2023 16:49:10 +0200 Subject: [PATCH 14/20] generate PON with CNVKIT --- conf/modules/cnvkit.config | 9 ++++++++- tests/csv/1.0.0/cram.csv | 6 +++--- workflows/createpanelrefs.nf | 30 ++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+), 4 deletions(-) diff --git a/conf/modules/cnvkit.config b/conf/modules/cnvkit.config index 9955a74..0e29261 100644 --- a/conf/modules/cnvkit.config +++ b/conf/modules/cnvkit.config @@ -13,7 +13,14 @@ process { withName: CNVKIT_BATCH { - ext.args = '--method wgs --output-reference panel_of_normals.cnn' + ext.args = {"--method wgs --output-reference ${meta.id}.cnn"} + publishDir = [ + [ + mode: params.publish_dir_mode, + path: { "${params.outdir}/reference/cnvkit/" }, + pattern: "*{.cnn}" + ] + ] } } diff --git a/tests/csv/1.0.0/cram.csv b/tests/csv/1.0.0/cram.csv index a4531dc..e132a68 100644 --- a/tests/csv/1.0.0/cram.csv +++ b/tests/csv/1.0.0/cram.csv @@ -1,3 +1,3 @@ -sample,cram -sample1,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram -sample2,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram +sample,bam +sample1,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam +sample2,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam diff --git a/workflows/createpanelrefs.nf b/workflows/createpanelrefs.nf index b5e20f3..11b7c6e 100644 --- a/workflows/createpanelrefs.nf +++ b/workflows/createpanelrefs.nf @@ -15,6 +15,20 @@ log.info logo + paramsSummaryLog(workflow) + citation WorkflowCreatepanelrefs.initialise(params, log) +// Check input path parameters to see if they exist + +def checkPathParamList = [ + params.fasta +] + +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + CHECK MANDATORY PARAMETERS +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ + +for (param in checkPathParamList) if (param) file(param, checkIfExists: true) + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ MANAGE SAMPLESHEET @@ -23,6 +37,17 @@ WorkflowCreatepanelrefs.initialise(params, log) ch_from_samplesheet = Channel.fromSamplesheet("input") +ch_input = ch_from_samplesheet.map{meta, bam, bai, cram, crai -> + if (bam) return [ [id:"panel", data_type:"bam" ], bam ] + if (cram) return [ [id:"panel", data_type:"cram" ], cram ] +}.groupTuple().branch{ + bam: it[0].data_type == "bam" + cram: it[0].data_type == "cram" +} + +// Initialize file channels based on params, defined in the params.genomes[params.genome] scope +ch_fasta = params.fasta ? Channel.fromPath(params.fasta).first() : Channel.empty() + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CONFIG FILES @@ -71,6 +96,11 @@ workflow CREATEPANELREFS { ch_versions = Channel.empty() + if (params.tools && params.tools.split(',').contains('cnvkit')) { + CNVKIT_BATCH ( ch_input.bam.map{meta, bam -> [ meta, [], bam ]}, ch_fasta, [], [], [], true ) + ch_versions = ch_versions.mix(CNVKIT_BATCH.out.versions) + } + CUSTOM_DUMPSOFTWAREVERSIONS ( ch_versions.unique().collectFile(name: 'collated_versions.yml') ) From 512b18411720b3a615bf167051fa8eae37154b75 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 18:50:14 +0200 Subject: [PATCH 15/20] add tests --- .gitattributes | 1 + .github/workflows/ci.yml | 185 +++++++++++++++++++++++++--- .gitignore | 9 +- README.md | 21 +++- nf-test.config | 16 +++ tests/configs/tags.yml | 14 +++ tests/lib/UTILS.groovy | 11 ++ tests/pipeline/default.nf.test | 25 ++++ tests/pipeline/default.nf.test.snap | 18 +++ 9 files changed, 273 insertions(+), 27 deletions(-) create mode 100644 nf-test.config create mode 100644 tests/configs/tags.yml create mode 100644 tests/lib/UTILS.groovy create mode 100644 tests/pipeline/default.nf.test create mode 100644 tests/pipeline/default.nf.test.snap diff --git a/.gitattributes b/.gitattributes index 7a2dabc..31ba574 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2,3 +2,4 @@ *.nf.test linguist-language=nextflow modules/nf-core/** linguist-generated subworkflows/nf-core/** linguist-generated +tests/**/*nf.test.snap linguist-generated diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 4ca7478..cdefe64 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -1,43 +1,194 @@ -name: nf-core CI # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors +name: nf-core CI on: push: branches: - dev pull_request: + branches: + - dev + - master release: - types: [published] + types: + - "published" env: NXF_ANSI_LOG: false + NFTEST_VER: "0.7.3" +# Cancel if a newer run is started concurrency: - group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}" + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} cancel-in-progress: true jobs: - test: - name: Run pipeline with test data - # Only run on push if this is the nf-core dev branch (merged PRs) - if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/createpanelrefs') }}" + changes: + name: Check for changes + runs-on: ubuntu-latest + outputs: + # Expose matched filters as job 'tags' output variable + tags: ${{ steps.filter.outputs.changes }} + steps: + - uses: actions/checkout@v3 + - uses: dorny/paths-filter@v2 + id: filter + with: + filters: "tests/config/tags.yml" + + define_nxf_versions: + name: Choose nextflow versions to test against depending on target branch + runs-on: ubuntu-latest + outputs: + matrix: ${{ steps.nxf_versions.outputs.matrix }} + steps: + - id: nxf_versions + run: | + if [[ "${{ github.event_name }}" == "pull_request" && "${{ github.base_ref }}" == "dev" && "${{ matrix.NXF_VER }}" != "latest-everything" ]]; then + echo matrix='["latest-everything"]' | tee -a $GITHUB_OUTPUT + else + echo matrix='["latest-everything", "23.04.0"]' | tee -a $GITHUB_OUTPUT + fi + + test-dev: + if: (github.base_ref == 'dev' || (github.event_name == 'push')) + name: ${{ matrix.tags }} ${{ matrix.profile }} NXF ${{ matrix.NXF_VER }} runs-on: ubuntu-latest + needs: changes strategy: + fail-fast: false matrix: - NXF_VER: - - "23.04.0" - - "latest-everything" + # Run tests based on changes in code + tags: ["${{ fromJson(needs.changes.outputs.tags) }}"] + # Only run docker tests on dev branch + profile: ["docker"] + # Only test minimal version + NXF_VER: ["23.04.0"] + # Always run default test + include: + - tags: default + steps: - name: Check out pipeline code uses: actions/checkout@v3 - - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + - uses: actions/cache@v3 + with: + path: /usr/local/bin/nextflow + key: ${{ runner.os }} + restore-keys: | + ${{ runner.os }}-nextflow- + + - name: Install nf-test + run: | + wget -qO- https://code.askimed.com/install/nf-test | bash -s $NFTEST_VER + sudo mv nf-test /usr/local/bin/ + + - name: Install Nextflow ${{ matrix.NXF_VER }} + uses: nf-core/setup-nextflow@v1.2.0 with: version: "${{ matrix.NXF_VER }}" - - name: Run pipeline with test data - # TODO nf-core: You can customise CI pipeline run tests as required - # For example: adding multiple test runs with different parameters - # Remember that you can parallelise this by using strategy.matrix + - name: Run nf-test + uses: Wandalen/wretry.action@v1.0.11 + with: + command: nf-test test tests/${{ matrix.tags }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap + attempt_limit: 3 + + - name: Output log on failure + if: failure() run: | - nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results + sudo apt install bat > /dev/null + batcat --decorations=always --color=always /home/runner/pytest_workflow_*/*/log.{out,err} + + - name: Upload logs on failure + if: failure() + uses: actions/upload-artifact@v2 + with: + name: logs-${{ matrix.profile }} + path: | + /home/runner/pytest_workflow_*/*/.nextflow.log + /home/runner/pytest_workflow_*/*/log.out + /home/runner/pytest_workflow_*/*/log.err + /home/runner/pytest_workflow_*/*/work + + test-master: + # Only run on master branch or when a PR is opened against master + if: github.base_ref == 'master' + name: ${{ matrix.tags }} ${{ matrix.profile }} NXF ${{ matrix.NXF_VER }} + runs-on: ubuntu-latest + needs: [changes, define_nxf_versions] + strategy: + fail-fast: false + matrix: + # Run tests based on changes in code + tags: ["${{ fromJson(needs.changes.outputs.tags) }}"] + # Only run docker tests on dev branch + profile: ["docker", "singularity", "conda"] + NXF_VER: ${{ fromJson(needs.define_nxf_versions.outputs.matrix) }} + # Always run default test + include: + - tags: default + + steps: + - name: Check out pipeline code + uses: actions/checkout@v3 + + - uses: actions/cache@v3 + with: + path: /usr/local/bin/nextflow + key: ${{ runner.os }} + restore-keys: | + ${{ runner.os }}-nextflow- + + - name: Install nf-test + run: | + wget -qO- https://code.askimed.com/install/nf-test | bash -s $NFTEST_VER + sudo mv nf-test /usr/local/bin/ + + - name: Install Nextflow ${{ matrix.NXF_VER }} + uses: nf-core/setup-nextflow@v1.2.0 + with: + version: "${{ matrix.NXF_VER }}" + + - name: Set up Singularity + if: matrix.profile == 'singularity' + uses: eWaterCycle/setup-singularity@v5 + with: + singularity-version: 3.7.1 + + - name: Set up miniconda + if: matrix.profile == 'conda' + uses: conda-incubator/setup-miniconda@v2 + with: + auto-update-conda: true + channels: conda-forge,bioconda,defaults + python-version: ${{ matrix.python-version }} + + - name: Conda clean + if: matrix.profile == 'conda' + run: conda clean -a + + - name: Run nf-test + uses: Wandalen/wretry.action@v1.0.11 + with: + command: nf-test test tests/${{ matrix.tag }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap + attempt_limit: 3 + + - name: Output log on failure + if: failure() + run: | + sudo apt install bat > /dev/null + batcat --decorations=always --color=always /home/runner/pytest_workflow_*/*/log.{out,err} + + - name: Upload logs on failure + if: failure() + uses: actions/upload-artifact@v2 + with: + name: logs-${{ matrix.profile }} + path: | + /home/runner/pytest_workflow_*/*/.nextflow.log + /home/runner/pytest_workflow_*/*/log.out + /home/runner/pytest_workflow_*/*/log.err + /home/runner/pytest_workflow_*/*/work + !/home/runner/pytest_workflow_*/*/work/conda + !/home/runner/pytest_workflow_*/*/work/singularity diff --git a/.gitignore b/.gitignore index 5124c9a..8cf857e 100644 --- a/.gitignore +++ b/.gitignore @@ -1,8 +1,9 @@ +*.pyc +.DS_Store .nextflow* -work/ +.nf-test/ data/ results/ -.DS_Store -testing/ testing* -*.pyc +testing/ +work/ diff --git a/README.md b/README.md index 70f8911..45e13c5 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,7 @@ # ![nf-core/createpanelrefs](docs/images/nf-core-createpanelrefs_logo_light.png#gh-light-mode-only) ![nf-core/createpanelrefs](docs/images/nf-core-createpanelrefs_logo_dark.png#gh-dark-mode-only) -[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/createpanelrefs/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) +[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/createpanelrefs/results) +[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) [![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/) @@ -8,7 +9,10 @@ [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) [![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/createpanelrefs) -[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23createpanelrefs-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/createpanelrefs)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) +[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23createpanelrefs-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/createpanelrefs) +[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core) +[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core) +[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) ## Introduction @@ -30,11 +34,14 @@ First, prepare a samplesheet with your input data that looks as follows: `samplesheet.csv`: ```csv -sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz +sample,bam +sample1,sample1.bam +sample2,sample2.bam +sample3,sample3.bam +sample4,sample4.bam ``` -Each row represents a fastq file (single-end) or a pair of fastq files (paired end). +Each row represents a bam file. Now, you can run the pipeline using: @@ -42,6 +49,7 @@ Now, you can run the pipeline using: nextflow run nf-core/createpanelrefs \ -profile \ --input samplesheet.csv \ + --genome GATK.GRCh38 \ --outdir ``` @@ -67,7 +75,8 @@ nf-core/createpanelrefs was originally written by @maxulysse. We thank the following people for their extensive assistance in the development of this pipeline: - +- @jfy133 +- @JoseEspinosa ## Contributions and Support diff --git a/nf-test.config b/nf-test.config new file mode 100644 index 0000000..c35074c --- /dev/null +++ b/nf-test.config @@ -0,0 +1,16 @@ +config { + // location for all nf-tests + testsDir "tests/pipeline" + + // nf-test directory including temporary files for each test + workDir ".nf-test" + + // location of library folder that is added automatically to the classpath + libDir "tests/lib/" + + // location of an optional nextflow.config file specific for executing tests + configFile "nextflow.config" + + // run all test with defined profile(s) from the main nextflow.config + profile "" +} diff --git a/tests/configs/tags.yml b/tests/configs/tags.yml new file mode 100644 index 0000000..7e9962d --- /dev/null +++ b/tests/configs/tags.yml @@ -0,0 +1,14 @@ +default: + - conf/** + - main.nf + - modules/** + - nextflow.config + - nextflow_schema.json + - subworkflows/** + - tests/*.nf.test + - workflows/** + +cnvkit: + - conf/modules/cnvkit.config + - modules/nf-core/cnvkit/batch/main.nf + - tests/cnvkit.nf.test diff --git a/tests/lib/UTILS.groovy b/tests/lib/UTILS.groovy new file mode 100644 index 0000000..311403c --- /dev/null +++ b/tests/lib/UTILS.groovy @@ -0,0 +1,11 @@ +// Function to remove Nextflow version from software_versions.yml + +class UTILS { + public static String removeNextflowVersion(outputDir) { + def softwareVersions = path("$outputDir/pipeline_info/software_versions.yml").yaml + if (softwareVersions.containsKey("Workflow")) { + softwareVersions.Workflow.remove("Nextflow") + } + return softwareVersions + } +} diff --git a/tests/pipeline/default.nf.test b/tests/pipeline/default.nf.test new file mode 100644 index 0000000..4d24bf1 --- /dev/null +++ b/tests/pipeline/default.nf.test @@ -0,0 +1,25 @@ +nextflow_pipeline { + + name "Test pipeline" + script "main.nf" + tag "default" + + test("Run default test") { + + when { + params { + outdir = "$outputDir" + validationSchemaIgnoreParams = 'genomes,baseDir,base-dir,outputDir,output-dir' + } + } + + then { + assertAll( + { assert workflow.success }, + { assert new File("$outputDir/multiqc/").exists() }, + { assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") }, + { assert snapshot(path("$outputDir/reference/cnvkit/").list()).match("cnvkit") } + ) + } + } +} diff --git a/tests/pipeline/default.nf.test.snap b/tests/pipeline/default.nf.test.snap new file mode 100644 index 0000000..d41eebb --- /dev/null +++ b/tests/pipeline/default.nf.test.snap @@ -0,0 +1,18 @@ +{ + "software_versions": { + "content": [ + "{CNVKIT_BATCH={cnvkit=0.9.9}, CUSTOM_DUMPSOFTWAREVERSIONS={python=3.11.0, yaml=6.0}, Workflow={nf-core/createpanelrefs=1.0dev}}" + ], + "timestamp": "2023-07-08T16:47:57+0000" + }, + "cnvkit": { + "content": [ + "panel.cnn:md5,07dea67088da689ad04012552c606882", + "test.paired_end.sorted.antitargetcoverage.cnn:md5,203caf8cef6935bb50b4138097955cb8", + "test.paired_end.sorted.targetcoverage.cnn:md5,ff526714696aa49bdc1dc8d00d965266", + "test2.paired_end.sorted.antitargetcoverage.cnn:md5,203caf8cef6935bb50b4138097955cb8", + "test2.paired_end.sorted.targetcoverage.cnn:md5,6ae6b3fce7299eedca6133d911c38fe1" + ], + "timestamp": "2023-07-08T16:47:57+0000" + } +} \ No newline at end of file From 538704eb31b7503b1b9936f5bacc86b34494b5c8 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 18:52:47 +0200 Subject: [PATCH 16/20] more tests --- tests/pipeline/cnvkit.nf.test | 26 ++++++++++++++++++++++++++ tests/pipeline/cnvkit.nf.test.snap | 18 ++++++++++++++++++ 2 files changed, 44 insertions(+) create mode 100644 tests/pipeline/cnvkit.nf.test create mode 100644 tests/pipeline/cnvkit.nf.test.snap diff --git a/tests/pipeline/cnvkit.nf.test b/tests/pipeline/cnvkit.nf.test new file mode 100644 index 0000000..dd255c3 --- /dev/null +++ b/tests/pipeline/cnvkit.nf.test @@ -0,0 +1,26 @@ +nextflow_pipeline { + + name "Test pipeline" + script "main.nf" + tag "cnvkit" + + test("Run cnvkit test") { + + when { + params { + outdir = "$outputDir" + tools = 'cnvkit' + validationSchemaIgnoreParams = 'genomes,baseDir,base-dir,outputDir,output-dir' + } + } + + then { + assertAll( + { assert workflow.success }, + { assert new File("$outputDir/multiqc/").exists() }, + { assert snapshot(UTILS.removeNextflowVersion("$outputDir")).match("software_versions") }, + { assert snapshot(path("$outputDir/reference/cnvkit/").list()).match("cnvkit") } + ) + } + } +} diff --git a/tests/pipeline/cnvkit.nf.test.snap b/tests/pipeline/cnvkit.nf.test.snap new file mode 100644 index 0000000..f52ff4b --- /dev/null +++ b/tests/pipeline/cnvkit.nf.test.snap @@ -0,0 +1,18 @@ +{ + "software_versions": { + "content": [ + "{CNVKIT_BATCH={cnvkit=0.9.9}, CUSTOM_DUMPSOFTWAREVERSIONS={python=3.11.0, yaml=6.0}, Workflow={nf-core/createpanelrefs=1.0dev}}" + ], + "timestamp": "2023-07-08T16:51:32+0000" + }, + "cnvkit": { + "content": [ + "panel.cnn:md5,07dea67088da689ad04012552c606882", + "test.paired_end.sorted.antitargetcoverage.cnn:md5,203caf8cef6935bb50b4138097955cb8", + "test.paired_end.sorted.targetcoverage.cnn:md5,ff526714696aa49bdc1dc8d00d965266", + "test2.paired_end.sorted.antitargetcoverage.cnn:md5,203caf8cef6935bb50b4138097955cb8", + "test2.paired_end.sorted.targetcoverage.cnn:md5,6ae6b3fce7299eedca6133d911c38fe1" + ], + "timestamp": "2023-07-08T16:51:32+0000" + } +} \ No newline at end of file From d48a1c2dac256bd563e30d18aedcec1174077beb Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 18:57:03 +0200 Subject: [PATCH 17/20] update CHANGELOG --- CHANGELOG.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index f1f6bc8..abde31e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,8 +9,9 @@ Initial release of nf-core/createpanelrefs, created with the [nf-core](https://n ### `Added` -- `CNVKIT` can be used to create a PON -- Usage of nf-validation +- [#5](https://github.com/nf-core/createpanelrefs/pull/5) - `CNVKIT` can be used to create a PON +- [#5](https://github.com/nf-core/createpanelrefs/pull/5) - Usage of nf-validation +- [#5](https://github.com/nf-core/createpanelrefs/pull/5) - Usage of nf-test ### `Fixed` From 77b10b83ba06d1e548be50e237b4e9e3b7d496d6 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 19:07:49 +0200 Subject: [PATCH 18/20] fix linting --- .nf-core.yml | 7 +++++++ .prettierignore | 17 +++++++++-------- modules.json | 9 ++------- .../nf-core/custom/dumpsoftwareversions/main.nf | 2 +- .../templates/dumpsoftwareversions.py | 3 +-- modules/nf-core/multiqc/main.nf | 2 +- nextflow_schema.json | 3 +++ 7 files changed, 24 insertions(+), 19 deletions(-) diff --git a/.nf-core.yml b/.nf-core.yml index 3805dc8..9ba16db 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1 +1,8 @@ repository_type: pipeline +lint: + actions_ci: False + files_exist: + - conf/modules.config + files_unchanged: + - .gitattributes + - .gitignore diff --git a/.prettierignore b/.prettierignore index 437d763..79934dc 100644 --- a/.prettierignore +++ b/.prettierignore @@ -1,12 +1,13 @@ -email_template.html -adaptivecard.json -slackreport.json +*.pyc +.DS_Store .nextflow* -work/ +.nf-test/ +adaptivecard.json +bin/ data/ +email_template.html results/ -.DS_Store -testing/ +slackreport.json testing* -*.pyc -bin/ +testing/ +work/ diff --git a/modules.json b/modules.json index 89ff874..29e931c 100644 --- a/modules.json +++ b/modules.json @@ -12,17 +12,12 @@ }, "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "76cc4938c1f6ea5c7d83fed1eeffc146787f9543", - "installed_by": ["modules"] - }, - "fastqc": { - "branch": "master", - "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "f2d63bd5b68925f98f572eed70993d205cc694b7", + "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", "installed_by": ["modules"] } } diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 800a609..ebc8727 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/custom/dumpsoftwareversions/main.nf @@ -5,7 +5,7 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { conda "bioconda::multiqc=1.14" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.14--pyhdfd78af_0' }" + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path versions diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py index e55b8d4..da03340 100755 --- a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py +++ b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py @@ -4,11 +4,10 @@ """Provide functions to merge multiple versions.yml files.""" +import yaml import platform from textwrap import dedent -import yaml - def _make_versions_html(versions): """Generate a tabular HTML output of all versions for MultiQC.""" diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 4b60474..1fc387b 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -4,7 +4,7 @@ process MULTIQC { conda "bioconda::multiqc=1.14" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/multiqc:1.14--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.14--pyhdfd78af_0' }" + 'biocontainers/multiqc:1.14--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" diff --git a/nextflow_schema.json b/nextflow_schema.json index 5f110e5..ae43650 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -312,6 +312,9 @@ { "$ref": "#/definitions/input_output_options" }, + { + "$ref": "#/definitions/main_options" + }, { "$ref": "#/definitions/reference_genome_options" }, From ebeda5545614cee8a9f6ecb1c0a5b344935307b1 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 19:12:03 +0200 Subject: [PATCH 19/20] fix path --- tests/{configs => config}/tags.yml | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename tests/{configs => config}/tags.yml (100%) diff --git a/tests/configs/tags.yml b/tests/config/tags.yml similarity index 100% rename from tests/configs/tags.yml rename to tests/config/tags.yml From abf40f5ea91aea07fded5a107ffad608fb1143c3 Mon Sep 17 00:00:00 2001 From: maxulysse Date: Sat, 8 Jul 2023 19:15:06 +0200 Subject: [PATCH 20/20] fix path to tests --- .github/workflows/ci.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index cdefe64..b4fad51 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -91,7 +91,7 @@ jobs: - name: Run nf-test uses: Wandalen/wretry.action@v1.0.11 with: - command: nf-test test tests/${{ matrix.tags }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap + command: nf-test test tests/pipeline/${{ matrix.tags }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap attempt_limit: 3 - name: Output log on failure @@ -171,7 +171,7 @@ jobs: - name: Run nf-test uses: Wandalen/wretry.action@v1.0.11 with: - command: nf-test test tests/${{ matrix.tag }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap + command: nf-test test tests/pipeline/${{ matrix.tag }}.nf.test --profile "test,${{ matrix.profile }}" --tap=test.tap attempt_limit: 3 - name: Output log on failure