diff --git a/CHANGELOG.md b/CHANGELOG.md
index d90cb63..5446abe 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -38,6 +38,8 @@ Initial release of nf-core/references, created with the [nf-core](https://nf-co.
- [41](https://github.com/nf-core/references/pull/41) - Better sarek tests
- [41](https://github.com/nf-core/references/pull/41) - Better publishing for sarek related files
- [43](https://github.com/nf-core/references/pull/43) - Fasta is no longer a required asset
+- [48](https://github.com/nf-core/references/pull/48) - Simplify VCF tabix index generation and related assets
+- [48](https://github.com/nf-core/references/pull/48) - Code refactoring (new subworfklows for each type of operations)
- [49](https://github.com/nf-core/references/pull/49) - Better publishing for all files
### Fixed
diff --git a/assets/genomes/test/default_extended.yml b/assets/genomes/test/default_extended.yml
index fc69d05..a51628b 100644
--- a/assets/genomes/test/default_extended.yml
+++ b/assets/genomes/test/default_extended.yml
@@ -1,22 +1,28 @@
- genome: "GRCh38_chr21"
- dbsnp_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
fasta: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa"
fasta_dict: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.dict"
fasta_fai: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa.fai"
fasta_sizes: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa.sizes"
- germline_resource_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
gff: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genes_chr21.gff"
gtf: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.gtf"
- known_indels_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
- known_snps_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
mito_name: "MT"
readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
source: "nf-core/references"
- source_dbsnp: "GATK_BUNDLE"
- source_germline_resource: "GATK_BUNDLE"
- source_known_indels: "GATK_BUNDLE"
- source_known_snps: "GATK_BUNDLE"
+ source_vcf: "GATK_BUNDLE"
species: "Homo_sapiens"
splice_sites: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genes_chr21.splice_sites.txt"
transcript_fasta: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genome.transcripts.fa"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
# macs_gsize: "1.2e7"
+- genome: "GRCh38_chr21"
+ readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
+ source: "nf-core/references"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
+- genome: "GRCh38_chr21"
+ readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
+ source: "nf-core/references"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
diff --git a/assets/genomes/test/default_full.yml b/assets/genomes/test/default_full.yml
index 27accf4..cc79561 100644
--- a/assets/genomes/test/default_full.yml
+++ b/assets/genomes/test/default_full.yml
@@ -1,27 +1,32 @@
- genome: "GRCh38_chr21"
- dbsnp_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
- dbsnp_vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
fasta: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa"
fasta_dict: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.dict"
fasta_fai: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa.fai"
fasta_sizes: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.fa.sizes"
- germline_resource_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
- germline_resource_vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz.tbi"
gff: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genes_chr21.gff"
gtf: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.gtf"
intervals_bed: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/GRCh38_chr21.bed"
- known_indels_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
- known_indels_vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
- known_snps_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
- known_snps_vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
mito_name: "MT"
readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
source: "nf-core/references"
- source_dbsnp: "GATK_BUNDLE"
- source_germline_resource: "GATK_BUNDLE"
- source_known_indels: "GATK_BUNDLE"
- source_known_snps: "GATK_BUNDLE"
+ source_vcf: "GATK_BUNDLE"
species: "Homo_sapiens"
splice_sites: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genes_chr21.splice_sites.txt"
transcript_fasta: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/genome.transcripts.fa"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
+ vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
# macs_gsize: "1.2e7"
+- genome: "GRCh38_chr21"
+ readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
+ source: "nf-core/references"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
+ vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz.tbi"
+- genome: "GRCh38_chr21"
+ readme: "https://raw.githubusercontent.com/nf-core/test-datasets/references/references/GRCh38_chr21/README.md"
+ source: "nf-core/references"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
+ vcf_tbi: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
diff --git a/assets/genomes/test/pipelines/sarek.yml b/assets/genomes/test/pipelines/sarek.yml
index f039b0f..c813acf 100644
--- a/assets/genomes/test/pipelines/sarek.yml
+++ b/assets/genomes/test/pipelines/sarek.yml
@@ -1,12 +1,16 @@
- genome: "testdata.GRCh38_chr22"
- dbsnp_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
fasta: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta"
- germline_resource_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
- known_indels_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
- known_snps_vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
source: "nf-core/references"
- source_dbsnp: "GATK_BUNDLE"
- source_germline_resource: "GATK_BUNDLE"
- source_known_indels: "GATK_BUNDLE"
- source_known_snps: "GATK_BUNDLE"
+ source_vcf: "GATK_BUNDLE"
species: "Homo_sapiens"
+- genome: "testdata.GRCh38_chr22"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ source: "nf-core/references"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
+- genome: "testdata.GRCh38_chr22"
+ source_vcf: "GATK_BUNDLE"
+ species: "Homo_sapiens"
+ source: "nf-core/references"
+ vcf: "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
diff --git a/assets/genomes/test/pipelines/sarek_s3_muliple_glob.yml b/assets/genomes/test/pipelines/sarek_s3_muliple_glob.yml
index 5eb4d04..23b1bd9 100644
--- a/assets/genomes/test/pipelines/sarek_s3_muliple_glob.yml
+++ b/assets/genomes/test/pipelines/sarek_s3_muliple_glob.yml
@@ -1,11 +1,11 @@
# from sarek igenomes.config
- genome: GRCh37
- known_indels_vcf: "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz"
- source_known_indels: "GATK_BUNDLE"
+ vcf: "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz"
+ source_vcf: "GATK_BUNDLE"
species: "Homo_sapiens"
source: "GATK"
- genome: GRCh38
- known_indels_vcf: "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz"
- source_known_indels: "GATK_BUNDLE"
+ vcf: "s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/{Mills_and_1000G_gold_standard.indels.hg38,beta/Homo_sapiens_assembly38.known_indels}.vcf.gz"
+ source_vcf: "GATK_BUNDLE"
species: "Homo_sapiens"
source: "GATK"
diff --git a/assets/schema_input.json b/assets/schema_input.json
index 36293cc..784a882 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -18,25 +18,10 @@
"errorMessage": "Where the references came from",
"meta": ["source"]
},
- "source_dbsnp": {
+ "source_vcf": {
"type": "string",
"errorMessage": "Where the references came from",
- "meta": ["source_dbsnp"]
- },
- "source_germline_resource": {
- "type": "string",
- "errorMessage": "Where the references came from",
- "meta": ["source_germline_resource"]
- },
- "source_known_indels": {
- "type": "string",
- "errorMessage": "Where the references came from",
- "meta": ["source_known_indels"]
- },
- "source_known_snps": {
- "type": "string",
- "errorMessage": "Where the references came from",
- "meta": ["source_known_snps"]
+ "meta": ["source_vcf"]
},
"species": {
"type": "string",
@@ -88,22 +73,7 @@
"pattern": "^\\S+\\.f(ast|n)?a(\\.gz)?$",
"errorMessage": "TODO"
},
- "dbsnp_vcf": {
- "type": "string",
- "pattern": "^\\S+\\.vcf\\.gz$",
- "errorMessage": "TODO"
- },
- "known_snps_vcf": {
- "type": "string",
- "pattern": "^\\S+\\.vcf\\.gz$",
- "errorMessage": "TODO"
- },
- "known_indels_vcf": {
- "type": "string",
- "pattern": "^\\S+\\.vcf\\.gz$",
- "errorMessage": "TODO"
- },
- "germline_resource_vcf": {
+ "vcf": {
"type": "string",
"pattern": "^\\S+\\.vcf\\.gz$",
"errorMessage": "TODO"
diff --git a/main.nf b/main.nf
index cad54fe..fd71eb9 100644
--- a/main.nf
+++ b/main.nf
@@ -102,19 +102,19 @@ workflow {
}
output {
- 'bowtie1' {
+ 'bowtie1_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/BowtieIndex/" } }
}
- 'bowtie2' {
+ 'bowtie2_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/Bowtie2Index/" } }
}
- 'bwamem1' {
+ 'bwamem1_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/BWAIndex/" } }
}
- 'bwamem2' {
+ 'bwamem2_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/BWAmem2Index/" } }
}
- 'dragmap' {
+ 'dragmap_hashmap' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/dragmap/" } }
}
'fasta' {
@@ -129,56 +129,47 @@ output {
'fasta_sizes' {
path { meta, sizes -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/WholeGenomeFasta/${file}" } }
}
- 'gffread' {
+ 'gtf' {
path { meta, intervals -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/Genes/${file}" } }
}
- 'hisat2' {
+ 'hisat2_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/Hisat2Index/" } }
}
- 'intervals' {
+ 'intervals_bed' {
path { meta, intervals -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/intervals/${file}" } }
}
- 'kallisto' {
+ 'kallisto_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/KallistoIndex/" } }
}
- 'msisensorpro' {
+ 'msisensorpro_list' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/msisensorpro/${file}" } }
}
'multiqc_data' {
- path 'multiqc'
+ path { folder -> { file -> "multiqc/multiqc_data" } }
}
'multiqc_plots' {
- path 'multiqc'
+ path { folder -> { file -> "multiqc/multiqc_plots" } }
}
'multiqc_report' {
- path 'multiqc'
+ path { folder -> { file -> "multiqc/multiqc_report" } }
}
- 'rsem' {
+ 'rsem_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/RSEMIndex/" } }
}
- 'salmon' {
+ 'salmon_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/SalmonIndex/" } }
}
'splice_sites' {
path { meta, txt -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/SpliceSites/${file}" } }
}
- 'star' {
+ 'star_index' {
path { meta, index -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/STARIndex/" } }
}
'transcript_fasta' {
path { meta, fasta -> { file -> "${meta.species}/${meta.source}/${meta.id}/Sequence/TranscriptFasta/${file}" } }
}
- 'tabix_dbsnp' {
- path { meta, vcf -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/${meta.source_dbsnp}/${file}" } }
- }
- 'tabix_germline_resource' {
- path { meta, vcf -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/${meta.source_germline_resource}/${file}" } }
- }
- 'tabix_known_indels' {
- path { meta, vcf -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/${meta.source_known_indels}/${file}" } }
- }
- 'tabix_known_snps' {
- path { meta, vcf -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/${meta.source_known_snps}/${file}" } }
+ 'vcf_tbi' {
+ path { meta, tbi -> { file -> "${meta.species}/${meta.source}/${meta.id}/Annotation/${meta.source_vcf}/${file}" } }
}
}
/*
@@ -200,28 +191,25 @@ workflow NFCORE_REFERENCES {
REFERENCES(input, tools)
emit:
- bowtie1 = REFERENCES.out.bowtie1
- bowtie2 = REFERENCES.out.bowtie2
- bwamem1 = REFERENCES.out.bwamem1
- bwamem2 = REFERENCES.out.bwamem2
- dbsnp_vcf_tbi = REFERENCES.out.dbsnp_vcf_tbi
- dragmap = REFERENCES.out.dragmap
- fasta = REFERENCES.out.fasta
- fasta_dict = REFERENCES.out.fasta_dict
- fasta_fai = REFERENCES.out.fasta_fai
- germline_resource_vcf_tbi = REFERENCES.out.germline_resource_vcf_tbi
- gffread = REFERENCES.out.gff_gtf
- hisat2 = REFERENCES.out.hisat2
- hisat2_splice_sites = REFERENCES.out.hisat2_splice_sites
- intervals = REFERENCES.out.intervals_bed
- kallisto = REFERENCES.out.kallisto
- known_indels_vcf_tbi = REFERENCES.out.known_indels_vcf_tbi
- known_snps_vcf_tbi = REFERENCES.out.known_snps_vcf_tbi
- msisensorpro = REFERENCES.out.msisensorpro
- rsem = REFERENCES.out.rsem
- rsem_transcript_fasta = REFERENCES.out.rsem_transcript_fasta
- salmon = REFERENCES.out.salmon
- sizes = REFERENCES.out.sizes
- star = REFERENCES.out.star
- versions = REFERENCES.out.versions
+ bowtie1_index = REFERENCES.out.bowtie1_index
+ bowtie2_index = REFERENCES.out.bowtie2_index
+ bwamem1_index = REFERENCES.out.bwamem1_index
+ bwamem2_index = REFERENCES.out.bwamem2_index
+ dragmap_hashmap = REFERENCES.out.dragmap_hashmap
+ fasta = REFERENCES.out.fasta
+ fasta_dict = REFERENCES.out.fasta_dict
+ fasta_fai = REFERENCES.out.fasta_fai
+ fasta_sizes = REFERENCES.out.fasta_sizes
+ gtf = REFERENCES.out.gtf
+ hisat2_index = REFERENCES.out.hisat2_index
+ splice_sites = REFERENCES.out.splice_sites
+ intervals_bed = REFERENCES.out.intervals_bed
+ kallisto_index = REFERENCES.out.kallisto_index
+ msisensorpro_list = REFERENCES.out.msisensorpro_list
+ rsem_index = REFERENCES.out.rsem_index
+ transcript_fasta = REFERENCES.out.transcript_fasta
+ salmon_index = REFERENCES.out.salmon_index
+ star_index = REFERENCES.out.star_index
+ vcf_tbi = REFERENCES.out.vcf_tbi
+ versions = REFERENCES.out.versions
}
diff --git a/subworkflows/local/create_align_index/main.nf b/subworkflows/local/create_align_index/main.nf
new file mode 100644
index 0000000..d087b9f
--- /dev/null
+++ b/subworkflows/local/create_align_index/main.nf
@@ -0,0 +1,67 @@
+include { BOWTIE_BUILD as BOWTIE1_BUILD } from '../../../modules/nf-core/bowtie/build'
+include { BOWTIE2_BUILD } from '../../../modules/nf-core/bowtie2/build'
+include { BWAMEM2_INDEX } from '../../../modules/nf-core/bwamem2/index'
+include { BWA_INDEX as BWAMEM1_INDEX } from '../../../modules/nf-core/bwa/index'
+include { DRAGMAP_HASHTABLE } from '../../../modules/nf-core/dragmap/hashtable'
+
+workflow CREATE_ALIGN_INDEX {
+ take:
+ fasta // channel: [meta, fasta]
+ run_bowtie1 // boolean: true/false
+ run_bowtie2 // boolean: true/false
+ run_bwamem1 // boolean: true/false
+ run_bwamem2 // boolean: true/false
+ run_dragmap // boolean: true/false
+
+ main:
+ bowtie1_index = Channel.empty()
+ bowtie2_index = Channel.empty()
+ bwamem1_index = Channel.empty()
+ bwamem2_index = Channel.empty()
+ dragmap_hashmap = Channel.empty()
+
+ versions = Channel.empty()
+
+ if (run_bowtie1) {
+ BOWTIE1_BUILD(fasta)
+
+ bowtie1_index = BOWTIE1_BUILD.out.index
+ versions = versions.mix(BOWTIE1_BUILD.out.versions)
+ }
+
+ if (run_bowtie2) {
+ BOWTIE2_BUILD(fasta)
+
+ bowtie2_index = BOWTIE2_BUILD.out.index
+ versions = versions.mix(BOWTIE2_BUILD.out.versions)
+ }
+
+ if (run_bwamem1) {
+ BWAMEM1_INDEX(fasta)
+
+ bwamem1_index = BWAMEM1_INDEX.out.index
+ versions = versions.mix(BWAMEM1_INDEX.out.versions)
+ }
+
+ if (run_bwamem2) {
+ BWAMEM2_INDEX(fasta)
+
+ bwamem2_index = BWAMEM2_INDEX.out.index
+ versions = versions.mix(BWAMEM2_INDEX.out.versions)
+ }
+
+ if (run_dragmap) {
+ DRAGMAP_HASHTABLE(fasta)
+
+ dragmap_hashmap = DRAGMAP_HASHTABLE.out.hashmap
+ versions = versions.mix(DRAGMAP_HASHTABLE.out.versions)
+ }
+
+ emit:
+ bowtie1_index // channel: [meta, BowtieIndex/]
+ bowtie2_index // channel: [meta, Bowtie2Index/]
+ bwamem1_index // channel: [meta, BWAmemIndex/]
+ bwamem2_index // channel: [meta, BWAmem2memIndex/]
+ dragmap_hashmap // channel: [meta, DragmapHashtable/]
+ versions // channel: [versions.yml]
+}
diff --git a/subworkflows/local/create_align_index_with_gff/main.nf b/subworkflows/local/create_align_index_with_gff/main.nf
new file mode 100644
index 0000000..0ca28be
--- /dev/null
+++ b/subworkflows/local/create_align_index_with_gff/main.nf
@@ -0,0 +1,132 @@
+include { GFFREAD } from '../../../modules/nf-core/gffread'
+include { HISAT2_BUILD } from '../../../modules/nf-core/hisat2/build'
+include { HISAT2_EXTRACTSPLICESITES } from '../../../modules/nf-core/hisat2/extractsplicesites'
+include { KALLISTO_INDEX } from '../../../modules/nf-core/kallisto/index'
+include { RSEM_PREPAREREFERENCE as MAKE_TRANSCRIPTS_FASTA } from '../../../modules/nf-core/rsem/preparereference'
+include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE_GENOME } from '../../../modules/nf-core/rsem/preparereference'
+include { SALMON_INDEX } from '../../../modules/nf-core/salmon/index'
+include { STAR_GENOMEGENERATE } from '../../../modules/nf-core/star/genomegenerate'
+
+workflow CREATE_ALIGN_INDEX_WITH_GFF {
+ take:
+ fasta // channel: [meta, fasta]
+ input_gff // channel: [meta, gff]
+ input_gtf // channel: [meta, gtf]
+ input_splice_sites // channel: [meta, splice_sites]
+ input_transcript_fasta // channel: [meta, transcript_fasta]
+ run_hisat2 // boolean: true/false
+ run_hisat2_extractsplicesites // boolean: true/false
+ run_kallisto // boolean: true/false
+ run_rsem // boolean: true/false
+ run_rsem_make_transcript_fasta // boolean: true/false
+ run_salmon // boolean: true/false
+ run_star // boolean: true/false
+
+ main:
+ gtf = Channel.empty()
+ hisat2_index = Channel.empty()
+ kallisto_index = Channel.empty()
+ rsem_index = Channel.empty()
+ salmon_index = Channel.empty()
+ splice_sites = Channel.empty()
+ star_index = Channel.empty()
+ transcript_fasta = Channel.empty()
+
+ versions = Channel.empty()
+
+ if (run_hisat2 || run_kallisto || run_rsem || run_rsem_make_transcript_fasta || run_salmon || run_star) {
+
+ GFFREAD(
+ input_gff,
+ []
+ )
+
+ versions = versions.mix(GFFREAD.out.versions)
+
+ gtf = input_gtf
+ .mix(GFFREAD.out.gtf)
+ .groupTuple()
+ .map { meta, file ->
+ return file[1] ? [meta, file[1]] : [meta, file]
+ }
+
+ if (run_hisat2 || run_hisat2_extractsplicesites) {
+ gtf_hisat2 = gtf.map { meta, map_gtf ->
+ return meta.run_hisat2 ? [meta, map_gtf] : null
+ }
+
+ HISAT2_EXTRACTSPLICESITES(gtf_hisat2)
+
+ splice_sites = input_splice_sites.mix(HISAT2_EXTRACTSPLICESITES.out.txt)
+
+ if (run_hisat2) {
+ HISAT2_BUILD(
+ fasta,
+ gtf,
+ splice_sites
+ )
+
+ hisat2_index = HISAT2_BUILD.out.index
+
+ versions = versions.mix(HISAT2_EXTRACTSPLICESITES.out.versions)
+ versions = versions.mix(HISAT2_BUILD.out.versions)
+ }
+ }
+
+ if (run_kallisto || run_rsem_make_transcript_fasta || run_salmon) {
+ fasta_make_transcripts_fasta = fasta.map { meta, map_fasta ->
+ return meta.run_rsem_make_transcript_fasta ? [meta, map_fasta] : null
+ }
+
+ MAKE_TRANSCRIPTS_FASTA(
+ fasta_make_transcripts_fasta,
+ gtf
+ )
+ versions = versions.mix(MAKE_TRANSCRIPTS_FASTA.out.versions)
+
+ transcript_fasta = input_transcript_fasta.mix(MAKE_TRANSCRIPTS_FASTA.out.transcript_fasta)
+
+ if (run_kallisto) {
+ KALLISTO_INDEX(transcript_fasta)
+
+ kallisto_index = KALLISTO_INDEX.out.index
+ versions = versions.mix(KALLISTO_INDEX.out.versions)
+ }
+
+ if (run_salmon) {
+ SALMON_INDEX(
+ fasta,
+ transcript_fasta
+ )
+
+ salmon_index = SALMON_INDEX.out.index
+ versions = versions.mix(SALMON_INDEX.out.versions)
+ }
+ }
+
+ if (run_rsem) {
+ RSEM_PREPAREREFERENCE_GENOME(fasta, gtf)
+
+ rsem_index = RSEM_PREPAREREFERENCE_GENOME.out.index
+ versions = versions.mix(RSEM_PREPAREREFERENCE_GENOME.out.versions)
+ }
+
+ if (run_star) {
+ STAR_GENOMEGENERATE(fasta, gtf)
+
+ star_index = STAR_GENOMEGENERATE.out.index
+ versions = versions.mix(STAR_GENOMEGENERATE.out.versions)
+ }
+ }
+
+ emit:
+ gtf // channel: [meta, gtf]
+ hisat2_index // channel: [meta, Hisat2Index/]
+ kallisto_index // channel: [meta, KallistoIndex]
+ rsem_index // channel: [meta, RSEMIndex/]
+ salmon_index // channel: [meta, SalmonIndex/]
+ splice_sites // channel: [meta, *.splice_sites.txt]
+ star_index // channel: [meta, STARIndex/]
+ transcript_fasta // channel: [meta, *.transcripts.fasta]
+ versions // channel: [versions.yml]
+}
diff --git a/subworkflows/local/index_fasta/main.nf b/subworkflows/local/index_fasta/main.nf
new file mode 100644
index 0000000..ab8e9b5
--- /dev/null
+++ b/subworkflows/local/index_fasta/main.nf
@@ -0,0 +1,72 @@
+include { GATK4_CREATESEQUENCEDICTIONARY } from '../../../modules/nf-core/gatk4/createsequencedictionary'
+include { GAWK as BUILD_INTERVALS } from '../../../modules/nf-core/gawk'
+include { MSISENSORPRO_SCAN } from '../../../modules/nf-core/msisensorpro/scan'
+include { SAMTOOLS_FAIDX } from '../../../modules/nf-core/samtools/faidx'
+
+workflow INDEX_FASTA {
+ take:
+ fasta // channel: [meta, fasta]
+ input_fasta_fai // channel: [meta, fasta_fai]
+ run_createsequencedictionary // boolean: true/false
+ run_faidx // boolean: true/false
+ run_intervals // boolean: true/false
+ run_msisensorpro // boolean: true/false
+ run_sizes // boolean: true/false
+
+ main:
+ intervals_bed = Channel.empty()
+ fasta_fai = Channel.empty()
+ fasta_dict = Channel.empty()
+ fasta_sizes = Channel.empty()
+ msisensorpro_list = Channel.empty()
+
+ versions = Channel.empty()
+
+ if (run_createsequencedictionary) {
+ GATK4_CREATESEQUENCEDICTIONARY(fasta)
+
+ fasta_dict = GATK4_CREATESEQUENCEDICTIONARY.out.dict
+ versions = versions.mix(GATK4_CREATESEQUENCEDICTIONARY.out.versions)
+ }
+
+ if (run_faidx || run_intervals || run_sizes) {
+ fasta_samtools = fasta.map { meta, map_fasta ->
+ return meta.run_faidx ? [meta, map_fasta] : null
+ }
+
+ SAMTOOLS_FAIDX(
+ fasta_samtools,
+ [[id: 'no_fai'], []],
+ run_sizes
+ )
+
+ fasta_fai = input_fasta_fai.mix(SAMTOOLS_FAIDX.out.fai)
+ fasta_sizes = SAMTOOLS_FAIDX.out.sizes
+ versions = versions.mix(SAMTOOLS_FAIDX.out.versions)
+
+ if (run_intervals) {
+ fasta_fai_intervals = fasta_fai.map { meta, map_fasta_fai ->
+ return meta.run_intervals ? [meta, map_fasta_fai] : null
+ }
+
+ BUILD_INTERVALS(fasta_fai_intervals, [])
+ intervals_bed = BUILD_INTERVALS.out.output
+ versions = versions.mix(BUILD_INTERVALS.out.versions)
+ }
+ }
+
+ if (run_msisensorpro) {
+ MSISENSORPRO_SCAN(fasta)
+
+ msisensorpro_list = MSISENSORPRO_SCAN.out.list
+ versions = versions.mix(MSISENSORPRO_SCAN.out.versions)
+ }
+
+ emit:
+ fasta_dict // channel: [meta, *.fa(sta).dict]
+ fasta_fai // channel: [meta, *.fa(sta).fai]
+ fasta_sizes // channel: [meta, *.fa(sta).sizes]
+ intervals_bed // channel: [meta, *.bed]
+ msisensorpro_list // channel: [meta, *.list]
+ versions // channel: [versions.yml]
+}
diff --git a/subworkflows/local/index_vcf/main.nf b/subworkflows/local/index_vcf/main.nf
new file mode 100644
index 0000000..48bab94
--- /dev/null
+++ b/subworkflows/local/index_vcf/main.nf
@@ -0,0 +1,23 @@
+include { TABIX_TABIX } from '../../../modules/nf-core/tabix/tabix'
+
+workflow INDEX_VCF {
+ take:
+ vcf // channel: [meta, vcf]
+ run_tabix // boolean: true/false
+
+ main:
+ vcf_tbi = Channel.empty()
+ versions = Channel.empty()
+
+
+ if (run_tabix) {
+ TABIX_TABIX(vcf)
+
+ vcf_tbi = TABIX_TABIX.out.tbi
+ versions = TABIX_TABIX.out.versions
+ }
+
+ emit:
+ vcf_tbi // channel: [meta, *.vcf.tbi]
+ versions // channel: [versions.yml]
+}
diff --git a/subworkflows/local/samplesheet_to_channel/main.nf b/subworkflows/local/samplesheet_to_channel/main.nf
new file mode 100644
index 0000000..611771c
--- /dev/null
+++ b/subworkflows/local/samplesheet_to_channel/main.nf
@@ -0,0 +1,60 @@
+workflow SAMPLESHEET_TO_CHANNEL {
+ take:
+ reference // channel: [meta, intervals_bed, fasta, fasta_dict, fasta_fai, fasta_sizes, gff, gtf, splice_sites, transcript_fasta, vcf, readme, bed12, mito_name, macs_gsize]
+
+ main:
+
+ intervals_bed = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_intervals_bed ? [meta, input_intervals_bed] : null
+ }
+
+ fasta = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_fasta ? [meta + [run_faidx: input_fasta_fai && input_fasta_sizes ? false : true] + [run_intervals: input_intervals_bed ? false : true] + [run_rsem_make_transcript_fasta: input_transcript_fasta ? false : true], input_fasta] : null
+ }
+
+ fasta_dict = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_fasta_dict ? [meta, input_fasta_dict] : null
+ }
+
+ fasta_fai = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_fasta_fai ? [meta + [run_intervals: input_intervals_bed ? false : true], input_fasta_fai] : null
+ }
+
+ fasta_sizes = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_fasta_sizes ? [meta, input_fasta_sizes] : null
+ }
+
+ gff = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_gff && !input_gtf ? [meta + [run_hisat2: input_splice_sites ? false : true], input_gff] : null
+ }
+
+ gtf = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_gtf ? [meta + [run_hisat2: input_splice_sites ? false : true], input_gtf] : null
+ }
+
+ splice_sites = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_splice_sites ? [meta, input_splice_sites] : null
+ }
+
+ transcript_fasta = reference.map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_transcript_fasta ? [meta, input_transcript_fasta] : null
+ }
+
+ vcf = reference
+ .map { meta, input_intervals_bed, input_fasta, input_fasta_dict, input_fasta_fai, input_fasta_sizes, input_gff, input_gtf, input_splice_sites, input_transcript_fasta, input_vcf, input_readme, input_bed12, input_mito_name, input_macs_gsize ->
+ return input_vcf ? [meta, file(input_vcf)] : null
+ }
+ .transpose()
+
+ emit:
+ intervals_bed
+ fasta
+ fasta_dict
+ fasta_fai
+ fasta_sizes
+ gff
+ gtf
+ splice_sites
+ transcript_fasta
+ vcf
+}
diff --git a/subworkflows/local/utils_nfcore_references_pipeline/main.nf b/subworkflows/local/utils_nfcore_references_pipeline/main.nf
index c6b006c..7885e2d 100644
--- a/subworkflows/local/utils_nfcore_references_pipeline/main.nf
+++ b/subworkflows/local/utils_nfcore_references_pipeline/main.nf
@@ -8,14 +8,14 @@
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
-include { UTILS_NFSCHEMA_PLUGIN } from '../../nf-core/utils_nfschema_plugin'
-include { paramsSummaryMap } from 'plugin/nf-schema'
-include { samplesheetToList } from 'plugin/nf-schema'
-include { completionEmail } from '../../nf-core/utils_nfcore_pipeline'
-include { completionSummary } from '../../nf-core/utils_nfcore_pipeline'
-include { imNotification } from '../../nf-core/utils_nfcore_pipeline'
-include { UTILS_NFCORE_PIPELINE } from '../../nf-core/utils_nfcore_pipeline'
-include { UTILS_NEXTFLOW_PIPELINE } from '../../nf-core/utils_nextflow_pipeline'
+include { UTILS_NFSCHEMA_PLUGIN } from '../../nf-core/utils_nfschema_plugin'
+include { paramsSummaryMap } from 'plugin/nf-schema'
+include { samplesheetToList } from 'plugin/nf-schema'
+include { completionEmail } from '../../nf-core/utils_nfcore_pipeline'
+include { completionSummary } from '../../nf-core/utils_nfcore_pipeline'
+include { imNotification } from '../../nf-core/utils_nfcore_pipeline'
+include { UTILS_NFCORE_PIPELINE } from '../../nf-core/utils_nfcore_pipeline'
+include { UTILS_NEXTFLOW_PIPELINE } from '../../nf-core/utils_nextflow_pipeline'
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -24,7 +24,6 @@ include { UTILS_NEXTFLOW_PIPELINE } from '../../nf-core/utils_nextflow_pipelin
*/
workflow PIPELINE_INITIALISATION {
-
take:
version // boolean: Display version and exit
validate_params // boolean: Boolean whether to validate parameters against the schema at runtime
@@ -40,7 +39,7 @@ workflow PIPELINE_INITIALISATION {
//
// Print version and exit if required and dump pipeline parameters to JSON file
//
- UTILS_NEXTFLOW_PIPELINE (
+ UTILS_NEXTFLOW_PIPELINE(
version,
true,
outdir,
@@ -50,7 +49,7 @@ workflow PIPELINE_INITIALISATION {
//
// Validate parameters and generate parameter summary to stdout
//
- UTILS_NFSCHEMA_PLUGIN (
+ UTILS_NFSCHEMA_PLUGIN(
workflow,
validate_params,
null
@@ -59,14 +58,14 @@ workflow PIPELINE_INITIALISATION {
//
// Check config provided to the pipeline
//
- UTILS_NFCORE_PIPELINE (
+ UTILS_NFCORE_PIPELINE(
nextflow_cli_args
)
//
// Create channel from input file provided through params.input
//
- ch_samplesheet = Channel.fromList(samplesheetToList(params.input, "${projectDir}/assets/schema_input.json"))
+ ch_samplesheet = Channel.fromList(samplesheetToList(input, "${projectDir}/assets/schema_input.json"))
emit:
samplesheet = ch_samplesheet
@@ -80,7 +79,6 @@ workflow PIPELINE_INITIALISATION {
*/
workflow PIPELINE_COMPLETION {
-
take:
email // string: email address
email_on_fail // string: email address sent on pipeline failure
@@ -116,7 +114,7 @@ workflow PIPELINE_COMPLETION {
}
workflow.onError {
- log.error "Pipeline failed. Please refer to troubleshooting docs: https://nf-co.re/docs/usage/troubleshooting"
+ log.error("Pipeline failed. Please refer to troubleshooting docs: https://nf-co.re/docs/usage/troubleshooting")
}
}
@@ -133,11 +131,11 @@ def toolCitationText() {
// Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "",
// Uncomment function in methodsDescriptionText to render in MultiQC report
def citation_text = [
- "Tools used in the workflow included:",
- "FastQC (Andrews 2010),",
- "MultiQC (Ewels et al. 2016)",
- "."
- ].join(' ').trim()
+ "Tools used in the workflow included:",
+ "FastQC (Andrews 2010),",
+ "MultiQC (Ewels et al. 2016)",
+ "."
+ ].join(' ').trim()
return citation_text
}
@@ -147,9 +145,9 @@ def toolBibliographyText() {
// Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Author (2023) Pub name, Journal, DOI" : "",
// Uncomment function in methodsDescriptionText to render in MultiQC report
def reference_text = [
- "Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).",
- "Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354"
- ].join(' ').trim()
+ "Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).",
+ "Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354"
+ ].join(' ').trim()
return reference_text
}
@@ -171,7 +169,10 @@ def methodsDescriptionText(mqc_methods_yaml) {
temp_doi_ref += "(doi: ${doi_ref.replace("https://doi.org/", "").replace(" ", "")}), "
}
meta["doi_text"] = temp_doi_ref.substring(0, temp_doi_ref.length() - 2)
- } else meta["doi_text"] = ""
+ }
+ else {
+ meta["doi_text"] = ""
+ }
meta["nodoi_text"] = meta.manifest_map.doi ? "" : "If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used. "
// Tool references
@@ -185,9 +186,8 @@ def methodsDescriptionText(mqc_methods_yaml) {
def methods_text = mqc_methods_yaml.text
- def engine = new groovy.text.SimpleTemplateEngine()
+ def engine = new groovy.text.SimpleTemplateEngine()
def description_html = engine.createTemplate(methods_text).make(meta)
return description_html.toString()
}
-
diff --git a/tests/multiple.nf.test.snap b/tests/multiple.nf.test.snap
index 126b0cd..72f8eaa 100644
--- a/tests/multiple.nf.test.snap
+++ b/tests/multiple.nf.test.snap
@@ -3,7 +3,7 @@
"content": [
5,
{
- "TABIX_KNOWN_INDELS": {
+ "TABIX_TABIX": {
"tabix": 1.2
},
"Workflow": {
@@ -46,7 +46,7 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
- "timestamp": "2024-11-28T18:25:56.49079277"
+ "timestamp": "2024-12-02T12:09:53.42046409"
},
"Run with profile test for multiple | --input assets/genomes/test/default_multiple.yml": {
"content": [
@@ -135,6 +135,6 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
- "timestamp": "2024-11-28T16:56:49.442608122"
+ "timestamp": "2024-12-02T12:27:31.034085088"
}
-}
+}
\ No newline at end of file
diff --git a/tests/sarek.nf.test.snap b/tests/sarek.nf.test.snap
index 3dcda1c..b51a2a0 100644
--- a/tests/sarek.nf.test.snap
+++ b/tests/sarek.nf.test.snap
@@ -1,7 +1,7 @@
{
"Run with profile test for sarek | --input assets/genomes/test/pipelines/sarek.yml": {
"content": [
- 12,
+ 11,
{
"BUILD_INTERVALS": {
"gawk": "5.3.0"
@@ -24,16 +24,7 @@
"SAMTOOLS_FAIDX": {
"samtools": 1.21
},
- "TABIX_DBSNP": {
- "tabix": 1.2
- },
- "TABIX_GERMLINE_RESOURCE": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_INDELS": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_SNPS": {
+ "TABIX_TABIX": {
"tabix": 1.2
},
"Workflow": {
@@ -120,6 +111,6 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
- "timestamp": "2024-11-28T15:48:25.039272086"
+ "timestamp": "2024-12-02T11:21:36.124482055"
}
}
\ No newline at end of file
diff --git a/tests/tabix.nf.test.snap b/tests/tabix.nf.test.snap
index 59c076f..1cb2417 100644
--- a/tests/tabix.nf.test.snap
+++ b/tests/tabix.nf.test.snap
@@ -1,18 +1,9 @@
{
"Run with profile test with tabix | --input assets/genomes/test/default_extended.yml": {
"content": [
- 5,
+ 4,
{
- "TABIX_DBSNP": {
- "tabix": 1.2
- },
- "TABIX_GERMLINE_RESOURCE": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_INDELS": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_SNPS": {
+ "TABIX_TABIX": {
"tabix": 1.2
},
"Workflow": {
@@ -51,22 +42,13 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
- "timestamp": "2024-11-28T14:57:48.388939938"
+ "timestamp": "2024-12-02T11:21:55.801035083"
},
"Run with profile test with tabix | --input assets/genomes/test/default_full.yml": {
"content": [
- 5,
+ 4,
{
- "TABIX_DBSNP": {
- "tabix": 1.2
- },
- "TABIX_GERMLINE_RESOURCE": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_INDELS": {
- "tabix": 1.2
- },
- "TABIX_KNOWN_SNPS": {
+ "TABIX_TABIX": {
"tabix": 1.2
},
"Workflow": {
@@ -105,6 +87,6 @@
"nf-test": "0.9.2",
"nextflow": "24.10.2"
},
- "timestamp": "2024-11-28T14:58:13.905623169"
+ "timestamp": "2024-12-02T11:22:15.160055968"
}
}
diff --git a/workflows/references/main.nf b/workflows/references/main.nf
index 53fe1c5..298d44f 100644
--- a/workflows/references/main.nf
+++ b/workflows/references/main.nf
@@ -1,362 +1,139 @@
-include { BOWTIE2_BUILD } from '../../modules/nf-core/bowtie2/build'
-include { BOWTIE_BUILD as BOWTIE1_BUILD } from '../../modules/nf-core/bowtie/build'
-include { BWAMEM2_INDEX } from '../../modules/nf-core/bwamem2/index'
-include { BWA_INDEX as BWAMEM1_INDEX } from '../../modules/nf-core/bwa/index'
-include { DRAGMAP_HASHTABLE } from '../../modules/nf-core/dragmap/hashtable'
-include { GATK4_CREATESEQUENCEDICTIONARY } from '../../modules/nf-core/gatk4/createsequencedictionary'
-include { GAWK as BUILD_INTERVALS } from '../../modules/nf-core/gawk'
-include { GFFREAD } from '../../modules/nf-core/gffread'
-include { HISAT2_BUILD } from '../../modules/nf-core/hisat2/build'
-include { HISAT2_EXTRACTSPLICESITES } from '../../modules/nf-core/hisat2/extractsplicesites'
-include { KALLISTO_INDEX } from '../../modules/nf-core/kallisto/index'
-include { MSISENSORPRO_SCAN } from '../../modules/nf-core/msisensorpro/scan'
-include { RSEM_PREPAREREFERENCE as MAKE_TRANSCRIPTS_FASTA } from '../../modules/nf-core/rsem/preparereference'
-include { RSEM_PREPAREREFERENCE as RSEM_PREPAREREFERENCE_GENOME } from '../../modules/nf-core/rsem/preparereference'
-include { SALMON_INDEX } from '../../modules/nf-core/salmon/index'
-include { SAMTOOLS_FAIDX } from '../../modules/nf-core/samtools/faidx'
-include { STAR_GENOMEGENERATE } from '../../modules/nf-core/star/genomegenerate'
-include { TABIX_TABIX as TABIX_DBSNP } from '../../modules/nf-core/tabix/tabix'
-include { TABIX_TABIX as TABIX_GERMLINE_RESOURCE } from '../../modules/nf-core/tabix/tabix'
-include { TABIX_TABIX as TABIX_KNOWN_INDELS } from '../../modules/nf-core/tabix/tabix'
-include { TABIX_TABIX as TABIX_KNOWN_SNPS } from '../../modules/nf-core/tabix/tabix'
-
-// include { BBMAP_BBSPLIT } from '../../modules/nf-core/bbmap/bbsplit'
-// include { CUSTOM_CATADDITIONALFASTA } from '../../modules/nf-core/custom/catadditionalfasta'
-// include { SORTMERNA as SORTMERNA_INDEX } from '../../modules/nf-core/sortmerna'
+include { CREATE_ALIGN_INDEX } from '../../subworkflows/local/create_align_index'
+include { CREATE_ALIGN_INDEX_WITH_GFF } from '../../subworkflows/local/create_align_index_with_gff'
+include { INDEX_FASTA } from '../../subworkflows/local/index_fasta'
+include { INDEX_VCF } from '../../subworkflows/local/index_vcf'
+include { SAMPLESHEET_TO_CHANNEL } from '../../subworkflows/local/samplesheet_to_channel'
workflow REFERENCES {
take:
- reference // fasta, gff, gtf, splice_sites, transcript_fasta
+ reference // fasta, gff, gtf, splice_sites, transcript_fasta, vcf
tools // bowtie|bowtie2|bwamem1|bwamem2|createsequencedictionary|dragmap|faidx|gffread|intervals|hisat2|hisat2_extractsplicesites|kallisto|msisensorpro|rsem|rsem_make_transcripts_fasta|salmon|star|tabix
main:
- ch_bowtie1 = Channel.empty()
- ch_bowtie2 = Channel.empty()
- ch_dbsnp_vcf_tbi = Channel.empty()
- ch_fasta_fai = Channel.empty()
- ch_germline_resource_vcf_tbi = Channel.empty()
- ch_gff_gtf = Channel.empty()
- ch_hisat2 = Channel.empty()
- ch_hisat2_splice_sites = Channel.empty()
- ch_intervals_bed = Channel.empty()
- ch_kallisto = Channel.empty()
- ch_known_indels_vcf_tbi = Channel.empty()
- ch_known_snps_vcf_tbi = Channel.empty()
- ch_msisensorpro = Channel.empty()
- ch_rsem = Channel.empty()
- ch_rsem_transcript_fasta = Channel.empty()
- ch_salmon = Channel.empty()
- ch_sizes = Channel.empty()
- ch_star = Channel.empty()
versions = Channel.empty()
- input = reference.multiMap { meta, intervals_bed, fasta, fasta_dict, fasta_fai, fasta_sizes, gff, gtf, splice_sites, transcript_fasta, dbsnp_vcf, known_snps_vcf, known_indels_vcf, germline_resource_vcf, readme, bed12, mito_name, macs_gsize ->
- fasta: [meta, fasta]
- fasta_dict: [meta, fasta_dict]
- fasta_fai: [meta, fasta_fai]
- fasta_sizes: [meta, fasta_sizes]
- gff: [meta, gff]
- gtf: [meta, gtf]
- splice_sites: [meta, splice_sites]
- transcript_fasta: [meta, transcript_fasta]
- readme: [meta, readme]
- bed12: [meta, bed12]
- mito_name: [meta, mito_name]
- macs_gsize: [meta, macs_gsize]
- intervals_bed: [meta, intervals_bed]
- bwamem1_fasta: tools.contains('bwamem1') && fasta ? [meta, file(fasta)] : [[:], []]
- bwamem2_fasta: tools.contains('bwamem2') && fasta ? [meta, file(fasta)] : [[:], []]
- createsequencedictionary_fasta: tools.contains('createsequencedictionary') && fasta ? [meta, file(fasta)] : [[:], []]
- dragmap_fasta: tools.contains('dragmap') && fasta ? [meta, file(fasta)] : [[:], []]
- fasta_samtools: ((tools.contains('faidx') || tools.contains('sizes')) && !(fasta_fai || fasta_sizes) && fasta) || (tools.contains('intervals') && !(fasta_fai || intervals_bed)) ? [meta, file(fasta)] : [[:], []]
- dbsnp_vcf: tools.contains('tabix') && dbsnp_vcf ? [meta, file(dbsnp_vcf)] : [[:], []]
- known_snps_vcf: tools.contains('tabix') && known_snps_vcf ? [meta, file(known_snps_vcf)] : [[:], []]
- known_indels_vcf: tools.contains('tabix') && known_indels_vcf ? [meta, file(known_indels_vcf)] : [[:], []]
- germline_resource_vcf: tools.contains('tabix') && germline_resource_vcf ? [meta, file(germline_resource_vcf)] : [[:], []]
- gff_gffread: !gtf && gff && (tools.contains('gffread') || tools.contains('hisat2') || tools.contains('kallisto') || tools.contains('rsem') || tools.contains('salmon') || tools.contains('star')) ? [meta, file(gff)] : [[:], []]
- }
- // I should be able to output null instead of `[[:], []] and have that registered as an empty channel and not trigger downstream processes
- // but not working currently
-
- if (tools && tools.split(',').contains('bowtie1')) {
- BOWTIE1_BUILD(input.fasta)
-
- ch_bowtie1 = BOWTIE1_BUILD.out.index
- versions = versions.mix(BOWTIE1_BUILD.out.versions)
- }
-
- if (tools && tools.split(',').contains('bowtie2')) {
- BOWTIE2_BUILD(input.fasta)
-
- ch_bowtie2 = BOWTIE2_BUILD.out.index
- versions = versions.mix(BOWTIE2_BUILD.out.versions)
- }
-
- // the whole map -> null should be removed once I managed to make it work properly
- BWAMEM1_INDEX(
- input.bwamem1_fasta.map { meta, file ->
- return file ? [meta, file] : null
- }
- )
- ch_bwamem1 = BWAMEM1_INDEX.out.index
-
- BWAMEM2_INDEX(
- input.bwamem2_fasta.map { meta, file ->
- return file ? [meta, file] : null
- }
- )
- ch_bwamem2 = BWAMEM2_INDEX.out.index
-
- DRAGMAP_HASHTABLE(
- input.dragmap_fasta.map { meta, file ->
- return file ? [meta, file] : null
- }
- )
- ch_dragmap = DRAGMAP_HASHTABLE.out.hashmap
-
- GATK4_CREATESEQUENCEDICTIONARY(
- input.createsequencedictionary_fasta.map { meta, file ->
- return file ? [meta, file] : null
- }
- )
- ch_fasta_dict = GATK4_CREATESEQUENCEDICTIONARY.out.dict
-
- SAMTOOLS_FAIDX(
- input.fasta_samtools.map { meta, file ->
- return file ? [meta, file] : null
- },
- [[id: 'no_fai'], []],
- tools.contains('sizes')
- )
-
- // TODO: be smarter about input assets
- // Here we either mix+GT an empty channel (either no output or no input faidx) with the faidx return faidx
- // And we filter out the empty value
- ch_fasta_fai = input.fasta_fai
- .mix(SAMTOOLS_FAIDX.out.fai)
- .groupTuple()
- .map { meta, file ->
- return file[1] ? [meta, file[1]] : [meta, file]
- }
-
- // TODO: be smarter about input assets
- // Here we either mix+GT an empty channel (either no output or no input sizes) with the sizes return sizes
- // And we filter out the empty value
- ch_sizes = input.fasta_sizes
- .mix(SAMTOOLS_FAIDX.out.sizes)
- .groupTuple()
- .map { meta, file ->
- return file[1] ? [meta, file[1]] : [meta, file]
- }
-
- ch_fasta_fai_intervals_bed = input.intervals_bed
- .mix(ch_fasta_fai)
- .groupTuple()
- .map { meta, file ->
- return file[0] || !tools.contains('intervals') ? null : file[1] ? [meta, file[1]] : [meta, file]
- }
-
- BUILD_INTERVALS(ch_fasta_fai_intervals_bed, [])
- ch_intervals_bed = BUILD_INTERVALS.out.output
-
- TABIX_DBSNP(
- input.dbsnp_vcf.map { meta, file ->
- return file ? [meta, file] : null
- }
- )
- ch_dbsnp_vcf_tbi = TABIX_DBSNP.out.tbi
-
- TABIX_KNOWN_SNPS(
- input.known_snps_vcf.map { meta, file ->
- return file ? [meta, file] : null
- }
+ SAMPLESHEET_TO_CHANNEL(reference)
+
+ intervals_bed = SAMPLESHEET_TO_CHANNEL.out.intervals_bed
+ fasta = SAMPLESHEET_TO_CHANNEL.out.fasta
+ fasta_dict = SAMPLESHEET_TO_CHANNEL.out.fasta_dict
+ fasta_fai = SAMPLESHEET_TO_CHANNEL.out.fasta_fai
+ fasta_sizes = SAMPLESHEET_TO_CHANNEL.out.fasta_sizes
+ gff = SAMPLESHEET_TO_CHANNEL.out.gff
+ gtf = SAMPLESHEET_TO_CHANNEL.out.gtf
+ splice_sites = SAMPLESHEET_TO_CHANNEL.out.splice_sites
+ transcript_fasta = SAMPLESHEET_TO_CHANNEL.out.transcript_fasta
+ vcf = SAMPLESHEET_TO_CHANNEL.out.vcf
+
+ CREATE_ALIGN_INDEX(
+ fasta,
+ tools.split(',').contains('bowtie1'),
+ tools.split(',').contains('bowtie2'),
+ tools.split(',').contains('bwamem1'),
+ tools.split(',').contains('bwamem2'),
+ tools.split(',').contains('dragmap')
)
- ch_known_snps_vcf_tbi = TABIX_KNOWN_SNPS.out.tbi
- TABIX_KNOWN_INDELS(
- input.known_indels_vcf.map { meta, file ->
- return file ? [meta, file] : null
- }.transpose()
+ CREATE_ALIGN_INDEX_WITH_GFF(
+ fasta,
+ gff,
+ gtf,
+ splice_sites,
+ transcript_fasta,
+ tools.split(',').contains('hisat2'),
+ tools.split(',').contains('hisat2_extractsplicesites'),
+ tools.split(',').contains('kallisto'),
+ tools.split(',').contains('rsem'),
+ tools.split(',').contains('rsem_make_transcript_fasta'),
+ tools.split(',').contains('salmon'),
+ tools.split(',').contains('star')
)
- ch_known_indels_vcf_tbi = TABIX_KNOWN_INDELS.out.tbi
- TABIX_GERMLINE_RESOURCE(
- input.germline_resource_vcf.map { meta, file ->
- return file ? [meta, file] : null
- }
+ INDEX_FASTA(
+ fasta,
+ fasta_fai,
+ tools.split(',').contains('createsequencedictionary'),
+ tools.split(',').contains('faidx'),
+ tools.split(',').contains('intervals'),
+ tools.split(',').contains('msisensorpro'),
+ tools.split(',').contains('sizes')
)
- ch_germline_resource_vcf_tbi = TABIX_GERMLINE_RESOURCE.out.tbi
- GFFREAD(
- input.gff_gffread.map { meta, file ->
- return file ? [meta, file] : null
- },
- []
+ INDEX_VCF(
+ vcf,
+ tools.split(',').contains('tabix')
)
- ch_gff_gtf = input.gtf
- .mix(GFFREAD.out.gtf)
- .groupTuple()
- .map { meta, file ->
- return file[1] ? [meta, file[1]] : [meta, file]
- }
-
- if (tools.contains('hisat2')) {
- // TODO: be smarter about input assets
- // Here we either return an empty channel if we have a splice_sites so that HISAT2_EXTRACTSPLICESITES is not triggered
- // Or we return the provided gtf so that HISAT2_EXTRACTSPLICESITES is run
- ch_gtf_hisat2 = ch_gff_gtf
- .join(input.splice_sites)
- .groupTuple()
- .map { meta, gtf, splice_sites ->
- return splice_sites[0][0] ? null : [meta, gtf]
- }
-
- HISAT2_EXTRACTSPLICESITES(ch_gtf_hisat2)
- versions = versions.mix(HISAT2_EXTRACTSPLICESITES.out.versions)
-
- // TODO: be smarter about input assets
- // Here we either mix+GT an empty channel (either no output or no input splice_sites) with the splice_sites return splice_sites
- // And we filter out the empty value
- ch_hisat2_splice_sites = input.splice_sites
- .mix(HISAT2_EXTRACTSPLICESITES.out.txt)
- .groupTuple()
- .map { meta, txt ->
- return txt[1] ? [meta, txt[1]] : [meta, txt]
- }
-
- if (tools && tools.split(',').contains('hisat2')) {
- HISAT2_BUILD(input.fasta, ch_gff_gtf, ch_hisat2_splice_sites)
-
- ch_hisat2 = HISAT2_BUILD.out.index
- versions = versions.mix(HISAT2_BUILD.out.versions)
- }
- }
-
- if (tools.contains('kallisto') || tools.contains('rsem_make_transcript_fasta') || tools.contains('salmon')) {
- // TODO: be smarter about input assets
- // Here we either return an empty channel if we have a transcript_fasta so that MAKE_TRANSCRIPTS_FASTA is not triggered
- // Or we return the provided gtf so that MAKE_TRANSCRIPTS_FASTA is run
- ch_gtf_rsem = ch_gff_gtf
- .join(input.transcript_fasta)
- .groupTuple()
- .map { meta, gtf, transcript_fasta ->
- return transcript_fasta[0][0] ? null : [meta, gtf]
- }
-
- MAKE_TRANSCRIPTS_FASTA(input.fasta, ch_gtf_rsem)
- versions = versions.mix(MAKE_TRANSCRIPTS_FASTA.out.versions)
-
- // TODO: be smarter about input assets
- // Here we either mix+GT an empty channel (either no output or no input transcript_fasta) with the transcript_fasta return transcript_fasta
- // And we filter out the empty value
- ch_rsem_transcript_fasta = input.transcript_fasta
- .mix(MAKE_TRANSCRIPTS_FASTA.out.transcript_fasta)
- .groupTuple()
- .map { meta, txt ->
- return txt[1] ? [meta, txt[1]] : [meta, txt]
- }
-
- if (tools.contains('kallisto')) {
- KALLISTO_INDEX(ch_rsem_transcript_fasta)
-
- ch_kallisto = KALLISTO_INDEX.out.index
- versions = versions.mix(KALLISTO_INDEX.out.versions)
- }
-
- if (tools.contains('salmon')) {
- SALMON_INDEX(input.fasta, ch_rsem_transcript_fasta)
-
- ch_salmon = SALMON_INDEX.out.index
- versions = versions.mix(SALMON_INDEX.out.versions)
- }
- }
-
- if (tools.contains('msisensorpro')) {
- MSISENSORPRO_SCAN(input.fasta)
-
- ch_msisensorpro = MSISENSORPRO_SCAN.out.list
- versions = versions.mix(MSISENSORPRO_SCAN.out.versions)
- }
-
- if (tools && tools.split(',').contains('rsem')) {
- RSEM_PREPAREREFERENCE_GENOME(input.fasta, ch_gff_gtf)
-
- ch_rsem = RSEM_PREPAREREFERENCE_GENOME.out.index
- versions = versions.mix(RSEM_PREPAREREFERENCE_GENOME.out.versions)
- }
-
- if (tools.contains('star')) {
- STAR_GENOMEGENERATE(input.fasta, ch_gff_gtf)
-
- ch_star = STAR_GENOMEGENERATE.out.index
- versions = versions.mix(STAR_GENOMEGENERATE.out.versions)
- }
-
- // versions
- versions = versions.mix(BUILD_INTERVALS.out.versions)
- versions = versions.mix(BWAMEM1_INDEX.out.versions)
- versions = versions.mix(BWAMEM2_INDEX.out.versions)
- versions = versions.mix(DRAGMAP_HASHTABLE.out.versions)
- versions = versions.mix(GATK4_CREATESEQUENCEDICTIONARY.out.versions)
- versions = versions.mix(GFFREAD.out.versions)
- versions = versions.mix(SAMTOOLS_FAIDX.out.versions)
- versions = versions.mix(TABIX_DBSNP.out.versions)
- versions = versions.mix(TABIX_GERMLINE_RESOURCE.out.versions)
- versions = versions.mix(TABIX_KNOWN_INDELS.out.versions)
- versions = versions.mix(TABIX_KNOWN_SNPS.out.versions)
-
- // input fasta
- ch_fasta = input.fasta
+ bowtie1_index = CREATE_ALIGN_INDEX.out.bowtie1_index
+ bowtie2_index = CREATE_ALIGN_INDEX.out.bowtie2_index
+ bwamem1_index = CREATE_ALIGN_INDEX.out.bwamem1_index
+ bwamem2_index = CREATE_ALIGN_INDEX.out.bwamem2_index
+ dragmap_hashmap = CREATE_ALIGN_INDEX.out.dragmap_hashmap
+
+ gtf = gtf.mix(CREATE_ALIGN_INDEX_WITH_GFF.out.gtf)
+ hisat2_index = CREATE_ALIGN_INDEX_WITH_GFF.out.hisat2_index
+ splice_sites = splice_sites.mix(CREATE_ALIGN_INDEX_WITH_GFF.out.splice_sites)
+ kallisto_index = CREATE_ALIGN_INDEX_WITH_GFF.out.kallisto_index
+ rsem_index = CREATE_ALIGN_INDEX_WITH_GFF.out.rsem_index
+ transcript_fasta = transcript_fasta.mix(CREATE_ALIGN_INDEX_WITH_GFF.out.transcript_fasta)
+ salmon_index = CREATE_ALIGN_INDEX_WITH_GFF.out.salmon_index
+ star_index = CREATE_ALIGN_INDEX_WITH_GFF.out.star_index
+
+ fasta_dict = fasta_dict.mix(INDEX_FASTA.out.fasta_dict)
+ fasta_fai = fasta_fai.mix(INDEX_FASTA.out.fasta_fai)
+ intervals_bed = intervals_bed.mix(INDEX_FASTA.out.intervals_bed)
+ fasta_sizes = fasta_sizes.mix(INDEX_FASTA.out.fasta_sizes)
+ msisensorpro_list = INDEX_FASTA.out.msisensorpro_list
+
+ vcf_tbi = INDEX_VCF.out.vcf_tbi
+
+ versions = versions.mix(CREATE_ALIGN_INDEX.out.versions)
+ versions = versions.mix(CREATE_ALIGN_INDEX_WITH_GFF.out.versions)
+ versions = versions.mix(INDEX_FASTA.out.versions)
+ versions = versions.mix(INDEX_VCF.out.versions)
emit:
- bowtie1 = ch_bowtie1
- bowtie2 = ch_bowtie2
- bwamem1 = ch_bwamem1
- bwamem2 = ch_bwamem2
- dbsnp_vcf_tbi = ch_dbsnp_vcf_tbi
- dragmap = ch_dragmap
- fasta = ch_fasta
- fasta_dict = ch_fasta_dict
- fasta_fai = ch_fasta_fai
- germline_resource_vcf_tbi = ch_germline_resource_vcf_tbi
- gff_gtf = ch_gff_gtf
- hisat2 = ch_hisat2
- hisat2_splice_sites = ch_hisat2_splice_sites
- intervals_bed = ch_intervals_bed
- kallisto = ch_kallisto
- known_indels_vcf_tbi = ch_known_indels_vcf_tbi
- known_snps_vcf_tbi = ch_known_snps_vcf_tbi
- msisensorpro = ch_msisensorpro
- rsem = ch_rsem
- rsem_transcript_fasta = ch_rsem_transcript_fasta
- salmon = ch_salmon
- sizes = ch_sizes
- star = ch_star
- versions = versions
+ bowtie1_index // channel: [meta, BowtieIndex/]
+ bowtie2_index // channel: [meta, Bowtie2Index/]
+ bwamem1_index // channel: [meta, BWAmemIndex/]
+ bwamem2_index // channel: [meta, BWAmem2memIndex/]
+ dragmap_hashmap // channel: [meta, DragmapHashtable/]
+ fasta // channel: [meta, *.fa(sta)]
+ fasta_dict // channel: [meta, *.fa(sta).dict]
+ fasta_fai // channel: [meta, *.fa(sta).fai]
+ fasta_sizes // channel: [meta, *.fa(sta).sizes]
+ gtf // channel: [meta, gtf]
+ hisat2_index // channel: [meta, Hisat2Index/]
+ intervals_bed // channel: [meta, *.bed]
+ kallisto_index // channel: [meta, KallistoIndex]
+ msisensorpro_list // channel: [meta, *.list]
+ rsem_index // channel: [meta, RSEMIndex/]
+ salmon_index // channel: [meta, SalmonIndex/]
+ splice_sites // channel: [meta, *.splice_sites.txt]
+ star_index // channel: [meta, STARIndex/]
+ transcript_fasta // channel: [meta, *.transcripts.fasta]
+ vcf_tbi // channel: [meta, *.vcf.tbi]
+ versions // channel: [versions.yml]
publish:
- ch_bowtie1 >> 'bowtie1'
- ch_bowtie2 >> 'bowtie2'
- ch_bwamem1 >> 'bwamem1'
- ch_bwamem2 >> 'bwamem2'
- ch_dbsnp_vcf_tbi >> 'tabix_dbsnp'
- ch_dragmap >> 'dragmap'
- ch_fasta >> 'fasta'
- ch_fasta_dict >> 'fasta_dict'
- ch_fasta_fai >> 'fasta_fai'
- ch_germline_resource_vcf_tbi >> 'tabix_germline_resource'
- ch_gff_gtf >> 'gffread'
- ch_hisat2 >> 'hisat2'
- ch_hisat2_splice_sites >> 'splice_sites'
- ch_intervals_bed >> 'intervals'
- ch_kallisto >> 'kallisto'
- ch_known_indels_vcf_tbi >> 'tabix_known_indels'
- ch_known_snps_vcf_tbi >> 'tabix_known_snps'
- ch_msisensorpro >> 'msisensorpro'
- ch_rsem >> 'rsem'
- ch_rsem_transcript_fasta >> 'transcript_fasta'
- ch_salmon >> 'salmon'
- ch_sizes >> 'fasta_sizes'
- ch_star >> 'star'
+ bowtie1_index >> 'bowtie1_index'
+ bowtie2_index >> 'bowtie2_index'
+ bwamem1_index >> 'bwamem1_index'
+ bwamem2_index >> 'bwamem2_index'
+ dragmap_hashmap >> 'dragmap_hashmap'
+ fasta >> 'fasta'
+ fasta_dict >> 'fasta_dict'
+ fasta_fai >> 'fasta_fai'
+ fasta_sizes >> 'fasta_sizes'
+ gtf >> 'gtf'
+ hisat2_index >> 'hisat2_index'
+ intervals_bed >> 'intervals_bed'
+ kallisto_index >> 'kallisto_index'
+ msisensorpro_list >> 'msisensorpro_list'
+ rsem_index >> 'rsem_index'
+ salmon_index >> 'salmon_index'
+ splice_sites >> 'splice_sites'
+ star_index >> 'star_index'
+ transcript_fasta >> 'transcript_fasta'
+ vcf_tbi >> 'vcf_tbi'
}