From c93fa3be844bb7ff08fa6cf15f4214cfccf6fd52 Mon Sep 17 00:00:00 2001
From: nservant <nservant@curie.fr>
Date: Tue, 2 Apr 2019 23:07:08 +0200
Subject: [PATCH] add igenomes
---
conf/base.config | 1 +
conf/hicpro.config | 11 +--
conf/igenomes.config | 89 ++++++----------------
conf/test.config | 10 ++-
main.nf | 173 +++++++++++++++++++++++++++++++++----------
nextflow.config | 6 +-
6 files changed, 175 insertions(+), 115 deletions(-)
diff --git a/conf/base.config b/conf/base.config
index 311c186..11bc185 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -69,4 +69,5 @@ params {
max_memory = 20.GB
max_cpus = 1
max_time = 24.h
+ igenomes_base = 's3://ngi-igenomes/igenomes/'
}
diff --git a/conf/hicpro.config b/conf/hicpro.config
index 9ef8dc6..268d4d4 100644
--- a/conf/hicpro.config
+++ b/conf/hicpro.config
@@ -9,17 +9,18 @@
params {
+ // Genome Reference
+ bwt2_index =
+ chromosome_size =
+
// Alignment options
- bwt2_index = '/data/annotations/pipelines/Human/hg19/indexes/bowtie2/hg19'
bwt2_opts_end2end = '--very-sensitive -L 30 --score-min L,-0.6,-0.2 --end-to-end --reorder'
bwt2_opts_trimmed = '--very-sensitive -L 20 --score-min L,-0.6,-0.2 --end-to-end --reorder'
min_mapq = 10
- // Genome Reference
- chromosome_size = '/data/users/nservant/Apps/HiC-Pro_annotation/chrom_hg19.sizes'
-
// Digestion Hi-C
- restriction_fragment_bed = '/data/users/nservant/Apps/HiC-Pro_annotation/HindIII_resfrag_hg19.bed'
+ restriction_site = 'A^AGGCT'
+ restriction_fragments =
ligation_site = 'AAGCTAGCTT'
min_restriction_fragment_size = 0
max_restriction_fragment_size = 100
diff --git a/conf/igenomes.config b/conf/igenomes.config
index d19e61f..5cb5f85 100644
--- a/conf/igenomes.config
+++ b/conf/igenomes.config
@@ -9,139 +9,94 @@
params {
// illumina iGenomes reference file paths
- // TODO nf-core: Add new reference types and strip out those that are not needed
genomes {
'GRCh37' {
- bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/genome"
}
'GRCm38' {
- bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/genome"
}
'TAIR10' {
- bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/genome"
}
'EB2' {
- bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed"
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"
- star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/genome"
}
'UMD3.1' {
- bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/genome"
}
'WBcel235' {
- bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/genome"
}
'CanFam3.1' {
- bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/genome"
}
'GRCz10' {
- bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/genome"
}
'BDGP6' {
- bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/genome"
}
'EquCab2' {
- bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/genome"
}
'EB1' {
- bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/genome"
}
'Galgal4' {
- bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/genome"
}
'Gm01' {
- bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/genome"
}
'Mmul_1' {
- bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed"
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"
- star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/genome"
}
'IRGSP-1.0' {
- bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/genome"
}
'CHIMP2.1.4' {
- bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed"
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"
- star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/genome"
}
'Rnor_6.0' {
- bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/genome"
}
'R64-1-1' {
- bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed"
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"
- star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/genome"
}
'EF2' {
- bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/genome"
}
'Sbi1' {
- bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/genome"
}
'Sscrofa10.2' {
- bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/genome"
}
'AGPv3' {
- bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed"
fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa"
- gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf"
- star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/"
+ bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/genome"
}
}
}
diff --git a/conf/test.config b/conf/test.config
index caad86c..e13858c 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -9,6 +9,9 @@
params {
+ config_profile_name = 'Hi-C test data from Dixon et al. (2012)'
+ config_profile_description = 'Minimal test dataset to check pipeline function'
+
// Limit resources so that this can run on Travis
max_cpus = 4
max_memory = 6.GB
@@ -16,7 +19,10 @@ params {
// Input data
readPaths = [
- ['SRR400264_00', ['https://github.com/nf-core/test-datasets/raw/hic/SRR400264_00_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/SRR400264_00_R2.fastq.gz']],
- ['SRR400264_01', ['https://github.com/nf-core/test-datasets/raw/hic/SRR400264_01_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/SRR400264_01_R2.fastq.gz']]
+ ['SRR400264_00', ['https://github.com/nf-core/test-datasets/raw/hic/testdata/SRR400264_00_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/testdata/SRR400264_00_R2.fastq.gz']],
+ ['SRR400264_01', ['https://github.com/nf-core/test-datasets/raw/hic/testdata/SRR400264_01_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/testdata/SRR400264_01_R2.fastq.gz']]
]
+
+ // Annotations
+ genome = 'GRch37'
}
diff --git a/main.nf b/main.nf
index 618977b..ee1945d 100644
--- a/main.nf
+++ b/main.nf
@@ -12,7 +12,6 @@
/*TOOO
- outputs
-- env
- multiqc
- update version tools
- install + compile
@@ -38,23 +37,27 @@ def helpMessage() {
The typical command for running the pipeline is as follows:
- nextflow run nf-core/hic --reads '*_R{1,2}.fastq.gz' -profile docker
+ nextflow run nf-core/hic --reads '*_R{1,2}.fastq.gz' -profile conda
Mandatory arguments:
- --reads Path to input data (must be surrounded with quotes)
- // --genome Name of iGenomes reference
- -profile Configuration profile to use. Can use multiple (comma separated)
- Available: conda, docker, singularity, awsbatch, test and more.
+ --reads Path to input data (must be surrounded with quotes)
+ --genome Name of iGenomes reference
+ -profile Configuration profile to use. Can use multiple (comma separated)
+ Available: conda, docker, singularity, awsbatch, test and more.
+
+ References If not specified in the configuration file or you wish to overwrite any of the references.
+ --bwt2_index Path to Bowtie2 index
+ --fasta Path to Fasta reference
+ --chromosome_size Path to chromosome size file
+ --restriction_fragment_bed Path to restriction fragment file (bed)
Options:
- --bwt2_index Path to bowtie2 indexes (including indexes prefix)
- --bwt2_opts_end2end Option for bowtie2 end-to-end mappinf (first mapping step)
- --bwt2_opts_trimmed Option for bowtie2 mapping after ligation site trimming
- --min_mapq Minimum mapping quality values to consider
+ --bwt2_opts_end2end Options for bowtie2 end-to-end mappinf (first mapping step)
+ --bwt2_opts_trimmed Options for bowtie2 mapping after ligation site trimming
+ --min_mapq Minimum mapping quality values to consider
- --chromosome_size Path to chromosome size file
- --restriction_fragment_bed Path to restriction fragment file (bed)
- --ligation-site Ligation motifs to trim (comma separated)
+ --restriction-site Cutting motif(s) of restriction enzyme(s) (comma separated)
+ --ligation-site Ligation motifs to trim (comma separated)
--min_restriction_fragment_size Minimum size of restriction fragments to consider
--max_restriction_framgnet_size Maximum size of restriction fragmants to consider
@@ -71,18 +74,14 @@ def helpMessage() {
--ice_filter_high_count_perc Percentage of high counts columns/rows to filter before ICE normalization
--ice_eps Convergence criteria for ICE normalization
-
- //References If not specified in the configuration file or you wish to overwrite any of the references.
- // --fasta Path to Fasta reference
-
Other options:
- --outdir The output directory where the results will be saved
- --email Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits
- -name Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic.
+ --outdir The output directory where the results will be saved
+ --email Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits
+ -name Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic.
AWSBatch options:
- --awsqueue The AWSBatch JobQueue that needs to be set when running on AWSBatch
- --awsregion The AWS Region for your AWS Batch job to run on
+ --awsqueue The AWSBatch JobQueue that needs to be set when running on AWSBatch
+ --awsregion The AWS Region for your AWS Batch job to run on
""".stripIndent()
}
@@ -96,13 +95,15 @@ if (params.help){
exit 0
}
-// TODO nf-core: Add any reference files that are needed
-// Configurable reference genomes
-//fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false
-//if ( params.fasta ){
-// fasta = file(params.fasta)
-// if( !fasta.exists() ) exit 1, "Fasta file not found: ${params.fasta}"
-//}
+// Check if genome exists in the config file
+if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
+ exit 1, "The provided genome '${params.genome}' is not available in the iGenomes file. Currently the available genomes are ${params.genomes.keySet().join(", ")}"
+}
+
+// Reference index path configuration
+// Define these here - after the profiles are loaded with the iGenomes paths
+params.bwt2_index = params.genome ? params.genomes[ params.genome ].bowtie2 ?: false : false
+params.fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false
// Has the run name been specified by the user?
@@ -112,7 +113,6 @@ if( !(workflow.runName ==~ /[a-z]+_[a-z]+/) ){
custom_runName = workflow.runName
}
-
if( workflow.profile == 'awsbatch') {
// AWSBatch sanity checking
if (!params.awsqueue || !params.awsregion) exit 1, "Specify correct --awsqueue and --awsregion parameters on AWSBatch!"
@@ -172,16 +172,50 @@ if (params.readPaths){
* Other input channels
*/
-// Bowtie2 Index
-bwt2_file = file("${params.bwt2_index}.1.bt2")
-if( !bwt2_file.exists() ) exit 1, "Reference genome Bowtie 2 not found: ${params.bwt2_index}"
-bwt2_index = Channel.value( "${params.bwt2_index}" )
+// Reference genome
+if ( params.bwt2_index ){
+ bwt2_file = file("${params.bwt2_index}.1.bt2")
+ if( !bwt2_file.exists() ) exit 1, "Reference genome Bowtie 2 not found: ${params.bwt2_index}"
+ bwt2_index = Channel.value( "${params.bwt2_index}" )
+}
+else if ( params.fasta ) {
+ Channel.fromPath(params.fasta)
+ .ifEmpty { exit 1, "Fasta file not found: ${params.fasta}" }
+ .set { fasta_for_index }
+}
+else {
+ exit 1, "No reference genome specified!"
+}
-res_frag_file = Channel.value( "${params.restriction_fragment_bed}" )
-chr_size = Channel.value( "${params.chromosome_size}" )
-map_res = Channel.from( params.bins_size.tokenize(',') )
+// Chromosome size
+if ( params.chromosome_size ){
+ chromosome_size = Channel.value( "${params.chromosome_size}" )
+}
+else if ( params.fasta ){
+ Channel.fromPath(params.fasta)
+ .ifEmpty { exit 1, "Fasta file not found: ${params.fasta}" }
+ .set { fasta_for_chromsize }
+}
+else {
+ exit 1, "No chromosome size specified!"
+}
+
+// Restriction fragments
+if ( params.restriction_fragments ){
+ res_frag_file = Channel.value( "${params.restriction_fragments}" )
+}
+else if ( params.fasta && params.restriction_site ){
+ Channel.fromPath(params.fasta)
+ .ifEmpty { exit 1, "Fasta file not found: ${params.fasta}" }
+ .set { fasta_for_resfrag }
+else {
+ exit 1, "No restriction fragments file specified!"
+}
+
+// Resolutions for contact maps
+map_res = Channel.from( params.bins_size.tokenize(',') )
/**********************************************************
@@ -204,7 +238,8 @@ summary['Pipeline Version'] = workflow.manifest.version
summary['Run Name'] = custom_runName ?: workflow.runName
// TODO nf-core: Report custom parameters here
summary['Reads'] = params.reads
-//summary['Fasta Ref'] = params.fasta
+summary['Fasta Ref'] = params.fasta
+
summary['Max Memory'] = params.max_memory
summary['Max CPUs'] = params.max_cpus
summary['Max Time'] = params.max_time
@@ -266,6 +301,68 @@ process get_software_versions {
}
+/****************************************************
+ * PRE-PROCESSING
+ */
+
+if(!params.bwt2_index && params.fasta){
+ process makeBowtieIndex {
+ tag "$fasta"
+ publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
+ saveAs: { params.saveReference ? it : null }, mode: 'copy'
+
+ input:
+ file fasta from fasta_for_index
+
+ output:
+ file "bowtie2" into bwt2_index
+
+ script:
+ """
+ mkdir bwt2_index
+ """
+ }
+ }
+
+
+if(!params.chromosome_size && params.fasta){
+ process makeChromSize {
+ tag "$fasta"
+ publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
+ saveAs: { params.saveReference ? it : null }, mode: 'copy'
+
+ input:
+ file fasta from fasta_for_chromsize
+
+ output:
+ file "*.size" into chromosome_size
+
+ script:
+ """
+ samtools faidx ${fasta} | cut -f1,2 > chrom.size
+ """
+ }
+ }
+
+if(!params.bwt2_index && params.fasta){
+ process makeRestrictionFragments {
+ tag "$fasta"
+ publishDir path: { params.saveReference ? "${params.outdir}/reference_genome" : params.outdir },
+ saveAs: { params.saveReference ? it : null }, mode: 'copy'
+
+ input:
+ file fasta from fasta_for_resfrag
+
+ output:
+ file "*.bed" into restriction_fragments
+
+ script:
+ """
+ python digest_genome.py -r ${params.restriction_site} -o restriction_fragments.bed ${fasta}
+ """
+ }
+ }
+
/****************************************************
* MAIN WORKFLOW
*/
diff --git a/nextflow.config b/nextflow.config
index 27c12fe..fe584c3 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -63,9 +63,9 @@ profiles {
}
// Load igenomes.config if required
-//if(!params.igenomesIgnore){
-// includeConfig 'conf/igenomes.config'
-//}
+if(!params.igenomesIgnore){
+ includeConfig 'conf/igenomes.config'
+}
// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']
--
GitLab