diff --git a/conf/modules.config b/conf/modules.config
index 9cef5f9b0dea9b7ed06be24cb17f84e87eaf0687..763ba3f5eb8dfeb64543febbf4c679d5ea7d4fa7 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -7,6 +7,14 @@ process {
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
+ withName: 'CUSTOM_DUMPSOFTWAREVERSIONS' {
+ publishDir = [
+ path: { "${params.outdir}/pipeline_info" },
+ mode: 'copy',
+ pattern: '*_versions.yml'
+ ]
+ }
+
//**********************************************
// PREPARE_GENOME
withName: 'BOWTIE2_BUILD' {
@@ -17,7 +25,7 @@ process {
]
}
- withName: 'GET_CHROMSIZE' {
+ withName: 'CUSTOM_GETCHROMSIZES' {
publishDir = [
path: { "${params.outdir}/genome" },
mode: 'copy',
@@ -41,8 +49,9 @@ process {
mode: 'copy',
enabled: params.save_aligned_intermediates
]
- ext.prefix = { "${meta.id}_${meta.mates}" }
+ ext.prefix = { params.split_fastq ? "${meta.chunk}_${meta.mates}" : "${meta.id}_${meta.mates}" }
ext.args = params.bwt2_opts_end2end ?: ''
+ ext.args2 = !params.dnase ? "-F 4" :""
}
withName: 'TRIM_READS' {
@@ -59,8 +68,9 @@ process {
mode: 'copy',
enabled: params.save_aligned_intermediates
]
- ext.prefix = { "${meta.id}_${meta.mates}_trimmed" }
+ ext.prefix = { params.split_fastq ? "${meta.chunk}_${meta.mates}_trimmed" : "${meta.id}_${meta.mates}_trimmed" }
ext.args = params.bwt2_opts_trimmed ?: ''
+ ext.args2 = ""
}
withName: 'MERGE_BOWTIE2' {
@@ -69,45 +79,61 @@ process {
mode: 'copy',
enabled: params.save_aligned_intermediates
]
+ ext.prefix = { params.split_fastq ? "${meta.chunk}_${meta.mates}" : "${meta.id}_${meta.mates}" }
}
withName: 'COMBINE_MATES' {
publishDir = [
path: { "${params.outdir}/hicpro/mapping" },
- mode: 'copy'
+ mode: 'copy',
+ pattern: '*.bam'
]
ext.args = [
"-t",
params.keep_multi ? "--multi" : "",
params.min_mapq ? "-q ${params.min_mapq}" : ""
].join(' ').trim()
+ ext.prefix = { params.split_fastq ? "${meta.chunk}" : "${meta.id}" }
}
withName: 'GET_VALID_INTERACTION' {
publishDir = [
path: { "${params.outdir}/hicpro/valid_pairs" },
- mode: 'copy'
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy',
+ enabled: params.save_pairs_intermediates
]
- ext.args = [
+ ext.args = { [
params.min_cis_dist > 0 ? " -d ${params.min_cis_dist}" : '',
params.min_insert_size > 0 ? " -s ${params.min_insert_size}" : '',
params.max_insert_size > 0 ? " -l ${params.max_insert_size}" : '',
params.min_restriction_fragment_size > 0 ? " -t ${params.min_restriction_fragment_size}" : '',
params.max_restriction_fragment_size > 0 ? " -m ${params.max_restriction_fragment_size}" : '',
params.save_interaction_bam ? " --sam" : ''
- ].join(' ').trim()
+ ].join(' ').trim() }
+ }
+
+ withName: 'GET_VALID_INTERACTION_DNASE' {
+ publishDir = [
+ path: { "${params.outdir}/hicpro/valid_pairs" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy',
+ enabled: params.save_pairs_intermediates
+ ]
+ ext.args = { params.min_cis_dist > 0 ? " -d ${params.min_cis_dist}" : "" }
}
withName: 'MERGE_VALID_INTERACTION' {
publishDir = [
[
- path: { "${params.outdir}/hicpro/stats/" },
+ path: { "${params.outdir}/hicpro/stats/${meta.id}" },
mode: 'copy',
pattern: "*stat"
],
[
path: { "${params.outdir}/hicpro/valid_pairs" },
mode: 'copy',
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
pattern: "*Pairs"
]
]
@@ -115,14 +141,17 @@ process {
withName: 'MERGE_STATS' {
publishDir = [
- path: { "${params.outdir}/hicpro/stats" },
- mode: 'copy'
+ path: { "${params.outdir}/hicpro/stats/${meta.id}" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy',
+ pattern: "*stat"
]
}
withName: 'HICPRO2PAIRS' {
publishDir = [
path: { "${params.outdir}/hicpro/valid_pairs/pairix/" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
mode: 'copy'
]
}
@@ -143,6 +172,17 @@ process {
]
}
+ //*****************************************
+ // QUALITY METRICS
+
+ withName: 'HIC_PLOT_DIST_VS_COUNTS'{
+ publishDir = [
+ path: { "${params.outdir}/distance_decay/" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy'
+ ]
+ }
+
//*****************************************
// COOLER
@@ -177,6 +217,7 @@ process {
publishDir = [
enabled: false
]
+ ext.prefix = { "${cool.baseName}" }
ext.args = "--one-based-ids --balanced --na-rep 0"
}
@@ -191,7 +232,7 @@ process {
[
path: { "${params.outdir}/contact_maps/txt/" },
mode: 'copy',
- pattern: "*_norm.txt"
+ pattern: "*_balanced.txt"
]
]
}
@@ -209,6 +250,11 @@ process {
// COMPARTMENTS
withName: 'CALL_COMPARTMENTS' {
+ publishDir = [
+ path: { "${params.outdir}/compartments/" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy'
+ ]
ext.args = '--bigwig'
}
@@ -216,11 +262,20 @@ process {
// TADS
withName: 'INSULATION' {
+ publishDir = [
+ path: { "${params.outdir}/tads/insulation/" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy'
+ ]
ext.args = '15 25 50 --window-pixels'
}
withName: 'HIC_FIND_TADS' {
+ publishDir = [
+ path: { "${params.outdir}/tads/hicExplorer" },
+ saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+ mode: 'copy'
+ ]
ext.args = '--correctForMultipleTesting fdr'
}
-
}
\ No newline at end of file
diff --git a/modules.json b/modules.json
index b7bfabedbf2ff583704d754b3432519ab329d941..58d81058caad44803f3f87571bb8c15fbe880793 100644
--- a/modules.json
+++ b/modules.json
@@ -18,10 +18,13 @@
"cooler/zoomify": {
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
},
- "fastqc": {
+ "custom/dumpsoftwareversions": {
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
},
- "multiqc": {
+ "custom/getchromsizes": {
+ "git_sha": "950700bcdc0e9a2b6883d40d2c51c6fc435cd714"
+ },
+ "fastqc": {
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
}
}
diff --git a/modules/local/cooler/balance.nf b/modules/local/cooler/balance.nf
index ce6e3bb5951edd34aab6aa4aa743ec2ee92a837f..37e808d0e5a1909775f9b6039a42eb069df7fe07 100644
--- a/modules/local/cooler/balance.nf
+++ b/modules/local/cooler/balance.nf
@@ -8,20 +8,24 @@ process COOLER_BALANCE {
'quay.io/biocontainers/cooler:0.8.11--pyh3252c3a_0' }"
input:
- tuple val(meta), val(resolution), path(cool)
+ tuple val(meta), path(cool), val(resolution)
output:
- tuple val(meta), val(resolution), path("*_norm.cool"), emit: cool
- path "versions.yml" , emit: versions
+ tuple val(meta), path("${prefix}.${extension}"), emit: cool
+ path "versions.yml" , emit: versions
script:
def args = task.ext.args ?: ''
+ prefix = task.ext.prefix ?: "${cool.baseName}_balanced"
+ suffix = resolution ? "::$resolution" : ""
+ extension = cool.getExtension()
"""
- cp ${cool} ${cool.baseName}_norm.cool
cooler balance \\
$args \\
-p ${task.cpus} \\
- ${cool.baseName}_norm.cool
+ ${cool}${suffix}
+
+ cp ${cool} ${prefix}.${extension}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
diff --git a/modules/local/cooler/makebins.nf b/modules/local/cooler/makebins.nf
index 0dc4dee4140b89c4a2eb07ee666f9ad936725a9a..49e18db719d8e9b97738d9156b2c6dc3015df6b1 100644
--- a/modules/local/cooler/makebins.nf
+++ b/modules/local/cooler/makebins.nf
@@ -11,8 +11,8 @@ process COOLER_MAKEBINS {
tuple path(chromsizes), val(cool_bin)
output:
- path ("*.bed") , emit: bed
- path "versions.yml", emit: versions
+ path ("*.bed") , emit: bed
+ path ("versions.yml"), emit: versions
script:
def args = task.ext.args ?: ''
diff --git a/modules/local/cooltools/eigs-cis.nf b/modules/local/cooltools/eigs-cis.nf
index 74cd265fa48906c116a64947939bcdd6905eea2e..a8b97b9bb18008734f7b5d50950a5ebf597fc191 100644
--- a/modules/local/cooltools/eigs-cis.nf
+++ b/modules/local/cooltools/eigs-cis.nf
@@ -6,7 +6,7 @@ process CALL_COMPARTMENTS {
label 'process_medium'
input:
- tuple val(meta), val(res), path(cool)
+ tuple val(meta), path(cool), val(resolution)
path(fasta)
path(chrsize)
@@ -18,7 +18,7 @@ process CALL_COMPARTMENTS {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
"""
- cooltools genome binnify --all-names ${chrsize} ${res} > genome_bins.txt
+ cooltools genome binnify --all-names ${chrsize} ${resolution} > genome_bins.txt
cooltools genome gc genome_bins.txt ${fasta} > genome_gc.txt
cooltools eigs-cis ${args} -o ${prefix}_compartments ${cool}
diff --git a/modules/local/get_restriction_fragments.nf b/modules/local/get_restriction_fragments.nf
deleted file mode 100644
index 93258b7528e120505dcdf1cb4120833fcf93aa50..0000000000000000000000000000000000000000
--- a/modules/local/get_restriction_fragments.nf
+++ /dev/null
@@ -1,16 +0,0 @@
-process GET_RESTRICTION_FRAGMENTS {
- tag "$res_site"
- label 'process_low'
-
- input:
- path fasta
- val(res_site)
-
- output:
- path "*.bed", emit: results
-
- script:
- """
- digest_genome.py -r ${res_site} -o restriction_fragments.bed ${fasta}
- """
-}
diff --git a/modules/local/hicpro/bowtie2_merge.nf b/modules/local/hicpro/bowtie2_merge.nf
index 0dfd25c26b2d99a61b82fb9019d22dbce1a4e7e8..b020b70fc990b4b18ea44bdb14ab723bc95bc82b 100644
--- a/modules/local/hicpro/bowtie2_merge.nf
+++ b/modules/local/hicpro/bowtie2_merge.nf
@@ -8,9 +8,10 @@ process MERGE_BOWTIE2{
output:
tuple val(meta), path("${prefix}_bwt2merged.bam"), emit: bam
tuple val(meta), path("${prefix}.mapstat"), emit: stats
+ path("versions.yml"), emit: versions
script:
- prefix = meta.id + "_" + meta.mates
+ prefix = task.ext.prefix ?: "${meta.id}"
tag = meta.mates
"""
samtools merge -@ ${task.cpus} \\
@@ -33,5 +34,10 @@ process MERGE_BOWTIE2{
samtools view -c -F 4 ${bam1} >> ${prefix}.mapstat
echo -n "local_${tag}\t" >> ${prefix}.mapstat
samtools view -c -F 4 ${bam2} >> ${prefix}.mapstat
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+ END_VERSIONS
"""
}
diff --git a/modules/local/hicpro/combine_mates.nf b/modules/local/hicpro/combine_mates.nf
index 2f5f2d097565664d7162ce940ead3473b67d6665..a137b78e44591fa897e516fe0351f8a324273868 100644
--- a/modules/local/hicpro/combine_mates.nf
+++ b/modules/local/hicpro/combine_mates.nf
@@ -8,11 +8,17 @@ process COMBINE_MATES {
output:
tuple val(meta), path("*bwt2pairs.bam"), emit:bam
tuple val(meta), path("*.pairstat"), optional:true, emit:stats
+ path("versions.yml"), emit: versions
script:
- prefix = meta.id
+ prefix = task.ext.prefix ?: "${meta.id}"
def args = task.ext.args ?: ''
"""
mergeSAM.py -f ${bam[0]} -r ${bam[1]} -o ${prefix}_bwt2pairs.bam ${args}
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ END_VERSIONS
"""
}
diff --git a/modules/local/hicpro/dnase_mapping_stats.nf b/modules/local/hicpro/dnase_mapping_stats.nf
index c11f3434e7de826ae318626441f1d095bd770150..aa78141665832af8214b574e133e3b396d235c5d 100644
--- a/modules/local/hicpro/dnase_mapping_stats.nf
+++ b/modules/local/hicpro/dnase_mapping_stats.nf
@@ -1,35 +1,25 @@
-// Import generic module functions
-include { initOptions; saveFiles; getSoftwareName } from './functions'
+process MAPPING_STATS_DNASE {
+ tag "$sample = $bam"
+ label 'process_medium'
-params.options = [:]
-options = initOptions(params.options)
+ input:
+ tuple val(meta), path(bam)
-process dnase_mapping_stats{
- tag "$sample = $bam"
- label 'process_medium'
- publishDir "${params.outdir}/hicpro/mapping", mode: params.publish_dir_mode,
- saveAs: { filename -> if (params.save_aligned_intermediates && filename.endsWith("stat")) "stats/$filename"
- else if (params.save_aligned_intermediates) filename}
+ output:
+ tuple val(meta), path(bam), emit:bam
+ tuple val(meta), path("${prefix}.mapstat"), emit:stats
- input:
- tuple val(prefix), path(bam)
-
- output:
- tuple val(sample), path(bam), emit:bwt2_merged_bam
- tuple val(oname), path("${prefix}.mapstat"), emit:all_mapstat
-
- script:
- sample = prefix.toString() - ~/(_R1|_R2)/
- tag = prefix.toString() =~/_R1/ ? "R1" : "R2"
- oname = prefix.toString() - ~/(\.[0-9]+)$/
- """
- echo "## ${prefix}" > ${prefix}.mapstat
- echo -n "total_${tag}\t" >> ${prefix}.mapstat
- samtools view -c ${bam} >> ${prefix}.mapstat
- echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam} >> ${prefix}.mapstat
- echo -n "global_${tag}\t" >> ${prefix}.mapstat
- samtools view -c -F 4 ${bam} >> ${prefix}.mapstat
- echo -n "local_${tag}\t0" >> ${prefix}.mapstat
- """
+ script:
+ prefix = meta.id + "_" + meta.mates
+ tag = meta.mates
+ """
+ echo "## ${prefix}" > ${prefix}.mapstat
+ echo -n "total_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c ${bam} >> ${prefix}.mapstat
+ echo -n "mapped_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam} >> ${prefix}.mapstat
+ echo -n "global_${tag}\t" >> ${prefix}.mapstat
+ samtools view -c -F 4 ${bam} >> ${prefix}.mapstat
+ echo -n "local_${tag}\t0" >> ${prefix}.mapstat
+ """
}
diff --git a/modules/local/hicpro/get_restriction_fragments.nf b/modules/local/hicpro/get_restriction_fragments.nf
new file mode 100644
index 0000000000000000000000000000000000000000..7b304e4dfc411f9a4066b05052c851af891a6b3d
--- /dev/null
+++ b/modules/local/hicpro/get_restriction_fragments.nf
@@ -0,0 +1,22 @@
+process GET_RESTRICTION_FRAGMENTS {
+ tag "$res_site"
+ label 'process_low'
+
+ input:
+ path fasta
+ val(res_site)
+
+ output:
+ path "*.bed", emit: results
+ path("versions.yml"), emit: versions
+
+ script:
+ """
+ digest_genome.py -r ${res_site} -o restriction_fragments.bed ${fasta}
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ END_VERSIONS
+ """
+}
diff --git a/modules/local/hicpro/get_valid_interaction.nf b/modules/local/hicpro/get_valid_interaction.nf
index 385857675ffdcb5c20e2186ebf5f8cdb50ce248c..d8ea17f7541aceea09d677cae49e0843d550b13a 100644
--- a/modules/local/hicpro/get_valid_interaction.nf
+++ b/modules/local/hicpro/get_valid_interaction.nf
@@ -8,16 +8,14 @@ process GET_VALID_INTERACTION {
output:
tuple val(meta), path("*.validPairs"), emit:valid_pairs
- tuple val(meta), path("*.DEPairs"), emit:de_pairs
- tuple val(meta), path("*.SCPairs"), emit:sc_pairs
- tuple val(meta), path("*.REPairs"), emit:re_pairs
- tuple val(meta), path("*.FiltPairs"), emit:filt_pairs
- tuple val(meta), path("*RSstat"), emit:stats
+ tuple val(meta), path("*.DEPairs"), optional:true, emit:de_pairs
+ tuple val(meta), path("*.SCPairs"), optional: true, emit:sc_pairs
+ tuple val(meta), path("*.REPairs"), optional: true, emit:re_pairs
+ tuple val(meta), path("*.FiltPairs"), optional: true, emit:filt_pairs
+ tuple val(meta), path("*RSstat"), optional: true, emit:stats
+ path("versions.yml"), emit: versions
script:
- if (params.split_fastq){
- sample = sample.toString() - ~/(\.[0-9]+)$/
- }
def args = task.ext.args ?: ''
"""
mapped_2hic_fragments.py \\
@@ -27,5 +25,10 @@ process GET_VALID_INTERACTION {
${args}
sort -k2,2V -k3,3n -k5,5V -k6,6n -o ${bam.baseName}.validPairs ${bam.baseName}.validPairs
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ END_VERSIONS
"""
}
diff --git a/modules/local/hicpro/get_valid_interaction_dnase.nf b/modules/local/hicpro/get_valid_interaction_dnase.nf
index 62c3ea4dfd8a1d86881a49d9078e0997151fb9a8..4bb40b8f1e5f081acd0044bd2bb78ef2561a01cf 100644
--- a/modules/local/hicpro/get_valid_interaction_dnase.nf
+++ b/modules/local/hicpro/get_valid_interaction_dnase.nf
@@ -1,33 +1,27 @@
-// Import generic module functions
-include { initOptions; saveFiles; getSoftwareName } from './functions'
+process GET_VALID_INTERACTION_DNASE {
+ tag "$meta.id"
+ label 'process_low'
+
+ input:
+ tuple val(meta), path(bam)
-params.options = [:]
-options = initOptions(params.options)
+ output:
+ tuple val(meta), path("*.validPairs"), emit:valid_pairs
+ tuple val(meta), path("*RSstat"), optional: true, emit:stats
+ path("versions.yml"), emit: versions
-process get_valid_interaction_dnase{
- tag "$sample"
- label 'process_low'
- publishDir "${params.outdir}/hicpro/valid_pairs", mode: params.publish_dir_mode,
- saveAs: {filename -> if (filename.endsWith("RSstat")) "stats/$filename"
- else filename}
+ script:
+ def args = task.ext.args ?: ''
+ """
+ mapped_2hic_dnase.py \\
+ -r ${bam} \\
+ ${args}
- input:
- tuple val(sample), path(pe_bam)
+ sort -k2,2V -k3,3n -k5,5V -k6,6n -o ${bam.baseName}.validPairs ${bam.baseName}.validPairs
- output:
- tuple val(sample), path("*.validPairs"), emit:valid_pairs
- tuple val(sample), path("*.validPairs"), emit:valid_pairs_4cool
- tuple val(sample), path("*RSstat"), emit:all_rsstat
-
- script:
- if (params.split_fastq){
- sample = sample.toString() - ~/(\.[0-9]+)$/
- }
-
- opts = params.min_cis_dist > 0 ? " -d ${params.min_cis_dist}" : ''
- prefix = pe_bam.toString() - ~/.bam/
- """
- mapped_2hic_dnase.py -r ${pe_bam} ${opts}
- sort -k2,2V -k3,3n -k5,5V -k6,6n -o ${prefix}.validPairs ${prefix}.validPairs
- """
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ END_VERSIONS
+ """
}
diff --git a/modules/local/hicpro/hicpro2pairs.nf b/modules/local/hicpro/hicpro2pairs.nf
index 698225da80c9474ef898c8c3238c3173eccab40b..99e4a6bd18ff61b674873b5053808b7297de17b4 100644
--- a/modules/local/hicpro/hicpro2pairs.nf
+++ b/modules/local/hicpro/hicpro2pairs.nf
@@ -8,6 +8,7 @@ process HICPRO2PAIRS {
output:
tuple val(meta), path("*.pairs.gz"), path("*.pairs.gz.px2"), emit: pairs
+ path("versions.yml"), emit: versions
script:
prefix = "${meta.id}"
@@ -16,5 +17,10 @@ process HICPRO2PAIRS {
awk '{OFS="\t";print \$1,\$2,\$3,\$5,\$6,\$4,\$7}' $vpairs > ${prefix}_contacts.pairs
sort -k2,2 -k4,4 -k3,3n -k5,5n ${prefix}_contacts.pairs | bgzip -c > ${prefix}_contacts.pairs.gz
pairix -f ${prefix}_contacts.pairs.gz
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ pairix: \$(echo \$(pairix 2>&1 | grep Version | sed -e 's/Version: //')
+ END_VERSIONS
"""
}
diff --git a/modules/local/hicpro/merge_stats.nf b/modules/local/hicpro/merge_stats.nf
index 2ef759d1c9aa8b97652aef20e404dc3b65d492ec..8fb0eee32cca429b749d0d5f4394fbba36065c3e 100644
--- a/modules/local/hicpro/merge_stats.nf
+++ b/modules/local/hicpro/merge_stats.nf
@@ -5,16 +5,22 @@ process MERGE_STATS {
tuple val(meta), path(fstat)
output:
- path("stats/"), emit:mqc_mstats
- path("*stat"), emit:all_mstats
+ path("${meta.id}/"), emit: mqc
+ path("*.{mmapstat,mpairstat,mRSstat}"), emit: stats
+ path("versions.yml"), emit:versions
script:
- if ( (fstat =~ /.mapstat/) ){ ext = "mmapstat" }
+ if ( (fstat =~ /.mapstat/) ){ ext = "${meta.mates}.mmapstat" }
if ( (fstat =~ /.pairstat/) ){ ext = "mpairstat" }
if ( (fstat =~ /.RSstat/) ){ ext = "mRSstat" }
"""
+ mkdir -p ${meta.id}
merge_statfiles.py -f ${fstat} > ${meta.id}.${ext}
- mkdir -p stats/${meta.id}
- cp ${meta.id}.${ext} stats/${meta.id}/
+ cp *${ext} ${meta.id}/
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ END_VERSIONS
"""
}
diff --git a/modules/local/hicpro/merge_valid_interaction.nf b/modules/local/hicpro/merge_valid_interaction.nf
index efc29ba1f65f87edb211acb8252b1f563ae15280..69163057aa2c29d3c3428275f99b80a85bc71362 100644
--- a/modules/local/hicpro/merge_valid_interaction.nf
+++ b/modules/local/hicpro/merge_valid_interaction.nf
@@ -7,14 +7,15 @@ process MERGE_VALID_INTERACTION {
output:
tuple val(meta), path("*.allValidPairs"), emit: valid_pairs
- path("stats/"), emit:mqc
- tuple val(meta), path("*mergestat"), emit:stats
+ path("${meta.id}/"), emit:mqc
+ path("*mergestat"), emit:stats
+ path("versions.yml"), emit: versions
script:
prefix = meta.id
if ( ! params.keep_dups ){
"""
- mkdir -p stats/${prefix}
+ mkdir -p ${prefix}
## Sort valid pairs and remove read pairs with same starts (i.e duplicated read pairs)
sort -S 50% -k2,2V -k3,3n -k5,5V -k6,6n -m ${vpairs} | \\
@@ -29,8 +30,13 @@ process MERGE_VALID_INTERACTION {
awk 'BEGIN{cis=0;trans=0;sr=0;lr=0} \$2 == \$5{cis=cis+1; d=\$6>\$3?\$6-\$3:\$3-\$6; if (d<=20000){sr=sr+1}else{lr=lr+1}} \$2!=\$5{trans=trans+1}END{print "trans_interaction\\t"trans"\\ncis_interaction\\t"cis"\\ncis_shortRange\\t"sr"\\ncis_longRange\\t"lr}' ${prefix}.allValidPairs >> ${prefix}_allValidPairs.mergestat
## For MultiQC
- mkdir -p stats/${prefix}
- cp ${prefix}_allValidPairs.mergestat stats/${prefix}/
+ mkdir -p ${prefix}
+ cp ${prefix}_allValidPairs.mergestat ${prefix}/
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ sort: \$(echo \$(sort --version 2>&1 | head -1 | awk '{print \$NF}' 2>&1))
+ END_VERSIONS
"""
}else{
"""
@@ -44,8 +50,13 @@ process MERGE_VALID_INTERACTION {
awk 'BEGIN{cis=0;trans=0;sr=0;lr=0} \$2 == \$5{cis=cis+1; d=\$6>\$3?\$6-\$3:\$3-\$6; if (d<=20000){sr=sr+1}else{lr=lr+1}} \$2!=\$5{trans=trans+1}END{print "trans_interaction\\t"trans"\\ncis_interaction\\t"cis"\\ncis_shortRange\\t"sr"\\ncis_longRange\\t"lr}' ${prefix}.allValidPairs >> ${prefix}_allValidPairs.mergestat
## For MultiQC
- mkdir -p stats/${prefix}
- cp ${prefix}_allValidPairs.mergestat stats/${prefix}/
+ mkdir -p ${prefix}
+ cp ${prefix}_allValidPairs.mergestat ${prefix}/
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ sort: \$(echo \$(sort --version 2>&1 | head -1 | awk '{print \$NF}' 2>&1))
+ END_VERSIONS
"""
}
}
diff --git a/modules/local/hicpro/run_ice.nf b/modules/local/hicpro/run_ice.nf
index 521cb3171b187fb14cefc95cd4caa5a404f79f47..7b4ee63a7cdc38059eb38a804cb17262dbf120db 100644
--- a/modules/local/hicpro/run_ice.nf
+++ b/modules/local/hicpro/run_ice.nf
@@ -8,6 +8,7 @@ process ICE_NORMALIZATION{
output:
tuple val(meta), val(res), path("*iced.matrix"), path(bed), emit:maps
path ("*.biases"), emit:bias
+ path("versions.yml"), emit: versions
script:
prefix = rmaps.toString() - ~/(\.matrix)?$/
@@ -16,5 +17,11 @@ process ICE_NORMALIZATION{
--results_filename ${prefix}_iced.matrix \
--filter_high_counts_perc ${params.ice_filter_high_count_perc} \
--max_iter ${params.ice_max_iter} --eps ${params.ice_eps} --remove-all-zeros-loci --output-bias 1 --verbose 1 ${rmaps}
- """
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ python: \$(echo \$(python --version 2>&1) | sed 's/Python //')
+ iced: \$(python -c "import iced; print(iced.__version__)")
+ END_VERSIONS
+ """
}
diff --git a/modules/local/hicpro/trim_reads.nf b/modules/local/hicpro/trim_reads.nf
index 5eafc43df06f9672e6734902d019642bc24dcad3..19edff14c18ccc17fe5804ced19158ab7429bf17 100644
--- a/modules/local/hicpro/trim_reads.nf
+++ b/modules/local/hicpro/trim_reads.nf
@@ -7,14 +7,18 @@ process TRIM_READS {
val(motif)
output:
- tuple val(meta), path("*trimmed.fastq"), emit: fastq
+ tuple val(meta), path("*trimmed.fastq.gz"), emit: fastq
path("versions.yml") , emit: versions
script:
"""
- cutsite_trimming --fastq $reads \\
- --cutsite ${motif} \\
- --out ${meta.id}_trimmed.fastq
+ zcat ${reads} > tmp.fastq
+ cutsite_trimming --fastq tmp.fastq \\
+ --cutsite ${motif[0]} \\
+ --out ${reads.simpleName}_trimmed.fastq
+ gzip ${reads.simpleName}_trimmed.fastq
+ /bin/rm -f tmp.fastq
+
cat <<-END_VERSIONS > versions.yml
"${task.process}":
python: \$(echo \$(python --version 2>&1) | sed 's/^Python//; s/ .*\$//')
diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/local/multiqc.nf
similarity index 87%
rename from modules/nf-core/modules/multiqc/main.nf
rename to modules/local/multiqc.nf
index 1264aac1ebfc902ae6633862472b412cd929656a..8fa76a16f250b1c5e2f1394508985b4a0b3ab2ab 100644
--- a/modules/nf-core/modules/multiqc/main.nf
+++ b/modules/local/multiqc.nf
@@ -7,7 +7,11 @@ process MULTIQC {
'quay.io/biocontainers/multiqc:1.12--pyhdfd78af_0' }"
input:
- path multiqc_files
+ path multiqc_config
+ path (mqc_custom_config)
+ path workflow_summary
+ path ('fastqc/*')
+ path ('input_*/*')
output:
path "*multiqc_report.html", emit: report
diff --git a/modules/local/split_cooler_dump.nf b/modules/local/split_cooler_dump.nf
index 3ce1aaaed39fce9a1e573f439a802baec5925a25..38e7357e2222b4216fa346fbf12fad3004b1e209 100644
--- a/modules/local/split_cooler_dump.nf
+++ b/modules/local/split_cooler_dump.nf
@@ -11,10 +11,10 @@ process SPLIT_COOLER_DUMP {
script:
def args = task.ext.args ?: ''
- prefix = bedpe.toString() - ~/(\_norm)?.bedpe$/
+ prefix = bedpe.toString() - ~/(\_balanced)?.bedpe$/
"""
cat ${bedpe} | awk '{OFS="\t"; print \$1,\$2,\$3}' > ${prefix}_raw.txt
- cat ${bedpe} | awk '{OFS="\t"; print \$1,\$2,\$4}' > ${prefix}_norm.txt
+ cat ${bedpe} | awk '{OFS="\t"; print \$1,\$2,\$4}' > ${prefix}_balanced.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
diff --git a/modules/local/get_chromsize.nf b/modules/local/trash/get_chromsize.nf
similarity index 100%
rename from modules/local/get_chromsize.nf
rename to modules/local/trash/get_chromsize.nf
diff --git a/modules/local/get_software_versions.nf b/modules/local/trash/get_software_versions.nf
similarity index 86%
rename from modules/local/get_software_versions.nf
rename to modules/local/trash/get_software_versions.nf
index be0d2b514ba664db2a19122f6ac60bb439b9705e..730316d59f951590334fb60a7ee3f0d29b35cd54 100644
--- a/modules/local/get_software_versions.nf
+++ b/modules/local/trash/get_software_versions.nf
@@ -1,8 +1,3 @@
-// Import generic module functions
-include { initOptions; saveFiles; getSoftwareName } from './functions'
-
-params.options = [:]
-options = initOptions(params.options)
process GET_SOFTWARE_VERSIONS {
publishDir "${params.outdir}",
diff --git a/modules/local/output_documentation.nf b/modules/local/trash/output_documentation.nf
similarity index 100%
rename from modules/local/output_documentation.nf
rename to modules/local/trash/output_documentation.nf
diff --git a/modules/nf-core/modules/cooler/cload/main.nf b/modules/nf-core/modules/cooler/cload/main.nf
index 8602fb44862bceb4d6f398404318a10c08c99ad6..2dd29b7234be38112205d3332f4126495030581d 100644
--- a/modules/nf-core/modules/cooler/cload/main.nf
+++ b/modules/nf-core/modules/cooler/cload/main.nf
@@ -12,7 +12,7 @@ process COOLER_CLOAD {
path chromsizes
output:
- tuple val(meta), val(cool_bin), path("*.cool"), emit: cool
+ tuple val(meta), path("*.cool"), val(cool_bin), emit: cool
path "versions.yml" , emit: versions
when:
diff --git a/modules/nf-core/modules/cooler/cload/main.nf~ b/modules/nf-core/modules/cooler/cload/main.nf~
deleted file mode 100644
index 52964b8dd931d30606bb69a122d1529c15470279..0000000000000000000000000000000000000000
--- a/modules/nf-core/modules/cooler/cload/main.nf~
+++ /dev/null
@@ -1,40 +0,0 @@
-process COOLER_CLOAD {
- tag "$meta.id"
- label 'process_high'
-
- conda (params.enable_conda ? "bioconda::cooler=0.8.11" : null)
- container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
- 'https://depot.galaxyproject.org/singularity/cooler:0.8.11--pyh3252c3a_0' :
- 'quay.io/biocontainers/cooler:0.8.11--pyh3252c3a_0' }"
-
- input:
- tuple val(meta), path(pairs), path(index)
- val cool_bin
- path chromsizes
-
- output:
- tuple val(meta), val(cool_bin), path("*.cool"), emit: cool
- path "versions.yml" , emit: versions
-
- when:
- task.ext.when == null || task.ext.when
-
- script:
- def args = task.ext.args ?: ''
- def prefix = task.ext.prefix ?: "${meta.id}"
- def nproc = args.contains('pairix') || args.contains('tabix')? "--nproc $task.cpus" : ''
-
- """
- cooler cload \\
- $args \\
- $nproc \\
- ${chromsizes}:${cool_bin} \\
- $pairs \\
- ${prefix}.${cool_bin}.cool
-
- cat <<-END_VERSIONS > versions.yml
- "${task.process}":
- cooler: \$(cooler --version 2>&1 | sed 's/cooler, version //')
- END_VERSIONS
- """
-}
diff --git a/modules/nf-core/modules/cooler/dump/main.nf b/modules/nf-core/modules/cooler/dump/main.nf
index 5aa98a1723013a0cf19ef409e8ec7e47e2d3b46d..0c01c8dbeab356f7a277426d4fd1cad36d946b50 100644
--- a/modules/nf-core/modules/cooler/dump/main.nf
+++ b/modules/nf-core/modules/cooler/dump/main.nf
@@ -8,7 +8,7 @@ process COOLER_DUMP {
'quay.io/biocontainers/cooler:0.8.11--pyh3252c3a_0' }"
input:
- tuple val(meta), val(resolution), path(cool)
+ tuple val(meta), path(cool), val(resolution)
output:
tuple val(meta), path("*.bedpe"), emit: bedpe
@@ -19,8 +19,8 @@ process COOLER_DUMP {
script:
def args = task.ext.args ?: ''
- def prefix = task.ext.prefix ?: "${cool.baseName}"
- def suffix = resolution ? "::/resolutions/$resolution" : ""
+ def prefix = task.ext.prefix ?: "${meta.id}"
+ def suffix = resolution ? "::$resolution" : ""
"""
cooler dump \\
$args \\
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf
new file mode 100644
index 0000000000000000000000000000000000000000..327d5100560d84eb0020b60acf0db2922497991b
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/main.nf
@@ -0,0 +1,24 @@
+process CUSTOM_DUMPSOFTWAREVERSIONS {
+ label 'process_low'
+
+ // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container
+ conda (params.enable_conda ? "bioconda::multiqc=1.11" : null)
+ container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+ 'https://depot.galaxyproject.org/singularity/multiqc:1.11--pyhdfd78af_0' :
+ 'quay.io/biocontainers/multiqc:1.11--pyhdfd78af_0' }"
+
+ input:
+ path versions
+
+ output:
+ path "software_versions.yml" , emit: yml
+ path "software_versions_mqc.yml", emit: mqc_yml
+ path "versions.yml" , emit: versions
+
+ when:
+ task.ext.when == null || task.ext.when
+
+ script:
+ def args = task.ext.args ?: ''
+ template 'dumpsoftwareversions.py'
+}
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml
new file mode 100644
index 0000000000000000000000000000000000000000..60b546a012c457b5459490e732e6ac9be6979db1
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/meta.yml
@@ -0,0 +1,34 @@
+name: custom_dumpsoftwareversions
+description: Custom module used to dump software versions within the nf-core pipeline template
+keywords:
+ - custom
+ - version
+tools:
+ - custom:
+ description: Custom module used to dump software versions within the nf-core pipeline template
+ homepage: https://github.com/nf-core/tools
+ documentation: https://github.com/nf-core/tools
+ licence: ["MIT"]
+input:
+ - versions:
+ type: file
+ description: YML file containing software versions
+ pattern: "*.yml"
+
+output:
+ - yml:
+ type: file
+ description: Standard YML file containing software versions
+ pattern: "software_versions.yml"
+ - mqc_yml:
+ type: file
+ description: MultiQC custom content YML file containing software versions
+ pattern: "software_versions_mqc.yml"
+ - versions:
+ type: file
+ description: File containing software versions
+ pattern: "versions.yml"
+
+authors:
+ - "@drpatelh"
+ - "@grst"
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
new file mode 100644
index 0000000000000000000000000000000000000000..fda9fc3f809f496767975f3df49d0148d98611be
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py
@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+
+import yaml
+import platform
+from textwrap import dedent
+
+
+def _make_versions_html(versions):
+ html = [
+ dedent(
+ """\\
+ <style>
+ #nf-core-versions tbody:nth-child(even) {
+ background-color: #f2f2f2;
+ }
+ </style>
+ <table class="table" style="width:100%" id="nf-core-versions">
+ <thead>
+ <tr>
+ <th> Process Name </th>
+ <th> Software </th>
+ <th> Version </th>
+ </tr>
+ </thead>
+ """
+ )
+ ]
+ for process, tmp_versions in sorted(versions.items()):
+ html.append("<tbody>")
+ for i, (tool, version) in enumerate(sorted(tmp_versions.items())):
+ html.append(
+ dedent(
+ f"""\\
+ <tr>
+ <td><samp>{process if (i == 0) else ''}</samp></td>
+ <td><samp>{tool}</samp></td>
+ <td><samp>{version}</samp></td>
+ </tr>
+ """
+ )
+ )
+ html.append("</tbody>")
+ html.append("</table>")
+ return "\\n".join(html)
+
+
+versions_this_module = {}
+versions_this_module["${task.process}"] = {
+ "python": platform.python_version(),
+ "yaml": yaml.__version__,
+}
+
+with open("$versions") as f:
+ versions_by_process = yaml.load(f, Loader=yaml.BaseLoader) #| versions_this_module
+
+# aggregate versions by the module name (derived from fully-qualified process name)
+versions_by_module = {}
+for process, process_versions in versions_by_process.items():
+ module = process.split(":")[-1]
+ try:
+ assert versions_by_module[module] == process_versions, (
+ "We assume that software versions are the same between all modules. "
+ "If you see this error-message it means you discovered an edge-case "
+ "and should open an issue in nf-core/tools. "
+ )
+ except KeyError:
+ versions_by_module[module] = process_versions
+
+versions_by_module["Workflow"] = {
+ "Nextflow": "$workflow.nextflow.version",
+ "$workflow.manifest.name": "$workflow.manifest.version",
+}
+
+versions_mqc = {
+ "id": "software_versions",
+ "section_name": "${workflow.manifest.name} Software Versions",
+ "section_href": "https://github.com/${workflow.manifest.name}",
+ "plot_type": "html",
+ "description": "are collected at run time from the software output.",
+ "data": _make_versions_html(versions_by_module),
+}
+
+with open("software_versions.yml", "w") as f:
+ yaml.dump(versions_by_module, f, default_flow_style=False)
+with open("software_versions_mqc.yml", "w") as f:
+ yaml.dump(versions_mqc, f, default_flow_style=False)
+
+with open("versions.yml", "w") as f:
+ yaml.dump(versions_this_module, f, default_flow_style=False)
diff --git a/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py~ b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py~
new file mode 100644
index 0000000000000000000000000000000000000000..be913b7c10a7b0df6bfe7242bfd072f8981538e5
--- /dev/null
+++ b/modules/nf-core/modules/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py~
@@ -0,0 +1,89 @@
+#!/usr/bin/env python
+
+import yaml
+import platform
+from textwrap import dedent
+
+
+def _make_versions_html(versions):
+ html = [
+ dedent(
+ """\\
+ <style>
+ #nf-core-versions tbody:nth-child(even) {
+ background-color: #f2f2f2;
+ }
+ </style>
+ <table class="table" style="width:100%" id="nf-core-versions">
+ <thead>
+ <tr>
+ <th> Process Name </th>
+ <th> Software </th>
+ <th> Version </th>
+ </tr>
+ </thead>
+ """
+ )
+ ]
+ for process, tmp_versions in sorted(versions.items()):
+ html.append("<tbody>")
+ for i, (tool, version) in enumerate(sorted(tmp_versions.items())):
+ html.append(
+ dedent(
+ f"""\\
+ <tr>
+ <td><samp>{process if (i == 0) else ''}</samp></td>
+ <td><samp>{tool}</samp></td>
+ <td><samp>{version}</samp></td>
+ </tr>
+ """
+ )
+ )
+ html.append("</tbody>")
+ html.append("</table>")
+ return "\\n".join(html)
+
+
+versions_this_module = {}
+versions_this_module["${task.process}"] = {
+ "python": platform.python_version(),
+ "yaml": yaml.__version__,
+}
+
+with open("$versions") as f:
+ versions_by_process = yaml.load(f, Loader=yaml.BaseLoader) | versions_this_module
+
+# aggregate versions by the module name (derived from fully-qualified process name)
+versions_by_module = {}
+for process, process_versions in versions_by_process.items():
+ module = process.split(":")[-1]
+ try:
+ assert versions_by_module[module] == process_versions, (
+ "We assume that software versions are the same between all modules. "
+ "If you see this error-message it means you discovered an edge-case "
+ "and should open an issue in nf-core/tools. "
+ )
+ except KeyError:
+ versions_by_module[module] = process_versions
+
+versions_by_module["Workflow"] = {
+ "Nextflow": "$workflow.nextflow.version",
+ "$workflow.manifest.name": "$workflow.manifest.version",
+}
+
+versions_mqc = {
+ "id": "software_versions",
+ "section_name": "${workflow.manifest.name} Software Versions",
+ "section_href": "https://github.com/${workflow.manifest.name}",
+ "plot_type": "html",
+ "description": "are collected at run time from the software output.",
+ "data": _make_versions_html(versions_by_module),
+}
+
+with open("software_versions.yml", "w") as f:
+ yaml.dump(versions_by_module, f, default_flow_style=False)
+with open("software_versions_mqc.yml", "w") as f:
+ yaml.dump(versions_mqc, f, default_flow_style=False)
+
+with open("versions.yml", "w") as f:
+ yaml.dump(versions_this_module, f, default_flow_style=False)
diff --git a/modules/nf-core/modules/custom/getchromsizes/main.nf b/modules/nf-core/modules/custom/getchromsizes/main.nf
new file mode 100644
index 0000000000000000000000000000000000000000..bbcfa9becd254aa507089a34c93ccbf35f78aaa4
--- /dev/null
+++ b/modules/nf-core/modules/custom/getchromsizes/main.nf
@@ -0,0 +1,32 @@
+process CUSTOM_GETCHROMSIZES {
+ tag "$fasta"
+ label 'process_low'
+
+ conda (params.enable_conda ? "bioconda::samtools=1.15" : null)
+ container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+ 'https://depot.galaxyproject.org/singularity/samtools:1.15--h1170115_1' :
+ 'quay.io/biocontainers/samtools:1.15--h1170115_1' }"
+
+ input:
+ path fasta
+
+ output:
+ path '*.sizes' , emit: sizes
+ path '*.fai' , emit: fai
+ path "versions.yml", emit: versions
+
+ when:
+ task.ext.when == null || task.ext.when
+
+ script:
+ def args = task.ext.args ?: ''
+ """
+ samtools faidx $fasta
+ cut -f 1,2 ${fasta}.fai > ${fasta}.sizes
+
+ cat <<-END_VERSIONS > versions.yml
+ "${task.process}":
+ custom: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+ END_VERSIONS
+ """
+}
diff --git a/modules/nf-core/modules/custom/getchromsizes/meta.yml b/modules/nf-core/modules/custom/getchromsizes/meta.yml
new file mode 100644
index 0000000000000000000000000000000000000000..ee6c257185a41746801ae1cccaaef1d31379ddd7
--- /dev/null
+++ b/modules/nf-core/modules/custom/getchromsizes/meta.yml
@@ -0,0 +1,38 @@
+name: custom_getchromsizes
+description: Generates a FASTA file of chromosome sizes and a fasta index file
+keywords:
+ - fasta
+ - chromosome
+ - indexing
+tools:
+ - samtools:
+ description: Tools for dealing with SAM, BAM and CRAM files
+ homepage: http://www.htslib.org/
+ documentation: http://www.htslib.org/doc/samtools.html
+ tool_dev_url: https://github.com/samtools/samtools
+ doi: 10.1093/bioinformatics/btp352
+ licence: ["MIT"]
+
+input:
+ - fasta:
+ type: file
+ description: FASTA file
+ pattern: "*.{fasta}"
+
+output:
+ - sizes:
+ type: file
+ description: File containing chromosome lengths
+ pattern: "*.{sizes}"
+ - fai:
+ type: file
+ description: FASTA index file
+ pattern: "*.{fai}"
+ - versions:
+ type: file
+ description: File containing software version
+ pattern: "versions.yml"
+
+authors:
+ - "@tamara-hodgetts"
+ - "@chris-cheshire"
diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml
deleted file mode 100644
index 6fa891efc2c607fa6e1d081171b1bf2a710443ab..0000000000000000000000000000000000000000
--- a/modules/nf-core/modules/multiqc/meta.yml
+++ /dev/null
@@ -1,40 +0,0 @@
-name: MultiQC
-description: Aggregate results from bioinformatics analyses across many samples into a single report
-keywords:
- - QC
- - bioinformatics tools
- - Beautiful stand-alone HTML report
-tools:
- - multiqc:
- description: |
- MultiQC searches a given directory for analysis logs and compiles a HTML report.
- It's a general use tool, perfect for summarising the output from numerous bioinformatics tools.
- homepage: https://multiqc.info/
- documentation: https://multiqc.info/docs/
- licence: ["GPL-3.0-or-later"]
-input:
- - multiqc_files:
- type: file
- description: |
- List of reports / files recognised by MultiQC, for example the html and zip output of FastQC
-output:
- - report:
- type: file
- description: MultiQC report file
- pattern: "multiqc_report.html"
- - data:
- type: dir
- description: MultiQC data dir
- pattern: "multiqc_data"
- - plots:
- type: file
- description: Plots created by MultiQC
- pattern: "*_data"
- - versions:
- type: file
- description: File containing software versions
- pattern: "versions.yml"
-authors:
- - "@abhi18av"
- - "@bunop"
- - "@drpatelh"
diff --git a/nextflow.config b/nextflow.config
index 1a413b7365ae1222599a798317cd6adb4d049a01..c6ed56da47d4429d9c1005ee34acc1ce126f557c 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -59,8 +59,8 @@ params {
max_restriction_fragment_size = 0
min_insert_size = 0
max_insert_size = 0
- save_nonvalid_pairs = false
-
+ save_pairs_intermediates = false
+
// Dnase Hi-C
dnase = false
min_cis_dist = 0
diff --git a/subworkflows/local/cooler.nf b/subworkflows/local/cooler.nf
index 5c61d8726ef45569d44bf13064e8959c1a0662f7..7e49aa423775be48da82fbbda4a5f93adf5013a4 100644
--- a/subworkflows/local/cooler.nf
+++ b/subworkflows/local/cooler.nf
@@ -1,6 +1,6 @@
/*
* COOLER MAIN WORKFLOW
- * INPUT : pair text file with the list of valid interaction
+ * INPUT : .pair text file with the list of valid interaction
* OUTPUT : cooler files
*/
@@ -12,6 +12,14 @@ include { COOLER_BALANCE } from '../../modules/local/cooler/balance'
include { SPLIT_COOLER_DUMP } from '../../modules/local/split_cooler_dump'
include { COOLER_MAKEBINS } from '../../modules/local/cooler/makebins'
+// add resolution in meta
+def addResolution(row) {
+ def meta = [:]
+ meta.id = row[0].id
+ meta.resolution = row[2]
+ return [meta, row[1], row[2]]
+}
+
workflow COOLER {
take:
@@ -40,8 +48,13 @@ workflow COOLER {
)
ch_versions = ch_versions.mix(COOLER_CLOAD.out.versions)
+ //Add resolution in meta
+ COOLER_CLOAD.out.cool
+ .map{ it -> addResolution(it) }
+ .set{ ch_cool }
+
COOLER_BALANCE(
- COOLER_CLOAD.out.cool
+ ch_cool.map{[it[0], it[1], ""]}
)
ch_versions = ch_versions.mix(COOLER_BALANCE.out.versions)
@@ -51,11 +64,11 @@ workflow COOLER {
}else{
ch_res_zoomify = params.res_zoomify
}
- COOLER_CLOAD.out.cool
+ ch_cool
.combine(ch_res_zoomify)
- .filter{ it [1] == it[3] }
- .map{it->[it[0], it[2]]}
- .set{ch_cool_zoomify}
+ .filter{ it[2] == it[3] }
+ .map{ it->[it[0], it[1]] }
+ .set{ ch_cool_zoomify }
COOLER_ZOOMIFY(
ch_cool_zoomify
@@ -67,12 +80,12 @@ workflow COOLER {
// [meta, cool] / resolution
COOLER_DUMP(
- COOLER_BALANCE.out.cool.map{[it[0], "", it[2]]}
+ COOLER_BALANCE.out.cool.map{[it[0], it[1], ""]}
)
ch_versions = ch_versions.mix(COOLER_DUMP.out.versions)
//COOLER_DUMP(
- // COOLER_ZOOMIFY.out.mcool.combine(cool_bins).map{it->[it[0], it[2], it[1]]}
+ // COOLER_ZOOMIFY.out.mcool.combine(cool_bins).map{it->[it[0], it[1], it[2]]}
//)
SPLIT_COOLER_DUMP(
diff --git a/subworkflows/local/hicpro.nf b/subworkflows/local/hicpro.nf
index 3869d4df9de7538ad3b2fad09296e1cf4e9d9538..f73fd95082e83f096f3fd3ec12155e8826a94af8 100644
--- a/subworkflows/local/hicpro.nf
+++ b/subworkflows/local/hicpro.nf
@@ -1,31 +1,39 @@
/*
- * HICPRO MAIN WORKFLOW
- * INPUT : paired-end sequencing data
- * OUTPUT : .pairs file with the list of valid interaction
+ * HICPRO
+ * MAIN WORKFLOW
+ * From the raw sequencing reads to the list of valid interactions
*/
include { HICPRO_MAPPING } from './hicpro_mapping'
include { GET_VALID_INTERACTION } from '../../modules/local/hicpro/get_valid_interaction'
+include { GET_VALID_INTERACTION_DNASE } from '../../modules/local/hicpro/get_valid_interaction_dnase'
include { MERGE_VALID_INTERACTION } from '../../modules/local/hicpro/merge_valid_interaction'
include { MERGE_STATS } from '../../modules/local/hicpro/merge_stats'
include { HICPRO2PAIRS } from '../../modules/local/hicpro/hicpro2pairs'
include { BUILD_CONTACT_MAPS } from '../../modules/local/hicpro/build_contact_maps'
include { ICE_NORMALIZATION } from '../../modules/local/hicpro/run_ice'
+// Remove meta.chunks
+def removeChunks(row){
+ meta = row[0].clone()
+ meta.remove('chunk')
+ return [meta, row[1]]
+}
+
workflow HICPRO {
take:
reads // [meta, read1, read2]
- index
- fragments
- chrsize
- ligation_site
- map_res
+ index // path
+ fragments // path
+ chrsize // path
+ ligation_site // value
+ map_res // values
main:
ch_versions = Channel.empty()
- // fastq to paired-end bam
+ // Fastq to paired-end bam
HICPRO_MAPPING(
reads,
index,
@@ -33,55 +41,94 @@ workflow HICPRO {
)
ch_versions = ch_versions.mix(HICPRO_MAPPING.out.versions)
- // get valid interaction
- GET_VALID_INTERACTION (
- HICPRO_MAPPING.out.bam,
- fragments
- )
- //TODO ch_versions = ch_versions.mix(GET_VALID_INTERACTION.out.versions)
+ //***************************************
+ // DIGESTION PROTOCOLS
+
+ if (!params.dnase){
+ GET_VALID_INTERACTION (
+ HICPRO_MAPPING.out.bam,
+ fragments.collect()
+ )
+ ch_versions = ch_versions.mix(GET_VALID_INTERACTION.out.versions)
+ ch_valid_pairs = GET_VALID_INTERACTION.out.valid_pairs
+ ch_valid_stats = GET_VALID_INTERACTION.out.stats
+
+ }else{
+
+ //****************************************
+ // DNASE-LIKE PROTOCOLS
+
+ GET_VALID_INTERACTION_DNASE (
+ HICPRO_MAPPING.out.bam
+ )
+ ch_versions = ch_versions.mix(GET_VALID_INTERACTION_DNASE.out.versions)
+ ch_valid_pairs = GET_VALID_INTERACTION_DNASE.out.valid_pairs
+ ch_valid_stats = GET_VALID_INTERACTION_DNASE.out.stats
+ }
+
+
+ //**************************************
+ // MERGE AND REMOVE DUPLICATES
- // merge valid interactions and remove duplicates
+ if (params.split_fastq){
+ ch_valid_pairs = ch_valid_pairs.map{ it -> removeChunks(it)}.groupTuple()
+ ch_hicpro_stats = HICPRO_MAPPING.out.mapstats.map{it->removeChunks(it)}.groupTuple()
+ .concat(HICPRO_MAPPING.out.pairstats.map{it->removeChunks(it)}.groupTuple(),
+ ch_valid_stats.map{it->removeChunks(it)}.groupTuple())
+ }else{
+ ch_hicpro_stats = HICPRO_MAPPING.out.mapstats.groupTuple()
+ .concat(HICPRO_MAPPING.out.pairstats.groupTuple(),
+ ch_valid_stats.groupTuple())
+ }
+
MERGE_VALID_INTERACTION (
- GET_VALID_INTERACTION.out.valid_pairs
+ ch_valid_pairs
)
- // TODO ch_versions = ch_versions.mix(MERGE_VALID_INTERACTION.out.versions)
+ ch_versions = ch_versions.mix(MERGE_VALID_INTERACTION.out.versions)
- // merge stats
- HICPRO_MAPPING.out.mapstats.groupTuple()
- .concat(HICPRO_MAPPING.out.pairstats.groupTuple(),
- GET_VALID_INTERACTION.out.stats.groupTuple())
- .view()
- .set{ ch_hicpro_stats }
+ ch_hicpro_stats.view()
MERGE_STATS(
ch_hicpro_stats
)
- //TODO ch_versions = ch_versions.mix(MERGE_STATS.out.versions)
+ ch_versions = ch_versions.mix(MERGE_STATS.out.versions)
- // convert to pairs
+ //***************************************
+ // CONVERTS TO PAIRS
HICPRO2PAIRS (
MERGE_VALID_INTERACTION.out.valid_pairs,
- chrsize
+ chrsize.collect()
)
- //TODO ch_versions = ch_versions.mix(HICPRO2PAIRS.out.versions)
+ ch_versions = ch_versions.mix(HICPRO2PAIRS.out.versions)
+
+ //***************************************
+ // CONTACT MAPS
+
+ if (params.hicpro_maps){
- if (params.hicpro_maps){
-
//build_contact_maps
BUILD_CONTACT_MAPS(
MERGE_VALID_INTERACTION.out.valid_pairs.combine(map_res),
chrsize.collect()
)
- //TODO ch_versions = ch_versions.mix(BUILD_CONTACT_MAPS.out.versions)
-
+ ch_hicpro_raw_maps = BUILD_CONTACT_MAPS.out.maps
+
// run_ice
ICE_NORMALIZATION(
BUILD_CONTACT_MAPS.out.maps
)
- //TODO ch_versions = ch_versions.mix(ICE_NORMALIZATION.out.versions)
+ ch_hicpro_iced_maps = ICE_NORMALIZATION.out.maps
+ ch_versions = ch_versions.mix(ICE_NORMALIZATION.out.versions)
+
+ }else{
+ ch_hicpro_raw_maps = Channel.empty()
+ ch_hicpro_iced_maps = Channel.empty()
}
emit:
versions = ch_versions
pairs = HICPRO2PAIRS.out.pairs
+ mqc = MERGE_VALID_INTERACTION.out.mqc.concat(MERGE_STATS.out.mqc)
+ raw_maps = ch_hicpro_raw_maps
+ iced_maps = ch_hicpro_iced_maps
}
diff --git a/subworkflows/local/hicpro_mapping.nf b/subworkflows/local/hicpro_mapping.nf
index 0add95df88cd7fdc4bf6ce5538969cf221fcb116..3529f4ef247b5d9ad76d48a021e0023a8a948061 100644
--- a/subworkflows/local/hicpro_mapping.nf
+++ b/subworkflows/local/hicpro_mapping.nf
@@ -1,28 +1,20 @@
+/*
+ * HiC-Pro mapping
+ * From the raw sequencing reads to a paired-end bam file
+ */
+
include { BOWTIE2_ALIGN } from '../../modules/nf-core/modules/bowtie2/align/main'
include { TRIM_READS } from '../../modules/local/hicpro/trim_reads'
include { BOWTIE2_ALIGN as BOWTIE2_ALIGN_TRIMMED } from '../../modules/nf-core/modules/bowtie2/align/main'
include { MERGE_BOWTIE2 } from '../../modules/local/hicpro/bowtie2_merge'
include { COMBINE_MATES} from '../../modules/local/hicpro/combine_mates'
-
-//include { BOWTIE2_ON_TRIMED_READS } from '../../modules/local/bowtie2_on_trimmed_reads' addParams( options: params.options )
-//include { BOWTIE2_MERGE_MAPPING_STEPS } from '../../modules/local/bowtie2_merge_mapping_steps' addParams( options: params.options )
-//include { DNASE_MAPPING_STATS } from '../../modules/local/dnase_mapping_stats' addParams( options: params.options )
-//include { COMBINE_MATES } from '../../modules/local/combine_mates' addParams( options: params.options )
-//include { GET_VALID_INTERACTION } from '../../modules/local/get_valid_interaction' addParams( options: params.options )
-//include { GET_VALID_INTERACTION_DNASE } from '../../modules/local/get_valid_interaction_dnase' addParams( options: params.options )
-//include { REMOVE_DUPLICATES } from '../../modules/local/remove_duplicates' addParams( options: params.options )
-//include { MERGE_STATS } from '../../modules/local/merge_stats' addParams( options: params.options )
-//include { BUILD_CONTACT_MAPS } from '../../modules/local/build_contact_maps' addParams( options: params.options )
-//include { RUN_ICE } from '../../modules/local/run_ice' addParams( options: params.options )
-//include { CONVERTS_TO_PAIRS } from '../../modules/local/convert_to_pairs' addParams( options: params.options )
+include { MAPPING_STATS_DNASE } from '../../modules/local/hicpro/dnase_mapping_stats'
// Paired-end to Single-end
def pairToSingle(row, mates) {
- def meta = [:]
- meta.id = row[0].id
+ def meta = row[0].clone()
meta.single_end = true
meta.mates = mates
- def array = []
if (mates == "R1") {
return [meta, [ row[1][0]] ]
}else if (mates == "R2"){
@@ -30,26 +22,28 @@ def pairToSingle(row, mates) {
}
}
+// Single-end to Paired-end
def singleToPair(row){
- def meta = [:]
- meta.id = row[0].id
+ def meta = row[0].clone()
+ meta.remove('mates')
meta.single_end = false
return [ meta, row[1] ]
}
+
workflow HICPRO_MAPPING {
take:
reads // [meta, read1, read2]
- index
- ligation_site
+ index // path
+ ligation_site // value
main:
ch_versions = Channel.empty()
- // Align each mates separetly
- ch_reads_r1 = reads.map{it -> pairToSingle(it,"R1")}
- ch_reads_r2 = reads.map{pairToSingle(it,"R2")}
+ // Align each mates separetly and add mates information in [meta]
+ ch_reads_r1 = reads.map{ it -> pairToSingle(it,"R1") }
+ ch_reads_r2 = reads.map{ it -> pairToSingle(it,"R2") }
ch_reads = ch_reads_r1.concat(ch_reads_r2)
// bowtie2
@@ -60,47 +54,62 @@ workflow HICPRO_MAPPING {
)
ch_versions = ch_versions.mix(BOWTIE2_ALIGN.out.versions)
- // trim reads
- TRIM_READS(
- BOWTIE2_ALIGN.out.fastq,
- ligation_site.collect()
- )
- ch_versions = ch_versions.mix(TRIM_READS.out.versions)
+ if (!params.dnase){
+ // trim reads
+ TRIM_READS(
+ BOWTIE2_ALIGN.out.fastq,
+ ligation_site.collect()
+ )
+ ch_versions = ch_versions.mix(TRIM_READS.out.versions)
- // bowtie2 on trimmed reads
- BOWTIE2_ALIGN_TRIMMED(
- TRIM_READS.out.fastq,
- index.collect(),
- Channel.value(false).collect()
- )
- ch_versions = ch_versions.mix(BOWTIE2_ALIGN_TRIMMED.out.versions)
+ // bowtie2 on trimmed reads
+ BOWTIE2_ALIGN_TRIMMED(
+ TRIM_READS.out.fastq,
+ index.collect(),
+ Channel.value(false).collect()
+ )
+ ch_versions = ch_versions.mix(BOWTIE2_ALIGN_TRIMMED.out.versions)
- // Merge the two mapping steps
- BOWTIE2_ALIGN.out.bam
- .combine(BOWTIE2_ALIGN_TRIMMED.out.bam, by:[0])
- .view()
- .set { ch_bowtie2_align}
+ // Merge the two mapping steps
+ BOWTIE2_ALIGN.out.bam
+ .combine(BOWTIE2_ALIGN_TRIMMED.out.bam, by:[0])
+ .set { ch_bowtie2_align}
- MERGE_BOWTIE2(
- ch_bowtie2_align
- )
- //TODO ch_versions = ch_versions.mix(MERGE_BOWTIE2.out.versions)
+ MERGE_BOWTIE2(
+ ch_bowtie2_align
+ )
+ ch_versions = ch_versions.mix(MERGE_BOWTIE2.out.versions)
+ ch_mapping_stats = MERGE_BOWTIE2.out.stats
+
+ // Combine mates
+ MERGE_BOWTIE2.out.bam
+ .map { singleToPair(it) }
+ .groupTuple()
+ .set {ch_bams}
+
+ }else{
+
+ MAPPING_STATS_DNASE(
+ BOWTIE2_ALIGN.out.bam
+ )
+ ch_mapping_stats = MAPPING_STATS_DNASE.out.stats
+
+ BOWTIE2_ALIGN.out.bam
+ .map { singleToPair(it) }
+ .groupTuple()
+ .set {ch_bams}
+ }
- // Combine mates
- MERGE_BOWTIE2.out.bam
- .map { singleToPair(it) }
- .groupTuple()
- .view()
- .set {ch_bams}
+ ch_bams.view()
COMBINE_MATES (
ch_bams
)
- //TODO ch_versions = ch_versions.mix(COMBINE_MATES.out.versions)
+ ch_versions = ch_versions.mix(COMBINE_MATES.out.versions)
emit:
versions = ch_versions
bam = COMBINE_MATES.out.bam
- mapstats = MERGE_BOWTIE2.out.stats
+ mapstats = ch_mapping_stats
pairstats = COMBINE_MATES.out.stats
}
diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf
index 267ea4f68ae40eee9ecdd3a4b181fe008896af84..c8582b000832a6be271236592e589d4329e84ee8 100644
--- a/subworkflows/local/input_check.nf
+++ b/subworkflows/local/input_check.nf
@@ -9,10 +9,27 @@ workflow INPUT_CHECK {
samplesheet // file: /path/to/samplesheet.csv
main:
- SAMPLESHEET_CHECK ( samplesheet )
+
+ if (params.split_fastq){
+
+ SAMPLESHEET_CHECK ( samplesheet )
+ .splitCsv ( header:true, sep:',' )
+ .map { create_fastq_channels(it) }
+ .splitFastq( by: params.fastq_chunks_size, pe:true, file: true, compress:true)
+ .map { it ->
+ def meta = it[0].clone()
+ meta.chunk = it[1].baseName - ~/.fastq(.gz)?/
+ return [meta, [it[1], it[2]]]
+ }
+ .set { reads }
+
+ }else{
+ SAMPLESHEET_CHECK ( samplesheet )
.splitCsv ( header:true, sep:',' )
.map { create_fastq_channels(it) }
+ .map { it -> [it[0], [it[1], it[2]]]}
.set { reads }
+ }
emit:
reads // channel: [ val(meta), [ reads ] ]
@@ -21,7 +38,7 @@ workflow INPUT_CHECK {
// Function to get list of [ meta, [ fastq_1, fastq_2 ] ]
def create_fastq_channels(LinkedHashMap row) {
def meta = [:]
- meta.id = row.sample
+ meta.id = row.sample
meta.single_end = false
def array = []
@@ -31,6 +48,6 @@ def create_fastq_channels(LinkedHashMap row) {
if (!file(row.fastq_2).exists()) {
exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}"
}
- array = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ]
+ array = [ meta, file(row.fastq_1), file(row.fastq_2) ]
return array
}
diff --git a/subworkflows/local/prepare_genome.nf b/subworkflows/local/prepare_genome.nf
index 2c4a226dfb42bd3a61cbb491680f8ab549ac9ac7..d9ee28235425c9ea98d83edeaf4663acdd165539 100644
--- a/subworkflows/local/prepare_genome.nf
+++ b/subworkflows/local/prepare_genome.nf
@@ -3,8 +3,8 @@
*/
include { BOWTIE2_BUILD } from '../../modules/nf-core/modules/bowtie2/build/main'
-include { GET_CHROMSIZE } from '../../modules/local/get_chromsize'
-include { GET_RESTRICTION_FRAGMENTS } from '../../modules/local/get_restriction_fragments'
+include { CUSTOM_GETCHROMSIZES } from '../../modules/nf-core/modules/custom/getchromsizes/main'
+include { GET_RESTRICTION_FRAGMENTS } from '../../modules/local/hicpro/get_restriction_fragments'
workflow PREPARE_GENOME {
@@ -22,6 +22,7 @@ workflow PREPARE_GENOME {
fasta
)
ch_index = BOWTIE2_BUILD.out.index
+ ch_versions = ch_versions.mix(BOWTIE2_BUILD.out.versions)
}else{
Channel.fromPath( params.bwt2_index , checkIfExists: true)
.ifEmpty { exit 1, "Genome index: Provided index not found: ${params.bwt2_index}" }
@@ -31,10 +32,11 @@ workflow PREPARE_GENOME {
//***************************************
// Chromosome size
if(!params.chromosome_size){
- GET_CHROMSIZE(
+ CUSTOM_GETCHROMSIZES(
fasta
)
- ch_chromsize = GET_CHROMSIZE.out.results
+ ch_chromsize = CUSTOM_GETCHROMSIZES.out.sizes
+ ch_versions = ch_versions.mix(CUSTOM_GETCHROMSIZES.out.versions)
}else{
Channel.fromPath( params.chromosome_size , checkIfExists: true)
.into {ch_chromsize}
@@ -48,13 +50,17 @@ workflow PREPARE_GENOME {
restriction_site
)
ch_resfrag = GET_RESTRICTION_FRAGMENTS.out.results
- }else{
+ ch_versions = ch_versions.mix(GET_RESTRICTION_FRAGMENTS.out.versions)
+ }else if (!params.dnase){
Channel.fromPath( params.restriction_fragments, checkIfExists: true )
.set {ch_resfrag}
+ }else{
+ ch_resfrag = Channel.empty()
}
emit:
index = ch_index
chromosome_size = ch_chromsize
res_frag = ch_resfrag
+ versions = ch_versions
}
diff --git a/subworkflows/local/tads.nf b/subworkflows/local/tads.nf
index 496e8d6ee13fbd63ae7162ca295b2689e22b84e0..5e7f4fc305e55e6707a2a320026b91292613da71 100644
--- a/subworkflows/local/tads.nf
+++ b/subworkflows/local/tads.nf
@@ -24,4 +24,5 @@ workflow TADS {
emit:
tads = ch_tads
+ versions = ch_versions
}
\ No newline at end of file
diff --git a/workflows/hic.nf b/workflows/hic.nf
index 0204db7e0c10dc8574bf45f8827dd7f1be602b92..4f705df847bf3b6ddbb9a486e562f85858e05e23 100644
--- a/workflows/hic.nf
+++ b/workflows/hic.nf
@@ -6,30 +6,38 @@
def summary_params = NfcoreSchema.paramsSummaryMap(workflow, params)
+//*****************************************
// Validate input parameters
-//WorkflowHic.initialise(params, log)
+WorkflowHic.initialise(params, log)
-// TODO nf-core: Add all file path parameters for the pipeline to the list below
// Check input path parameters to see if they exist
-//def checkPathParamList = [ params.input ]
-//for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
+def checkPathParamList = [ params.input ]
+checkPathParamList = [
+ params.input, params.multiqc_config,
+ params.fasta, params.bwt2_index
+]
+for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
// Check mandatory parameters
if (params.input) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' }
+//*****************************************
// Digestion parameters
if (params.digestion){
restriction_site = params.digestion ? params.digest[ params.digestion ].restriction_site ?: false : false
ch_restriction_site = Channel.value(restriction_site)
-
ligation_site = params.digestion ? params.digest[ params.digestion ].ligation_site ?: false : false
ch_ligation_site = Channel.value(ligation_site)
-}else{
+}else if (params.dnase){
ch_restriction_site = Channel.empty()
ch_ligation_site = Channel.empty()
+}else{
+ exit 1, "Ligation motif not found. Please either use the `--digestion` parameters or specify the `--restriction_site` and `--ligation_site`. For DNase Hi-C, please use '--dnase' option"
}
-// Resolutions for contact maps
+//****************************************
+// Maps resolution for downstream analysis
+
ch_map_res = Channel.from( params.bin_size ).splitCsv().flatten()
if (params.res_tads && !params.skip_tads){
Channel.from( "${params.res_tads}" )
@@ -58,16 +66,12 @@ if (params.res_dist_decay && !params.skip_dist_decay){
}
if (params.res_compartments && !params.skip_compartments){
- //Channel.fromPath( params.fasta )
- // .ifEmpty { exit 1, "Compartments calling: Fasta file not found: ${params.fasta}" }
- // .set { fasta_for_compartments }
Channel.from( "${params.res_compartments}" )
.splitCsv()
.flatten()
.set {ch_comp_res}
ch_map_res = ch_map_res.concat(ch_comp_res)
}else{
- //fasta_for_compartments = Channel.empty()
ch_comp_res = Channel.create()
if (!params.skip_compartments){
log.warn "[nf-core/hic] Hi-C resolution for compartment calling not specified. See --res_compartments"
@@ -90,15 +94,12 @@ ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multi
========================================================================================
*/
-// Don't overwrite global params.modules, create a copy instead and use that within the main script.
-//def modules = params.modules.clone()
-
//
// MODULE: Local to the pipeline
//
-//include { GET_SOFTWARE_VERSIONS } from '../modules/local/get_software_versions'
-//include { OUTPUT_DOCUMENTATION } from '../modules/local/output_documentation'
include { HIC_PLOT_DIST_VS_COUNTS } from '../modules/local/hicexplorer/hicPlotDistVsCounts'
+include { MULTIQC } from '../modules/local/multiqc'
+
//
// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
//
@@ -115,14 +116,12 @@ include { TADS } from '../subworkflows/local/tads'
========================================================================================
*/
-//def multiqc_options = modules['multiqc']
-//multiqc_options.args += params.multiqc_title ? Utils.joinModuleArgs(["--title \"$params.multiqc_title\""]) : ''
-
//
// MODULE: Installed directly from nf-core/modules
//
+include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/modules/custom/dumpsoftwareversions/main'
include { FASTQC } from '../modules/nf-core/modules/fastqc/main'
-//include { MULTIQC } from '../modules/nf-core/modules/multiqc/main' addParams( options: multiqc_options )
+//include { MULTIQC } from '../modules/nf-core/modules/multiqc/main'
/*
========================================================================================
@@ -145,7 +144,7 @@ def multiqc_report = []
workflow HIC {
- ch_software_versions = Channel.empty()
+ ch_versions = Channel.empty()
//
// SUBWORKFLOW: Read in samplesheet, validate and stage input files
@@ -154,6 +153,8 @@ workflow HIC {
ch_input
)
+ INPUT_CHECK.out.reads.view()
+
//
// SUBWORKFLOW: Prepare genome annotation
//
@@ -161,6 +162,7 @@ workflow HIC {
ch_fasta,
ch_restriction_site
)
+ ch_versions = ch_versions.mix(PREPARE_GENOME.out.versions)
//
// MODULE: Run FastQC
@@ -168,6 +170,7 @@ workflow HIC {
FASTQC (
INPUT_CHECK.out.reads
)
+ ch_versions = ch_versions.mix(FASTQC.out.versions)
//
// SUB-WORFLOW: HiC-Pro
@@ -180,6 +183,7 @@ workflow HIC {
ch_ligation_site,
ch_map_res
)
+ ch_versions = ch_versions.mix(HICPRO.out.versions)
//
// SUB-WORKFLOW: COOLER
@@ -189,6 +193,7 @@ workflow HIC {
PREPARE_GENOME.out.chromosome_size,
ch_map_res
)
+ ch_versions = ch_versions.mix(COOLER.out.versions)
//
// MODULE: HICEXPLORER/HIC_PLOT_DIST_VS_COUNTS
@@ -196,13 +201,15 @@ workflow HIC {
if (!params.skip_dist_decay){
COOLER.out.cool
.combine(ch_ddecay_res)
- .filter{ it[1] == it[3] }
- .map { it -> [it[0], it[2]]}
+ .view()
+ .filter{ it[0].resolution == it[2] }
+ .map { it -> [it[0], it[1]]}
.set{ ch_distdecay }
HIC_PLOT_DIST_VS_COUNTS(
ch_distdecay
)
+ ch_versions = ch_versions.mix(HIC_PLOT_DIST_VS_COUNTS.out.versions)
}
//
@@ -211,7 +218,7 @@ workflow HIC {
if (!params.skip_compartments){
COOLER.out.cool
.combine(ch_comp_res)
- .filter{ it[1] == it[3] }
+ .filter{ it[0].resolution == it[2] }
.map { it -> [it[0], it[1], it[2]]}
.set{ ch_cool_compartments }
@@ -220,6 +227,7 @@ workflow HIC {
ch_fasta,
PREPARE_GENOME.out.chromosome_size
)
+ ch_versions = ch_versions.mix(COMPARTMENTS.out.versions)
}
//
@@ -228,15 +236,23 @@ workflow HIC {
if (!params.skip_tads){
COOLER.out.cool
.combine(ch_tads_res)
- .filter{ it[1] == it[3] }
- .map { it -> [it[0], it[2]]}
+ .filter{ it[0].resolution == it[2] }
+ .map { it -> [it[0], it[1]]}
.set{ ch_cool_tads }
TADS(
ch_cool_tads
)
+ ch_versions = ch_versions.mix(TADS.out.versions)
}
+ //
+ // SOFTWARE VERSION
+ //
+ CUSTOM_DUMPSOFTWAREVERSIONS(
+ ch_versions.unique().collectFile(name: 'collated_versions.yml')
+ )
+
//
// MODULE: MultiQC
//
@@ -245,17 +261,19 @@ workflow HIC {
ch_multiqc_files = Channel.empty()
ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_config))
- ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([]))
+ ch_multiqc_files = ch_multiqc_files.mix(Channel.from(ch_multiqc_custom_config.collect().ifEmpty([])))
ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
- //ch_multiqc_files = ch_multiqc_files.mix(GET_SOFTWARE_VERSIONS.out.yaml.collect())
- //ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
-
- //MULTIQC (
- // ch_multiqc_files.collect()
- //)
- //multiqc_report = MULTIQC.out.report.toList()
- multiqc_report = []
- //ch_software_versions = ch_software_versions.mix(MULTIQC.out.version.ifEmpty(null))
+ ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.map{it->it[1]})
+ ch_multiqc_files = ch_multiqc_files.mix(HICPRO.out.mqc)
+
+ MULTIQC (
+ ch_multiqc_config,
+ ch_multiqc_custom_config.collect().ifEmpty([]),
+ ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'),
+ FASTQC.out.zip.map{it->it[1]},
+ HICPRO.out.mqc.collect()
+ )
+ multiqc_report = MULTIQC.out.report.toList()
}
/*