From a35879eef58b0fe43dc7b39917db65007d2200f7 Mon Sep 17 00:00:00 2001
From: nservant <nicolas.servant@curie.fr>
Date: Wed, 14 Apr 2021 20:50:25 +0200
Subject: [PATCH] [MODIF] fix issue in json and bwt2 index
---
conf/test.config | 3 ++
conf/test_full.config | 22 ++++++-------
main.nf | 32 ++++++++++--------
nextflow.config | 8 ++---
nextflow_schema.json | 77 +++++++++++++++++--------------------------
5 files changed, 66 insertions(+), 76 deletions(-)
diff --git a/conf/test.config b/conf/test.config
index d06ad50..5c5fc84 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -35,4 +35,7 @@ params {
res_tads = '1000'
tads_caller = 'insulation,hicexplorer'
res_compartments = '1000'
+
+ // Ignore `--input` as otherwise the parameter validation will throw an error
+ schema_ignore_params = 'genomes,digest,input_paths,input'
}
diff --git a/conf/test_full.config b/conf/test_full.config
index 65dcbf8..1e793cc 100644
--- a/conf/test_full.config
+++ b/conf/test_full.config
@@ -11,8 +11,6 @@ params {
config_profile_name = 'Full test profile'
config_profile_description = 'Full test dataset to check pipeline function'
- // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
- // TODO nf-core: Give any required params for the test so that command line flags are not needed
// Input data for full size test
input_paths = [
['SRR4292758_00', ['https://github.com/nf-core/test-datasets/raw/hic/data/SRR4292758_00_R1.fastq.gz', 'https://github.com/nf-core/test-datasets/raw/hic/data/SRR4292758_00_R2.fastq.gz']]
@@ -20,19 +18,19 @@ params {
// Annotations
fasta = 'https://github.com/nf-core/test-datasets/raw/hic/reference/W303_SGD_2015_JRIU00000000.fsa'
- restriction_site = 'A^AGCTT'
- ligation_site = 'AAGCTAGCTT'
-
- min_mapq = 2
- rm_dup = true
- rm_singleton = true
- rm_multi = true
-
+ digestion = 'hindiii'
+ min_mapq = 10
min_restriction_fragment_size = 100
max_restriction_fragment_size = 100000
min_insert_size = 100
max_insert_size = 600
+
+ bin_size = '1000'
+ res_dist_decay = '1000'
+ res_tads = '1000'
+ tads_caller = 'insulation,hicexplorer'
+ res_compartments = '1000'
- // Options
- skip_cool = true
+ // Ignore `--input` as otherwise the parameter validation will throw an error
+ schema_ignore_params = 'genomes,digest,input_paths,input'
}
diff --git a/main.nf b/main.nf
index 776a48e..e45087a 100644
--- a/main.nf
+++ b/main.nf
@@ -121,19 +121,19 @@ if (params.split_fastq ){
// Reference genome
if ( params.bwt2_index ){
- lastPath = params.bwt2_index.lastIndexOf(File.separator)
- bwt2_dir = params.bwt2_index.substring(0,lastPath+1)
- bwt2_base = params.bwt2_index.substring(lastPath+1)
+ //lastPath = params.bwt2_index.lastIndexOf(File.separator)
+ //bwt2_dir = params.bwt2_index.substring(0,lastPath+1)
+ //bwt2_base = params.bwt2_index.substring(lastPath+1)
- Channel.fromPath( bwt2_dir , checkIfExists: true)
+ Channel.fromPath( params.bwt2_index , checkIfExists: true)
.ifEmpty { exit 1, "Genome index: Provided index not found: ${params.bwt2_index}" }
.into { bwt2_index_end2end; bwt2_index_trim }
}
else if ( params.fasta ) {
- lastPath = params.fasta.lastIndexOf(File.separator)
- fasta_base = params.fasta.substring(lastPath+1)
- bwt2_base = fasta_base.toString() - ~/(\.fa)?(\.fasta)?(\.fas)?(\.fsa)?$/
+ //lastPath = params.fasta.lastIndexOf(File.separator)
+ //fasta_base = params.fasta.substring(lastPath+1)
+ //fasta_base = fasta_base.toString() - ~/(\.fa)?(\.fasta)?(\.fas)?(\.fsa)?$/
Channel.fromPath( params.fasta )
.ifEmpty { exit 1, "Genome index: Fasta file not found: ${params.fasta}" }
@@ -329,7 +329,7 @@ process get_software_versions {
if(!params.bwt2_index && params.fasta){
process makeBowtie2Index {
- tag "$bwt2_base"
+ tag "$fasta_base"
label 'process_highmem'
publishDir path: { params.save_reference ? "${params.outdir}/reference_genome" : params.outdir },
saveAs: { params.save_reference ? it : null }, mode: params.publish_dir_mode
@@ -342,9 +342,10 @@ if(!params.bwt2_index && params.fasta){
file "bowtie2_index" into bwt2_index_trim
script:
+ fasta_base = fasta.toString() - ~/(\.fa)?(\.fasta)?(\.fas)?(\.fsa)?$/
"""
mkdir bowtie2_index
- bowtie2-build ${fasta} bowtie2_index/${bwt2_base}
+ bowtie2-build ${fasta} bowtie2_index/${fasta_base}
"""
}
}
@@ -418,19 +419,21 @@ process bowtie2_end_to_end {
def bwt2_opts = params.bwt2_opts_end2end
if (!params.dnase){
"""
+ INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
bowtie2 --rg-id BMG --rg SM:${prefix} \\
${bwt2_opts} \\
-p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
+ -x \${INDEX} \\
--un ${prefix}_unmap.fastq \\
-U ${reads} | samtools view -F 4 -bS - > ${prefix}.bam
"""
}else{
"""
+ INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
bowtie2 --rg-id BMG --rg SM:${prefix} \\
${bwt2_opts} \\
-p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
+ -x \${INDEX} \\
--un ${prefix}_unmap.fastq \\
-U ${reads} > ${prefix}.bam
"""
@@ -480,10 +483,11 @@ process bowtie2_on_trimmed_reads {
script:
prefix = reads.toString() - ~/(_trimmed)?(\.fq)?(\.fastq)?(\.gz)?$/
"""
+ INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
bowtie2 --rg-id BMG --rg SM:${prefix} \\
${params.bwt2_opts_trimmed} \\
-p ${task.cpus} \\
- -x ${index}/${bwt2_base} \\
+ -x \${INDEX} \\
-U ${reads} | samtools view -bS - > ${prefix}_trimmed.bam
"""
}
@@ -784,9 +788,9 @@ process run_ice{
script:
prefix = rmaps.toString() - ~/(\.matrix)?$/
"""
- ice --filter_low_counts_perc ${params.ice_filer_low_count_perc} \
+ ice --filter_low_counts_perc ${params.ice_filter_low_count_perc} \
--results_filename ${prefix}_iced.matrix \
- --filter_high_counts_perc ${params.ice_filer_high_count_perc} \
+ --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 ${rmaps}
"""
}
diff --git a/nextflow.config b/nextflow.config
index 48a1cbc..c5b39ad 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -63,8 +63,8 @@ params {
bin_size = '1000000'
res_zoomify = '5000'
ice_max_iter = 100
- ice_filer_low_count_perc = 0.02
- ice_filer_high_count_perc = 0
+ ice_filter_low_count_perc = 0.02
+ ice_filter_high_count_perc = 0
ice_eps = 0.1
// Downstream Analysis
@@ -86,7 +86,6 @@ params {
// Boilerplate options
publish_dir_mode = 'copy'
multiqc_config = false
- name = false
email = false
email_on_fail = false
max_multiqc_email_size = 25.MB
@@ -101,12 +100,13 @@ params {
custom_config_version = 'master'
custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
hostnames = false
+ config_profile_name = false
config_profile_description = false
config_profile_contact = false
config_profile_url = false
validate_params = true
show_hidden_params = false
- schema_ignore_params = 'genomes,input_paths'
+ schema_ignore_params = 'genomes,digest,input_paths'
// Defaults only, expecting to be overwritten
max_memory = 24.GB
diff --git a/nextflow_schema.json b/nextflow_schema.json
index f866246..9274877 100644
--- a/nextflow_schema.json
+++ b/nextflow_schema.json
@@ -133,7 +133,6 @@
},
"min_cis_dist": {
"type": "integer",
- "default": "O",
"description": "Minimum distance between loci to consider. Useful for --dnase mode to remove spurious ligation products. Only values > 0 are considered"
}
}
@@ -148,17 +147,16 @@
"split_fastq": {
"type": "boolean",
"description": "Split the reads into chunks before running the pipelne",
- "fa_icon": "fas fa-dna",
- "default": "false"
+ "fa_icon": "fas fa-dna"
},
"fastq_chunks_size": {
"type": "integer",
"description": "Read number per chunks if split_fastq is used",
- "default": "20000000"
+ "default": 20000000
},
"min_mapq": {
"type": "integer",
- "default": "10",
+ "default": 10,
"description": "Keep aligned reads with a minimum quality value"
},
"bwt2_opts_end2end": {
@@ -185,33 +183,27 @@
"fa_icon": "fas fa-signature",
"properties": {
"keep_dups": {
- "type": "string",
- "description": "Keep duplicated reads",
- "default": "False"
+ "type": "boolean",
+ "description": "Keep duplicated reads"
},
"keep_multi": {
- "type": "string",
- "description": "Keep multi-aligned reads",
- "default": "False"
+ "type": "boolean",
+ "description": "Keep multi-aligned reads"
},
"max_insert_size": {
"type": "integer",
- "default": "0",
"description": "Maximum fragment size to consider. Only values > 0 are considered"
},
"min_insert_size": {
"type": "integer",
- "default": "0",
"description": "Minimum fragment size to consider. Only values > 0 are considered"
},
"max_restriction_fragment_size": {
"type": "integer",
- "default": "0",
"description": "Maximum restriction fragment size to consider. Only values > 0 are considered"
},
"min_restriction_fragment_size": {
"type": "integer",
- "default": "0",
"description": "Minimum restriction fragment size to consider. Only values > 0 are considered"
},
"save_interaction_bam": {
@@ -232,29 +224,28 @@
"default": "'1000000,500000'",
"description": "Resolution to build the maps (comma separated)"
},
- "ice_filer_low_count_perc": {
- "type": "string",
+ "ice_filter_low_count_perc": {
+ "type": "number",
"default": 0.02,
"description": "Filter low counts rows before normalization"
},
- "ice_filer_high_count_perc": {
+ "ice_filter_high_count_perc": {
"type": "integer",
- "default": "0",
"description": "Filter high counts rows before normalization"
},
"ice_eps": {
- "type": "string",
- "default": "0.1",
+ "type": "number",
+ "default": 0.1,
"description": "Threshold for ICE convergence"
},
"ice_max_iter": {
"type": "integer",
- "default": "100",
+ "default": 100,
"description": "Maximum number of iteraction for ICE normalization"
},
"res_zoomify": {
- "type": "integer",
- "default": 5000,
+ "type": "string",
+ "default": "5000",
"description": "Maximum resolution to build mcool file"
}
}
@@ -266,8 +257,8 @@
"default": "",
"properties": {
"res_dist_decay": {
- "type": "integer",
- "default": 1000000,
+ "type": "string",
+ "default": "1000000",
"description": "Resolution to build count/distance plot"
},
"tads_caller": {
@@ -281,8 +272,8 @@
"description": "Resolution to run TADs callers (comma separated)"
},
"res_compartments": {
- "type": "integer",
- "default": 250000,
+ "type": "string",
+ "default": "250000",
"description": "Resolution for compartments calling"
}
}
@@ -299,33 +290,28 @@
"description": "Do not build contact maps"
},
"skip_ice": {
- "type": "string",
- "description": "Do not run ICE normalization",
- "default": "False"
+ "type": "boolean",
+ "description": "Do not run ICE normalization"
},
"skip_dist_decay": {
- "type": "string",
- "description": "Do not run distance/decay plot",
- "default": "False"
+ "type": "boolean",
+ "description": "Do not run distance/decay plot"
},
"skip_tads": {
- "type": "string",
- "description": "Do not run TADs calling",
- "default": "False"
+ "type": "boolean",
+ "description": "Do not run TADs calling"
},
"skip_compartments": {
"type": "string",
"description": "Do not run compartments calling"
},
"skip_balancing": {
- "type": "string",
- "description": "Do not run cooler balancing normalization",
- "default": "False"
+ "type": "boolean",
+ "description": "Do not run cooler balancing normalization"
},
"skip_mcool": {
- "type": "string",
- "description": "Do not generate mcool file for Higlass visualization",
- "default": "False"
+ "type": "boolean",
+ "description": "Do not generate mcool file for Higlass visualization"
},
"skip_multiqc": {
"type": "boolean",
@@ -487,9 +473,8 @@
},
"config_profile_name": {
"type": "string",
- "description": "Institutional config name.",
- "hidden": true,
- "fa_icon": "fas fa-users-cog"
+ "description": "Institutional config name",
+ "hidden": true
},
"config_profile_description": {
"type": "string",
--
GitLab