From 322c97aca6abdbe3524a46bcaae25f17c26846e8 Mon Sep 17 00:00:00 2001
From: nservant <nservant@curie.fr>
Date: Mon, 15 Apr 2019 13:22:52 +0200
Subject: [PATCH] update test-dataset
---
conf/hicpro.config | 10 +++++-----
conf/test.config | 13 ++++++++-----
main.nf | 27 ++++++++++++++++++---------
nextflow.config | 3 ++-
4 files changed, 33 insertions(+), 20 deletions(-)
diff --git a/conf/hicpro.config b/conf/hicpro.config
index d969960..5d145a1 100644
--- a/conf/hicpro.config
+++ b/conf/hicpro.config
@@ -13,15 +13,15 @@ params {
splitFastq = false
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 = 0
+ min_mapq = 0
// Digestion Hi-C
restriction_site = 'A^AGCTT'
ligation_site = 'AAGCTAGCTT'
- min_restriction_fragment_size = 100
- max_restriction_fragment_size = 100000
- min_insert_size = 100
- max_insert_size = 600
+ min_restriction_fragment_size =
+ max_restriction_fragment_size =
+ min_insert_size =
+ max_insert_size =
// Hi-C Processing
min_cis_dist =
diff --git a/conf/test.config b/conf/test.config
index 1dd0992..d8220d2 100644
--- a/conf/test.config
+++ b/conf/test.config
@@ -9,7 +9,7 @@
params {
- config_profile_name = 'Hi-C test data from Dixon et al. (2012)'
+ config_profile_name = 'Hi-C test data from Schalbetter et al. (2017)'
config_profile_description = 'Minimal test dataset to check pipeline function'
// Limit resources so that this can run on Travis
@@ -19,10 +19,13 @@ 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']]
- ]
+ ['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']]
+ ]
// Annotations
- genome = 'GRCh37'
+ fasta = 'https://github.com/nf-core/test-datasets/raw/hic/reference/W303_SGD_2015_JRIU00000000.fsa'
+
+ // Options
+ skip_cool = true
}
+
diff --git a/main.nf b/main.nf
index 53798f4..8ac8bd5 100644
--- a/main.nf
+++ b/main.nf
@@ -33,11 +33,11 @@ def helpMessage() {
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.
References If not specified in the configuration file or you wish to overwrite any of the references.
+ --genome Name of iGenomes reference
--bwt2_index Path to Bowtie2 index
--fasta Path to Fasta reference
--chromosome_size Path to chromosome size file
@@ -72,6 +72,10 @@ def helpMessage() {
--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.
+ Step options:
+ --skip_cool Skip generation of cool files
+ --skip_multiQC Skip MultiQC
+
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
@@ -138,8 +142,7 @@ if (params.readPaths){
.from( params.readPaths )
.map { row -> [ row[0], [file(row[1][0]), file(row[1][1])]] }
.separate( raw_reads, raw_reads_2 ) { a -> [tuple(a[0], a[1][0]), tuple(a[0], a[1][1])] }
- .println()
-}else{
+ }else{
raw_reads = Channel.create()
raw_reads_2 = Channel.create()
@@ -674,6 +677,9 @@ process generate_cool{
tag "$sample"
publishDir "${params.outdir}/export/cool", mode: 'copy'
+ when:
+ !params.skip_cool
+
input:
set val(sample), file(vpairs) from all_valid_pairs_4cool
file chrsize from chromosome_size_cool.collect()
@@ -694,15 +700,18 @@ process generate_cool{
process multiqc {
publishDir "${params.outdir}/MultiQC", mode: 'copy'
+ when:
+ !params.skip_multiqc
+
input:
- file multiqc_config from ch_multiqc_config
- file ('input_*/*') from all_mstats.concat(all_mergestat).collect()
- file ('software_versions/*') from software_versions_yaml
- file workflow_summary from create_workflow_summary(summary)
+ file multiqc_config from ch_multiqc_config
+ file ('input_*/*') from all_mstats.concat(all_mergestat).collect()
+ file ('software_versions/*') from software_versions_yaml
+ file workflow_summary from create_workflow_summary(summary)
output:
- file "*multiqc_report.html" into multiqc_report
- file "*_data"
+ file "*multiqc_report.html" into multiqc_report
+ file "*_data"
script:
rtitle = custom_runName ? "--title \"$custom_runName\"" : ''
diff --git a/nextflow.config b/nextflow.config
index 0a46040..c9f2203 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -24,7 +24,8 @@ params {
readPaths = false
chromosome_size = false
restriction_fragments = false
-
+ skip_cool = false
+ skip_multiqc = false
// Boilerplate options
name = false
--
GitLab