From feccab2cc027ce2837fbd9f7a9dcb17b4303f093 Mon Sep 17 00:00:00 2001
From: gmillot <gael.millot@pasteur.fr>
Date: Fri, 24 Jun 2022 19:41:30 +0200
Subject: [PATCH] release v3.0: vcf_ficher.nf now parallelized for all the
genome
---
README.md | 5 +++++
bin/fisher_lod.py | 17 +++++++++--------
vcf_fisher.config | 2 +-
vcf_fisher.nf | 14 +++++++++-----
4 files changed, 24 insertions(+), 14 deletions(-)
diff --git a/README.md b/README.md
index 8710596..debb259 100644
--- a/README.md
+++ b/README.md
@@ -203,6 +203,11 @@ Gitlab developers
<br /><br />
## WHAT'S NEW IN
+### v3.0
+
+1) vcf_ficher.nf now parallelized for all the genome
+
+
### v2.1
1) vcf_ficher.nf improved for the whole genome
diff --git a/bin/fisher_lod.py b/bin/fisher_lod.py
index a827afe..0a2ac08 100644
--- a/bin/fisher_lod.py
+++ b/bin/fisher_lod.py
@@ -182,11 +182,11 @@ random.seed(1)
################ Ignition
-if region == "None":
- region = None
-else:
- # region = region.strip('[]').replace('"', '').replace(' ', '').split(',') # old version when no parall in nf
- region = region.replace('"', '').replace(' ', '')
+# if region == "None":
+# region = None
+#else:
+# # region = region.strip('[]').replace('"', '').replace(' ', '').split(',') # old version when no parall in nf
+# region = region.replace('"', '').replace(' ', '')
################ End ignition
@@ -240,9 +240,10 @@ with warnings.catch_warnings():
# for v in vcf(i1):
# tempo = fisher(v = v, columns = columns)
# df = df.append(tempo)
- for v in vcf:
- tempo = fisher(v = v, columns = columns)
- df = df.append(tempo)
+ for v in vcf: # parse each line of vcf with the content of region in it
+ if v.CHROM == region:
+ tempo = fisher(v = v, columns = columns)
+ df = df.append(tempo)
# on ecrit la dataframe dans un fichier
df.to_csv('./fisher.tsv', sep='\t', index=False)
diff --git a/vcf_fisher.config b/vcf_fisher.config
index 45fa722..00ab124 100644
--- a/vcf_fisher.config
+++ b/vcf_fisher.config
@@ -20,7 +20,7 @@ env {
//Warning: do not write the out_path now. See below. If written here, the one below is not considered"
ped_path = "/pasteur/zeus/projets/p01/BioIT/gmillot/08002_bourgeron/dataset/Dyslexia.pedigree.txt" // pedigree
chr_path = "/pasteur/zeus/projets/p01/BioIT/gmillot/reference_genomes/human hg19_grch37/hg19_grch37p5_chr_size_cumul.txt"
- region = "chr7, chr1, chr2" // region to parse. Write "chr7:0-147000000, chr10:1000000-2000000" for a single region, "chr7:0-147000000, chr10:1000000-2000000" if two regions, ""chr7" for a whole chromosome, "chr7, chr1" for two chromosomes and "None" for the complete genome // Warning : replace eval() by ast.literal_eval() from ast package in the main py code ?
+ region = "None" // region to parse. Write "chr7:0-147000000, chr10:1000000-2000000" for a single region, "chr7:0-147000000, chr10:1000000-2000000" if two regions, ""chr7" for a whole chromosome, "chr7, chr1" for two chromosomes and "None" for the complete genome // Warning : replace eval() by ast.literal_eval() from ast package in the main py code ?
y_lim1 = 5 // max y-axis limit of the top panel in the miami plot, in log10, i.e., 5 means up to score 10^5
y_lim2 = 5 // max y-axis limit of the bottom panel in the miami plot, in log10, i.e., 5 means up to score 10^5
cute_path = "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/-/raw/v11.4.0/cute_little_R_functions.R" // single character string indicating the file (and absolute pathway) of the required cute_little_R_functions toolbox. With ethernet connection available, this can also be used: "https://gitlab.pasteur.fr/gmillot/cute_little_R_functions/raw/v5.1.0/cute_little_R_functions.R" or local "C:\\Users\\Gael\\Documents\\Git_projects\\cute_little_R_functions\\cute_little_R_functions.R"
diff --git a/vcf_fisher.nf b/vcf_fisher.nf
index 92b7e6b..6946670 100644
--- a/vcf_fisher.nf
+++ b/vcf_fisher.nf
@@ -131,7 +131,7 @@ process WorkflowVersion { // create a file with the workflow version in out_path
process fisher {
label 'python' // see the withLabel: bash in the nextflow config file
- publishDir path: "${out_path}", mode: 'copy', overwrite: false
+ //publishDir path: "${out_path}", mode: 'copy', overwrite: false
cache 'true'
//no channel input here for the vcf, because I do not transform it
@@ -143,7 +143,7 @@ process fisher {
//val region2 from region_ch
output:
- file "*.tsv" into fisher_ch
+ file "*.tsv" into fisher_ch1 // multi channel
script:
"""
@@ -151,17 +151,20 @@ process fisher {
fisher_lod.py ${vcf} ${ped} "${region2}"
"""
}
-fisher_ch.collectFile(name: "fisher.tsv").subscribe{it -> it.copyTo("${out_path}")} // concatenate all the cov_report.txt files in channel cov_report_ch into a single file published into ${out_path}/reports
+
+fisher_ch1.collectFile(name: "fisher.tsv", skip:1, keepHeader:true).into{fisher_ch2 ; fisher_ch3}
+fisher_ch2.subscribe{it -> it.copyTo("${out_path}")}
process miamiplot {
label 'r_ext' // see the withLabel: bash in the nextflow config file
- publishDir path: "${out_path}", mode: 'copy', overwrite: false
+ publishDir "${out_path}", mode: 'copy', pattern: "{*.png}", overwrite: false // https://docs.oracle.com/javase/tutorial/essential/io/fileOps.html#glob
+ publishDir "${out_path}/reports", mode: 'copy', pattern: "{miami_report.txt}", overwrite: false // https://docs.oracle.com/javase/tutorial/essential/io/fileOps.html#glob
cache 'true'
//no channel input here for the vcf, because I do not transform it
input:
- file fisher from fisher_ch
+ file fisher from fisher_ch3
file chr from chr_ch
val y_lim1
val y_lim2
@@ -180,6 +183,7 @@ process miamiplot {
}
+
process Backup {
label 'bash' // see the withLabel: bash in the nextflow config file
publishDir "${out_path}/reports", mode: 'copy', overwrite: false // since I am in mode copy, all the output files will be copied into the publishDir. See \\wsl$\Ubuntu-20.04\home\gael\work\aa\a0e9a739acae026fb205bc3fc21f9b
--
GitLab