Initial commit

Dup_Data.sh

+#!/bin/bash
+
+if [ ! -e /work/gad/sv347413/epilepsie/vcf_tmp/$i*.vcf ]
+then
+for i in $(cat /work/gad/sv347413/HLAscan/liste_patients_epileptiques.txt)
+do
+	cp /work/gad/shared/vcf/individu/$i/*.raw.vcf /work/gad/sv347413/epilepsie/vcf_tmp/.
+done
+fi
+
+if [ ! -e /work/gad/sv347413/epilepsie/tsv_tmp/$i*.tsv ]
+then
+for i in $(cat /work/gad/sv347413/HLAscan/liste_patients_epileptiques.txt)
+do 
+	cp /work/gad/shared/vcf/individu/$i/*.cnv.annot.tsv /work/gad/sv347413/epilepsie/tsv_tmp/.
+done
+fi

Master.sh

+#!/bin/bash
+
+set -e;
+true;
+
+i=$1
+
+if [ ! -d /work/gad/sv347413/epilepsie/tmp_res/$i ]
+then
+mkdir /work/gad/sv347413/epilepsie/tmp_res/$i
+fi
+
+if [ ! -e /work/gad/sv347413/epilepsie/tmp_res/$i/$i.SNP.vcf ]
+then
+echo "SNP"
+/work/gad/sv347413/jdk1.8.0_111/bin/java -jar /work/gad/shared/bin/snpEff/SnpSift.jar annotate pharmgkb_v2.vcf /work/gad/sv347413/epilepsie/vcf_tmp/$i.* > /work/gad/sv347413/epilepsie/tmp_res/$i/$i.SNP.vcf
+fi
+
+if [ ! -e /work/gad/sv347413/epilepsie/tmp_res/$i/header_CNV.vcf ]
+then
+echo "CNV" 
+cp /work/gad/sv347413/epilepsie/Pipeline/header_CNV.vcf /work/gad/sv347413/epilepsie/tmp_res/$i/header_CNV.vcf 
+fi
+
+if [ ! -e /work/gad/sv347413/epilepsie/tmp_res/$i/$i.CNV.vcf ]
+then
+echo "CNV2"
+python2.7 tsv2vcf.py /work/gad/sv347413/epilepsie/tsv_tmp/$i* /work/gad/sv347413/epilepsie/tmp_res/$i/header_CNV.vcf
+mv /work/gad/sv347413/epilepsie/tmp_res/$i/header_CNV.vcf /work/gad/sv347413/epilepsie/tmp_res/$i/$i.CNV.vcf
+fi
+
+if [ ! -e /work/gad/sv347413/epilepsie/results_html/$i.html ]
+then
+echo "html"
+python2.7 create_html_v2.py /work/gad/sv347413/epilepsie/tmp_res/$i/$i.SNP.vcf /work/gad/sv347413/epilepsie/tmp_res/$i/$i.CNV.vcf /work/gad/sv347413/HLAscan/results/$i/Report > /work/gad/sv347413/epilepsie/results_html/$i.html
+fi

VCF_tools.py

+class VCF_CNV:
+
+    def __init__(self):
+        self.CHROM = 0
+        self.POS = 0
+        self.ID = "."
+        self.REF = "."
+        self.ALT = "."
+        self.QUAL = 6
+        self.FILTER = "PASS"
+        self.SVTYPE = None
+        self.END = 0
+        self.SVLEN = 0
+        self.CIPOS = "0,0"
+        self.CIEND = "0,0"
+        self.GENE = "."
+        self.FORMAT = "GT:GQ"
+        self.SAMPLE = ".:0"
+
+    def __repr__(self):
+        vcf = "{}\t{}\t{}\t{}\t{}\t{}\t{}\tSVTYPE={};END={};SVLEN={};CIPOS={};CIEND={};GENE={}\t{}\t{}".format(self.CHROM,self.POS,self.ID,self.REF,self.ALT,self.QUAL,self.FILTER,self.SVTYPE,self.END,self.SVLEN,self.CIPOS,self.CIEND,self.GENE,self.FORMAT,self.SAMPLE)
+        return vcf

start.sh

+#!/bin/bash
+
+set -e;
+true;
+
+
+for i in $(cat /work/gad/sv347413/HLAscan/liste_patients_epileptiques.txt)
+do
+echo $i
+	qsub -V -q batch /work/gad/sv347413/epilepsie/Pipeline/Master.sh ${i}
+done

tsv2vcf.py

+import os
+import sys
+
+import vcf
+import csv
+from pyexcel_ods import *
+from VCF_tools import *
+import subprocess
+from operator import *
+
+"""extraction du tableau """
+data = get_data("/work/gad/sv347413/epilepsie/Pipeline/tableau pharmgkb.ods")
+data2 = get_data("/work/gad/sv347413/epilepsie/Pipeline/tableau OMIM.ods")
+
+"""Liste contenant les genes d'interets"""
+ListeG = []
+
+"""recuperation des genes dans le fichier"""
+for i in range(len(data["hg19"])-1):
+    if not data["hg19"][i]:
+        pass
+    else:
+        if data["hg19"][i][1] != "gene":
+            """remplissage de la liste"""
+            if data["hg19"][i][1] not in ListeG:
+                ListeG.append((data["hg19"][i][1]))
+for i in range(len(data2["hg19"])-1):
+    if not data2["hg19"][i]:
+        pass
+    else:
+        if data2["hg19"][i][1] != "GENE":
+            if data2["hg19"][i][1] not in ListeG:
+                ListeG.append((data2["hg19"][i][1]))
+
+#print(ListeG)
+
+"""ecriture des lignes CNV dans le vcf"""
+
+ListeVCF=[]
+
+for gene in ListeG:
+    with open(sys.argv[1]) as tsvfile:
+        reader = csv.DictReader(tsvfile, dialect='excel-tab')
+        for row in reader:
+            if gene in row['GeneList'] and gene != "":
+                line_vcf = VCF_CNV()
+                line_vcf.CHROM = row["#CHR"]
+                line_vcf.POS = row["START"]
+                p = subprocess.Popen(["samtools", 'faidx',"index/hg19_essential.fa", row["#CHR"]+":"+row["START"]+"-"+row["START"]], stdout = subprocess.PIPE)
+                line_vcf.REF = p.stdout.readlines()[1].strip("\n")
+                line_vcf.ALT = "<"+row["CNV"]+">"
+                line_vcf.QUAL = "6"
+                line_vcf.SVTYPE = row["CNV"]
+                line_vcf.END = row["END"]
+                if row["CNV"] == "DEL":
+                    line_vcf.SVLEN = "-"+row["CNVLength"]
+                else :
+                    line_vcf.SVLEN =row["CNVLength"]
+                line_vcf.GENE = str(gene)
+                ListeVCF.append(line_vcf)
+
+ListeVCF = sorted(ListeVCF,key=attrgetter('POS'))
+
+#print ListeVCF
+
+for line in ListeVCF:
+    with open (sys.argv[2],'a') as vcf_out:
+        vcf_out.write(repr(line)+"\n")
+
+#test = vcf.Reader(filename = "header_CNV.vcf")
+#for record in test:
+#    print record