# HG changeset patch
# User jingchunzhu
# Date 1439535881 25200
# Node ID a38cc72edd75c031869c552a56dee830f5249fb7
# Parent  23d98125d20c11d477f3192f15e07c36b46b4c4f
xena header

diff -r 23d98125d20c -r a38cc72edd75 parseSnpEffVcf.py
--- a/parseSnpEffVcf.py	Thu Aug 13 23:26:33 2015 -0700
+++ b/parseSnpEffVcf.py	Fri Aug 14 00:04:41 2015 -0700
@@ -436,7 +436,13 @@
 
     myVcf = vcf(sys.stdin)
 
-    fout =open(args.ID,'w')
+    tmpOutput = "file_"+args.ID
+    fout =open(tmpOutput, 'w')
+
+    if args.ID[-4:]==".vcf":
+        sampleID = args.ID[:-4]
+    else:
+        sampleID = args.ID
 
     for row in myVcf.read():
         #total =total+1
@@ -460,7 +466,7 @@
                 AA_Change = row.effectPerGene[gene]["Amino_Acid_Change"]
                 if AA_Change !="" and AA_Change[:2]!="p.":
                     AA_Change="p."+AA_Change
-                fout.write(string.join([args.ID, row.chr, str(row.start),
+                fout.write(string.join([sampleID, row.chr, str(row.start),
                                         str(row.end), row.reference, row.alt,
                                         gene,row.effectPerGene[gene]["effect"],
                                         str(row.DNA_AF), str(row.RNA_AF),AA_Change
@@ -470,7 +476,7 @@
             gene =""
             AA_Change=""
             effect =""
-            fout.write(string.join([args.ID, row.chr, str(row.start),
+            fout.write(string.join([sampleID, row.chr, str(row.start),
                                     str(row.end), row.reference, row.alt,
                                     gene,effect,
                                     str(row.DNA_AF), str(row.RNA_AF),AA_Change
@@ -478,10 +484,10 @@
                                     ],"\t")+"\n")
     fout.close()
 
-    os.system("cat "+args.ID+" >> "+args.output)
-    os.system("rm -f "+args.ID)
+    os.system("cat "+tmpOutput+" >> "+args.output)
+    os.system("rm -f "+tmpOutput)
 
 if __name__ == '__main__':
-        main()
+    main()
 
 
diff -r 23d98125d20c -r a38cc72edd75 vcfToXena.xml
--- a/vcfToXena.xml	Thu Aug 13 23:26:33 2015 -0700
+++ b/vcfToXena.xml	Fri Aug 14 00:04:41 2015 -0700
@@ -4,7 +4,8 @@
       java -Xmx4G -jar $__tool_directory__/snpEff/snpEff.jar  -c $__tool_directory__/snpEff/snpEff.config 
       -i vcf -upDownStreamLen 5000 $genome
       $input > $__tool_directory__/tmp ;
-      cat $__tool_directory__/tmp | python $__tool_directory__/parseSnpEffVcf.py  $input.name $snpeff_output
+      python $__tool_directory__/xenaHeader.py $snpeff_output;
+      cat $__tool_directory__/tmp | python $__tool_directory__/parseSnpEffVcf.py $input.name $snpeff_output
     </command>
     <inputs>
         <param format="vcf" name="input" type="data" label="Input VCF file"/>
diff -r 23d98125d20c -r a38cc72edd75 xenaHeader.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/xenaHeader.py	Fri Aug 14 00:04:41 2015 -0700
@@ -0,0 +1,14 @@
+import argparse
+import string
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("output", type=str, help="outputfile")
+    args = parser.parse_args()
+
+    fout= open(args.output,'w')
+    fout.write("#"+string.join(["sample","chr","start","end","reference","alt","gene","effect","DNA_VAF","RNA_VAF","Amino_Acid_Change"],"\t")+"\n")
+    fout.close()
+
+if __name__ == '__main__':
+    main()