helper scripts

print_fields_from_vcf.py

@@ -11,8 +11,21 @@ parser.add_argument("-m", "--method", help="annotation method", type=str, choice
 def vcfelements(line): # parse the main, tab-delimited elements of the VCF line
    vcf_elements=line.split('\t')
    vcf_elements[7]=tagelements(vcf_elements[7])
+   if len(vcf_elements)>9: # check if genotype fields present; this requires at least 2 additional columns
+      vcf_elements=list_genotypes(vcf_elements)
+   else :
+      vcf_elements.append([])  # make sure that the data structure is allways of lenth 9
    return vcf_elements # return list
 
+def list_genotypes(vcflist): # reshape the genotypes to a single list
+   genotypes=vcflist[9:]
+   gt_field=list()
+   gt_field.append(vcflist[8])
+   gt_field.append(genotypes)
+   vcflist=vcflist[0:8]
+   vcflist.append(gt_field)
+   return vcflist
+
 def tagelements(tag): # parse the fields/tags in the 8th column - ';' delimited
    tags=tag.split(';')
    tagdict={tag.split('=')[0]:tag.split('=')[1] for tag in tags}
@@ -73,6 +86,7 @@ if __name__=="__main__":
          myline=myline[:-1]
          if not myline.startswith('#'): # avoid VCF comment lines
             vcf_line=vcfelements(myline)
+            print(vcf_line)
             print_by_method(vcf_line,method)
    except (BrokenPipeError,IOError): # exception handling for BrokenPipeError; works in P3.3, not P3.4! Need this workaround
      sys.stdout.write = _void_f