Mercurial > repos > saskia-hiltemann > cgatools_v17
comparison tools/cgatools17/vcf_to_listVariants.py @ 1:3a2e0f376f26 draft
Minor change to tv2vcf.xml to allow for workflow automation
| author | dgdekoning |
|---|---|
| date | Wed, 21 Oct 2015 10:09:15 -0400 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| 0:751b62d30ae1 | 1:3a2e0f376f26 |
|---|---|
| 1 #!/usr/bin/env python | |
| 2 | |
| 3 """[License: GNU General Public License v3 (GPLv3)] | |
| 4 | |
| 5 This is free software: you can redistribute it and/or modify | |
| 6 it under the terms of the GNU General Public License as published by | |
| 7 the Free Software Foundation, either version 3 of the License, or | |
| 8 (at your option) any later version. | |
| 9 | |
| 10 This is distributed in the hope that it will be useful, | |
| 11 but WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
| 13 GNU General Public License for more details. | |
| 14 | |
| 15 You should have received a copy of the GNU General Public License | |
| 16 along with this program. If not, see <http://www.gnu.org/licenses/>. | |
| 17 | |
| 18 Documentation as defined by: | |
| 19 <http://epydoc.sourceforge.net/manual-fields.html#fields-synonyms> | |
| 20 """ | |
| 21 | |
| 22 import sys,os,os.path,argparse,textwrap,datetime | |
| 23 | |
| 24 def convert_vcf_to_listVariants(filename_in, filename_out): | |
| 25 if(filename_out == "-"): | |
| 26 fh_out = sys.stdout | |
| 27 else: | |
| 28 fh_out = open(filename_out,"w") | |
| 29 | |
| 30 i = 1 | |
| 31 | |
| 32 fh_out.write("variantId\tchromosome\tbegin\tend\tvarType\treference\talleleSeq\txRef\n") | |
| 33 | |
| 34 with open(filename_in, 'r') as fh_in: | |
| 35 for line in fh_in: | |
| 36 line_s = line.strip() | |
| 37 if((len(line_s) >= 6) and line_s[0] != "#"): | |
| 38 params = line.split("\t") | |
| 39 | |
| 40 if(len(params[4]) == 1):# single base substitution | |
| 41 fh_out.write(str(i)) # id | |
| 42 | |
| 43 fh_out.write("\t"+params[0]) # chr | |
| 44 fh_out.write("\t"+str(int(params[1])-1)) # begin | |
| 45 fh_out.write("\t"+params[1]) # end | |
| 46 fh_out.write("\tsnp") | |
| 47 fh_out.write("\t"+params[3]) # reference | |
| 48 fh_out.write("\t"+params[4]) # alleleSeq | |
| 49 fh_out.write("\t"+params[2]) # dbsnpid / annotation id | |
| 50 | |
| 51 fh_out.write("\n") | |
| 52 i += 1 | |
| 53 # else: # indel... | |
| 54 | |
| 55 if(filename_out != "-"): | |
| 56 fh_out.close() | |
| 57 | |
| 58 if __name__ == "__main__": | |
| 59 parser = argparse.ArgumentParser() | |
| 60 | |
| 61 parser.add_argument("-i","--input", help="input file (VCF)") | |
| 62 parser.add_argument("-o","--output",help="output filename; '-' for stdout",default="-") | |
| 63 | |
| 64 args = parser.parse_args() | |
| 65 | |
| 66 convert_vcf_to_listVariants(args.input,args.output) |