def load_dbsnp():
dbsnp_file = open(settings.INTERMEDIATE_FILE_DIR + 'dbsnp.tsv', 'w')
for i, variant in enumerate(vcf_stuff.iterate_vcf(open(settings.DBSNP_VCF_FILE))):
if not i % 100000:
print i
fields = [
str(variant.xpos),
variant.ref,
variant.alt,
variant.vcf_id,
]
dbsnp_file.write('\t'.join(fields)+'\n')
dbsnp_file.close()
import sys
from xbrowse.parsers.vcf_stuff import iterate_vcf
from xbrowse.utils import get_aaf, compressed_file
if __name__ == '__main__':
vcf_file = compressed_file(sys.argv[1])
for variant in iterate_vcf(vcf_file, genotypes=True):
print '\t'.join([
str(variant.xpos),
variant.ref,
variant.alt,
str(get_aaf(variant)),
])
import sys
from xbrowse.parsers.vcf_stuff import iterate_vcf
from xbrowse.utils import get_aaf, compressed_file
if __name__ == '__main__':
vcf_file = compressed_file(sys.argv[1])
for variant in iterate_vcf(vcf_file, genotypes=True):
print '\t'.join([
str(variant.xpos),
variant.ref,
variant.alt,
str(get_aaf(variant)),
])
import gzip
import argparse
from xbrowse.parsers import vcf_stuff
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Create a CSV from the ClinVar VCF file that can go into a pandas dataframe')
parser.add_argument('vcf')
args = parser.parse_args()
for variant in vcf_stuff.iterate_vcf(gzip.open(args.vcf)):
fields = [
str(variant.xpos),
variant.ref,
variant.alt
]
print '\t'.join(fields)