def main():
# argument method
parser = argparse.ArgumentParser()
# positional argument
parser.add_argument('-d',
'--directory',
'--dir',
help='parent directory of the samples i.e. Sample_054',
required=True)
# optional argument
parser.add_argument(
'-f',
'--filter',
action='store_true',
help=
'use argument to keep the following columns: CHROM, POS, REF, ALT, genotype info. \n'
'Note: if option selection, the -d can either be the vcf.gz or the parent directory. '
'If vcf.gz, it will perform filtering on that file. Else, it will perform filtering on'
'all the files in the hierarchical directory.')
# optional argument
parser.add_argument(
'-m',
'--merge',
action='store_true',
help=
'use argument to merge all filtered.vcf.gz files in the parent directory'
)
# optional argument
parser.add_argument(
'-o',
'--output',
help='directory where to output the filtered or merged files')
# optional argument
parser.add_argument('-ht',
'--homozygous_test',
action='store_true',
help='use argument to collect homozygous statistics')
# optional argument
parser.add_argument(
'-s',
'--subset',
action='store_true',
help='use argument to subset the vcf file based on chromosomes')
# optional argument
parser.add_argument(
'-c',
'--chromosome',
help=
'use argument to select the chromosome number on which to subset on')
# optional argument
parser.add_argument(
'-n',
'--number_sites',
help='use argument to select the number of line on which to subset on',
type=int)
# optional argument
parser.add_argument('-p',
'--phase',
action='store_true',
help='use argument to select the phasing test')
parser.add_argument('-lc',
'--list_chromosomes',
action='store_true',
help='list all the chromosomes in a vcf.gz '
'file')
args = parser.parse_args()
working_directory, output_directory, chromosome, filter_merge = process_arguments(
c_directory=args.directory,
o_directory=args.output,
filter_flag=args.filter,
merge_flag=args.merge,
chrom=args.chromosome,
arg_parser=parser)
# create VCF object
vcf = VCF()
if args.list_chromosomes:
vcf.read_files(c_dir=working_directory, vcf_filtered_file=False)
vcf.list_chrom(output_dir=output_directory)
# filtering and merging have to read all the vcf files on the subdirectories of the families
elif filter_merge:
# read all the vcf files for that family
vcf.read_files(c_dir=working_directory)
# filter columns of the vcf files
if args.filter:
vcf.filter(output_dir=output_directory)
else:
vcf.merge(output_dir=output_directory)
# subset, homozygous or phasing tests have to read a vcf file in the parent directory
else:
# for the subset, the chromosome should not be given in the read_file function
if args.subset:
# chromosome if required if goal is to subset since the file will be subsetted on it
if not args.chromosome:
raise ValueError(
'Chromosome number must be provided in order to perform subset'
)
# read all the vcf files for that family
vcf.read_files(c_dir=working_directory, vcf_filtered_file=True)
vcf.subset(chrom=args.chromosome,
output_dir=output_directory,
n_sites=args.number_sites)
else:
# read all the vcf files for that family
vcf.read_files(c_dir=working_directory,
vcf_filtered_file=True,
chrom=chromosome)
if args.homozygous_test:
# collect homozygous statistics
vcf.tests(output_dir=output_directory,
chrom=chromosome,
homozygous_test=True)
if args.phase:
vcf.tmp_test(output_dir=output_directory, chrom=chromosome)
title_indel_exonicfunc = ['Sample','frameshift_deletion','frameshift_insertion','nonframeshift_deletion','nonframeshift_insertion','stoploss','stopgain','unknown']
indel_exonicfunc.write('\t'.join(title_indel_exonicfunc)+'\n')
for file in open(files, 'r'):
if file.startswith('#'):continue
file = file.strip()
sample_name = os.path.basename(file)
sample_name = sample_name.split('.')[0]
myVCF = VCF(file)
snp = myVCF.filter()
indel_file = file.replace('snp','indel')
myVCF = VCF(indel_file)
indel = myVCF.filter()
"""
##chr.xls
chr = myVCF.chr_stat(vcf)
chromosome.write(sample_name)
for i in [str(i) for i in range(1,23)]+['X','Y']:
try:
chromosome.write('\t'+str(chr[i]))
except:
chromosome.write('\t0')
chromosome.write('\n')
"""
##indel_exonicfunc.xls
title_indel_exonicfunc = [
'Sample', 'frameshift_deletion', 'frameshift_insertion',
'nonframeshift_deletion', 'nonframeshift_insertion', 'stoploss',
'stopgain', 'unknown'
]
indel_exonicfunc.write('\t'.join(title_indel_exonicfunc) + '\n')
for file in open(files, 'r'):
if file.startswith('#'): continue
file = file.strip()
sample_name = os.path.basename(file)
sample_name = sample_name.split('.')[0]
myVCF = VCF(file)
snp = myVCF.filter()
indel_file = file.replace('snp', 'indel')
myVCF = VCF(indel_file)
indel = myVCF.filter()
"""
##chr.xls
chr = myVCF.chr_stat(vcf)
chromosome.write(sample_name)
for i in [str(i) for i in range(1,23)]+['X','Y']:
try:
chromosome.write('\t'+str(chr[i]))
except:
chromosome.write('\t0')
chromosome.write('\n')
"""