def test_parse(self):
input_fasta = StringIO("""\
>foo
AAAAAAAAAAAAAAAAAAA
>bar
GGGGGGGGGGGGGGGGGGG
""")
sequences = snp_sites_extensions.parse_fasta(input_fasta)
self.assertEqual(sequences.next(), ('foo', 'AAAAAAAAAAAAAAAAAAA'))
self.assertEqual(sequences.next(), ('bar', 'GGGGGGGGGGGGGGGGGGG'))
def test_parse(self):
input_fasta = StringIO("""\
>foo
AAAAAAAAAAAAAAAAAAA
>bar
GGGGGGGGGGGGGGGGGGG
""")
sequences = snp_sites_extensions.parse_fasta(input_fasta)
self.assertEqual(sequences.next(), ('foo', 'AAAAAAAAAAAAAAAAAAA'))
self.assertEqual(sequences.next(), ('bar', 'GGGGGGGGGGGGGGGGGGG'))
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
""" % reference_length)
header_row = ["#CHROM", "POS", "ID", "REF", "ALT", "QUAL", "FILTER", "INFO", "FORMAT"]
header_row += sequence_names
write_row(header_row, output_file)
BUFFER_SIZE = 10*1024*1024
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('input', type=argparse.FileType('r', BUFFER_SIZE))
parser.add_argument('output', type=argparse.FileType('w'),
default=open('random.short.fa.vcf', 'w'))
args = parser.parse_args()
sequences = snp_sites_extensions.parse_fasta(args.input)
ref_name,ref_seq = sequences.next()
snps = {}
sequence_names = []
sequence_names.append(ref_name)
for seq_name,seq_seq in sequences:
snp_sites_extensions.update_snps(sequence_names, snps, bytearray(ref_seq),
seq_name, bytearray(seq_seq))
snps = OrderedDict([(posn, snps[posn]) for posn in sorted(snps.keys())])
write_header(sequence_names, len(ref_seq), args.output)
for row_idx, (posn, snp_in_posn) in enumerate(snps.items()):
ref_base = ref_seq[posn]
]
header_row += sequence_names
write_row(header_row, output_file)
BUFFER_SIZE = 10 * 1024 * 1024
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('input', type=argparse.FileType('r', BUFFER_SIZE))
parser.add_argument('output',
type=argparse.FileType('w'),
default=open('random.short.fa.vcf', 'w'))
args = parser.parse_args()
sequences = snp_sites_extensions.parse_fasta(args.input)
ref_name, ref_seq = sequences.next()
snps = {}
sequence_names = []
sequence_names.append(ref_name)
for seq_name, seq_seq in sequences:
snp_sites_extensions.update_snps(sequence_names, snps,
bytearray(ref_seq), seq_name,
bytearray(seq_seq))
snps = OrderedDict([(posn, snps[posn]) for posn in sorted(snps.keys())])
write_header(sequence_names, len(ref_seq), args.output)
for row_idx, (posn, snp_in_posn) in enumerate(snps.items()):