def test_extract_seqs_by_sample_id(self):
"""extract_seqs_by_sample_id: functions as expected """
seqs = [('Samp1_109','ACGG'),\
('Samp1_110','CCGG'),\
('samp1_109','GCGG'),\
('S2','AA'),\
('S3','CC'),\
('S4','GG'),\
('S44','TT'),\
('S4','TAAT')]
sample_ids = ['Samp1', 'S44']
expected = [('Samp1_109','ACGG'),\
('Samp1_110','CCGG'),\
('S44','TT')]
actual = list(extract_seqs_by_sample_id(seqs, sample_ids))
self.assertEqual(actual, expected)
#negated
expected_neg = [('samp1_109','GCGG'),\
('S2','AA'),\
('S3','CC'),\
('S4','GG'),\
('S4','TAAT')]
actual = list(extract_seqs_by_sample_id(seqs, sample_ids, negate=True))
self.assertEqual(actual, expected_neg)
# OK if user passes dict of sample ids
sample_ids = {'samp1': 25}
expected = [('samp1_109', 'GCGG')]
actual = list(extract_seqs_by_sample_id(seqs, sample_ids))
self.assertEqual(actual, expected)
def test_extract_seqs_by_sample_id(self):
"""extract_seqs_by_sample_id: functions as expected """
seqs = [('Samp1_109','ACGG'),\
('Samp1_110','CCGG'),\
('samp1_109','GCGG'),\
('S2','AA'),\
('S3','CC'),\
('S4','GG'),\
('S44','TT'),\
('S4','TAAT')]
sample_ids = ['Samp1','S44']
expected = [('Samp1_109','ACGG'),\
('Samp1_110','CCGG'),\
('S44','TT')]
actual = list(extract_seqs_by_sample_id(seqs,sample_ids))
self.assertEqual(actual,expected)
#negated
expected_neg = [('samp1_109','GCGG'),\
('S2','AA'),\
('S3','CC'),\
('S4','GG'),\
('S4','TAAT')]
actual = list(extract_seqs_by_sample_id(seqs,sample_ids,negate=True))
self.assertEqual(actual,expected_neg)
# OK if user passes dict of sample ids
sample_ids = {'samp1':25}
expected = [('samp1_109','GCGG')]
actual = list(extract_seqs_by_sample_id(seqs,sample_ids))
self.assertEqual(actual,expected)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
negate = opts.negate
sample_ids = opts.sample_ids
mapping_fp = opts.mapping_fp
input_fasta_fp = opts.input_fasta_fp
output_fasta_fp = opts.output_fasta_fp
if not mapping_fp:
sample_ids = sample_ids.split(',')
else:
map_data, map_header, map_comments = parse_mapping_file(mapping_fp)
sample_ids = get_sample_ids(
map_data,
map_header,
parse_metadata_state_descriptions(sample_ids))
if len(sample_ids) == 0:
raise ValueError(
"No samples match the search criteria: %s" %
valid_states)
if opts.verbose:
# This is useful when using the --valid_states feature so you can
# find out if a search query didn't work as you expected before a
# lot of time is spent
print "Extracting samples: %s" % ', '.join(sample_ids)
try:
seqs = parse_fasta(open(input_fasta_fp))
except IOError:
option_parser.error(
'Cannot open %s. Does it exist? Do you have read access?' %
input_fasta_fp)
exit(1)
try:
output_fasta_f = open(output_fasta_fp, 'w')
except IOError:
option_parser.error(
"Cannot open %s. Does path exist? Do you have write access?" %
output_fasta_fp)
exit(1)
for r in extract_seqs_by_sample_id(seqs, sample_ids, negate):
output_fasta_f.write('>%s\n%s\n' % r)
output_fasta_f.close()
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
negate = opts.negate
sample_ids = opts.sample_ids
mapping_fp = opts.mapping_fp
input_fasta_fp = opts.input_fasta_fp
output_fasta_fp = opts.output_fasta_fp
if not mapping_fp:
sample_ids = sample_ids.split(',')
else:
map_data, map_header, map_comments = parse_mapping_file(mapping_fp)
sample_ids = get_sample_ids(
map_data,
map_header,
parse_metadata_state_descriptions(sample_ids))
if len(sample_ids) == 0:
raise ValueError(
"No samples match the search criteria: %s" %
valid_states)
if opts.verbose:
# This is useful when using the --valid_states feature so you can
# find out if a search query didn't work as you expected before a
# lot of time is spent
print "Extracting samples: %s" % ', '.join(sample_ids)
try:
seqs = parse_fasta(open(input_fasta_fp))
except IOError:
option_parser.error(
'Cannot open %s. Does it exist? Do you have read access?' %
input_fasta_fp)
exit(1)
try:
output_fasta_f = open(output_fasta_fp, 'w')
except IOError:
option_parser.error(
"Cannot open %s. Does path exist? Do you have write access?" %
output_fasta_fp)
exit(1)
for r in extract_seqs_by_sample_id(seqs, sample_ids, negate):
output_fasta_f.write('>%s\n%s\n' % r)
output_fasta_f.close()
