def unique(self, options):
"""Unique command"""
self.logger.info('')
self.logger.info('*******************************************************************************')
self.logger.info('[RefineM - unique] Ensuring sequences are assigned to a single genome.')
self.logger.info('*******************************************************************************')
genome_files = self._genome_files(options.genome_nt_dir, options.genome_ext)
if not self._check_nuclotide_seqs(genome_files):
self.logger.warning('[Warning] All files must contain nucleotide sequences.')
sys.exit()
duplicates = genome_tk.unique(genome_files)
self.logger.info('')
if len(duplicates) == 0:
self.logger.info(' Pass: All sequences were identified exactly once.')
else:
self.logger.info(' Fail: One or more sequences were observed multiple times.')
genome_ids = sorted(duplicates.keys())
for i in xrange(0, len(genome_ids)):
genome_idA = genome_ids[i]
for j in xrange(i, len(genome_ids)):
genome_idB = genome_ids[j]
dup_seq_ids = duplicates[genome_idA][genome_idB]
if len(dup_seq_ids) == 0:
continue
self.logger.info('')
if genome_idA == genome_idB:
self.logger.info(' There are %d sequences present more than once in %s:' % (len(dup_seq_ids), genome_idA))
else:
self.logger.info(' There are %d sequences shared between %s and %s:' % (len(dup_seq_ids), genome_idA, genome_idB))
for seq_id in dup_seq_ids:
self.logger.info(' %s' % seq_id)
self.time_keeper.print_time_stamp()
def test_unique(self):
"""Verify GenomeTk.unique()"""
unique_test_data_dir = os.path.join(self.test_data_dir, 'unique')
genome_files = [
os.path.join(unique_test_data_dir, f)
for f in os.listdir(unique_test_data_dir)
]
duplicates = genome_tk.unique(genome_files)
gt = {
'genome2': {
'genome1': set(['c_dup'])
},
'genome1': {
'genome2': set(['c_dup']),
'genome1': ['b_dup']
}
}
assert_equals(duplicates, gt)
def unique(self, options):
"""Unique command"""
genome_files = self._genome_files(options.genome_nt_dir,
options.genome_ext)
if not self._check_nuclotide_seqs(genome_files):
self.logger.warning('All files must contain nucleotide sequences.')
sys.exit()
duplicates = genome_tk.unique(genome_files)
if len(duplicates) == 0:
self.reporter.info(
'Pass: All sequences were identified exactly once.')
else:
self.reporter.info(
'Fail: One or more sequences were observed multiple times.')
genome_ids = sorted(duplicates.keys())
for i in xrange(0, len(genome_ids)):
genome_idA = genome_ids[i]
for j in xrange(i, len(genome_ids)):
genome_idB = genome_ids[j]
dup_seq_ids = duplicates[genome_idA][genome_idB]
if len(dup_seq_ids) == 0:
continue
if genome_idA == genome_idB:
self.logger.info(
'There are %d sequences present more than once in %s:'
% (len(dup_seq_ids), genome_idA))
else:
self.logger.info(
'There are %d sequences shared between %s and %s:'
% (len(dup_seq_ids), genome_idA, genome_idB))
for seq_id in dup_seq_ids:
print ' %s' % seq_id