def test_chop_maxsize_divisor(self):
pair_list = sequence_ops.coord_chop(self.length, self.size, "maxsize_divisor")
first_pair_len = pair_list[0][1] - pair_list[0][0]
last_pair_len = pair_list[-1][1] - pair_list[-1][0]
self.assertGreaterEqual(len(pair_list), self.length / self.size)
self.assertLessEqual(first_pair_len, self.size)
self.assertLessEqual(last_pair_len, self.size)
def test_chop_exactsize(self):
pair_list = sequence_ops.coord_chop(self.length, self.size, "exact_size")
first_pair_len = pair_list[0][1] - pair_list[0][0]
last_pair_len = pair_list[-1][1] - pair_list[-1][0]
self.assertGreaterEqual(len(pair_list), self.length / self.size)
self.assertEquals(first_pair_len, self.size)
self.assertLessEqual(last_pair_len, self.size)
self.assertGreaterEqual(first_pair_len, last_pair_len)
def seq_subset_load(infile, subset_mode, subset_args):
"""Load a subset of sequence segments from a sequence file."""
from analysis.sequence_ops import feat_collect, feature_coords, \
coord_chop, get_seq_subset_by_coords
from analysis.seqfile_ops import load_multifasta, surefmt_load, \
write_fasta
from analysis.text_manipulation import adaptive_list_load
if subset_mode is 'flatfile':
# in this case the sequence file MUST be multifasta
try: subset = load_multifasta(infile)
except: raise
else:
print "set of", len(subset), "sequence segments"
subset_file = infile
else:
# load the query single sequence file (convert format if necessary)
try: seq_record = surefmt_load(infile, 'fasta', 'generic_dna')
except: raise
else: print "query sequence loaded from", infile
# load or generate coordinate pairs for target segments
if subset_mode is 'coordinates':
try:
coords_file = subset_args['file']
header = subset_args['header']
columns = subset_args['columns']
coords_list = adaptive_list_load(coords_file, header, columns)
except: raise
else: print len(coords_list), "segments loaded from", infile
elif subset_mode is 'features':
try:
feat_mode = subset_args
features = feat_collect(infile, feat_mode)
coords_list = feature_coords(features)
print coords_list
except: raise
else: print len(coords_list),"features loaded from", infile
elif subset_mode is 'size':
try:
size = subset_args['size']
chop_mode = subset_args['chop_mode']
coords_list = coord_chop(len(seq_record.seq), size, chop_mode)
except: raise
else: print len(coords_list), "segments generated to fit", size
else:
print "ERROR: A mode MUST be specified."
coords_list = None
# collect subset of sequence segments using resulting coords_list
try: subset = get_seq_subset_by_coords(seq_record, coords_list)
except: raise
else: print "subset of", len(subset), "sequence segments"
# save subset to multifasta file for later use or reference
subset_file = seq_record.id+'_subset.fas'
try: write_fasta(subset_file, subset)
except: raise
else: print "subset written to fasta file", subset_file
return subset, subset_file
def test_chop_none(self):
pair_list = sequence_ops.coord_chop(self.length, None, None)
first_pair_len = pair_list[0][1] - pair_list[0][0]
self.assertIs(len(pair_list), 1)
self.assertEqual(first_pair_len, self.length)
def test_chop_count_divisor(self):
pair_list = sequence_ops.coord_chop(self.length, self.count, "count_divisor")
first_pair_len = pair_list[0][1] - pair_list[0][0]
last_pair_len = pair_list[-1][1] - pair_list[-1][0]
self.assertLessEqual(abs(len(pair_list) - self.count), 1)
self.assertGreaterEqual(first_pair_len, last_pair_len)
