def test_parseFasta(self):
parsed_input = fasta.parseFasta(self.ex1, alphabet='AMINO_ACID')
for rec_id, rec_seq in parsed_input:
self._checkParsedRecord(rec_id, rec_seq)
self.assertEqual(len(parsed_input), 3)
parsed_input = fasta.parseFasta(self.ex2, alphabet='AMINO_ACID')
self.assertEqual(len(parsed_input), 3)
def test_parseFasta(self):
parsed_input = fasta.parseFasta(self.ex1, alphabet='AMINO_ACID')
for rec_id, rec_seq in parsed_input:
self._checkParsedRecord(rec_id, rec_seq)
self.assertEqual(len(parsed_input), 3)
parsed_input = fasta.parseFasta(self.ex2, alphabet='AMINO_ACID')
self.assertEqual(len(parsed_input), 3)
def getSeqFromFile(seq_fp):
_, ext = _ospath.splitext(seq_fp)
if ext in ('.gb', '.gbk', '.genbank'):
rec = gb_reader.parse(seq_fp)
return str(rec['seq'])
elif ext in ('.fa', '.fasta'):
# Just returns the first sequence in the file for now --
# this may be undesirable as a general behavior
return fasta.parseFasta(seq_fp)[0][1]
def getSeqFromFile(seq_fp):
_, ext = _ospath.splitext(seq_fp)
if ext in ('.gb', '.gbk', '.genbank'):
rec = gb_reader.parse(seq_fp)
return str(rec['seq'])
elif ext in ('.fa', '.fasta'):
# Just returns the first sequence in the file for now --
# this may be undesirable as a general behavior
return fasta.parseFasta(seq_fp)[0][1]
def test():
import sys
GENOME = os.path.join(LOCAL_DIR, 'mds42_recoded.fa')
REF_GENOME = os.path.join(LOCAL_DIR, 'mds42_full.fa')
try:
idx_lut = np.load(os.path.join(LOCAL_DIR, 'test_index_lut.npy'))
except IOError:
idx_lut = buildIndex(GENOME, REF_GENOME, fill_gaps=False,
smooth_edges=False)
fillGaps(idx_lut)
smoothEdges(idx_lut)
np.save(os.path.join(LOCAL_DIR, 'test_index_lut'), idx_lut)
genome = parseFasta(GENOME)[0][1]
ref_genome = parseFasta(REF_GENOME)[0][1]
return idx_lut, genome, ref_genome
def setUp(self):
recs = fasta.parseFasta(join(LOCAL_DIR, 'test_data/MG1655.fa'))
self.mg1655 = recs[0][1]
def setUp(self):
recs = fasta.parseFasta(join(LOCAL_DIR, 'test_data/MG1655.fa'))
self.mg1655 = recs[0][1]