def test_blast_record_set(self):
# prepare database
seqfile_ops.write_fasta(self.db_file, self.db_records)
db_records_list = seqfile_ops.load_multifasta(self.db_file)
index = 0
for record in db_records_list:
self.assertEqual(record.id,self.db_records[index].id)
self.assertEqual(str(record.seq),str(self.db_records[index].seq))
index +=1
# make database
self.dbfile_path, db_report = blasting.make_blastDB(self.temp_dir,
self.db_name,
self.db_file,
'nucl')
self.assertIs(db_report['status'], 0)
self.assertEquals(db_report['message'], 'database exists')
# run local blast batch (with multiple queries)
matches_multi = blasting.blast_record_set(self.dbfile_path,
self.multi_records,
self.prefs)
self.assertIs(len(matches_multi), 3)
index = 0
for record in self.multi_records:
self.assertEqual(matches_multi[record.id][0]['contig_id'],
self.multi_records[index].id)
self.assertEqual(matches_multi[record
.id][0]['details']['match_p100'], 100)
index +=1
def test_local_blastn(self):
# prepare query
seqfile_ops.write_fasta(self.single_q_file, self.single_record)
query_record = seqfile_ops.load_fasta(self.single_q_file)
self.assertEqual(query_record.id,self.record_1.id)
self.assertEqual(str(query_record.seq),str(self.record_1.seq))
# prepare database
seqfile_ops.write_fasta(self.db_file, self.db_records)
records_list = seqfile_ops.load_multifasta(self.db_file)
index = 0
for record in records_list:
self.assertEqual(record.id,self.db_records[index].id)
self.assertEqual(str(record.seq),str(self.db_records[index].seq))
index +=1
# make database
self.dbfile_path, db_report = blasting.make_blastDB(self.temp_dir,
self.db_name,
self.db_file,
'nucl')
self.assertIs(db_report['status'], 0)
self.assertEquals(db_report['message'], 'database exists')
# run local blast with single query
self.status = blasting.local_blastn(self.single_q_file,
self.single_out_file,
self.dbfile_path,
self.prefs)
self.assertEquals(self.status['output'], '')
self.assertIsNone(self.status['error'])
# parse blast output
matches_single = blasting.parse_blast_out6(self.single_out_file,
self.prefs)
self.assertIs(len(matches_single), 1)
self.assertEqual(matches_single[0]['contig_id'],
self.single_record.id)
self.assertEqual(matches_single[0]['details']['match_p100'], 100)
def test_write_and_load_multifasta(self):
count = seqfile_ops.write_fasta(self.fas_filename,
self.three_records)
self.assertIs(count, 3)
fas_records = seqfile_ops.load_multifasta(self.fas_filename)
for index in range (0,2):
self.assertEqual(fas_records[index].id,
self.three_records[index].id)
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