def _get_blast_hits(self, blast_db, seqs):
""" blast each seq in seqs against blast_db and retain good hits
"""
max_evalue = self.Params['Max E value']
min_percent_identity = self.Params['Min percent identity']
if min_percent_identity < 1.0:
min_percent_identity *= 100.0
seq_ids = [s[0] for s in seqs]
result = {}
blast_result = blast_seqs(
seqs, Blastall, blast_db=blast_db,
params={'-p': 'blastn', '-n': 'T'},
add_seq_names=False)
if blast_result['StdOut']:
lines = [x for x in blast_result['StdOut']]
blast_result = BlastResult(lines)
else:
return {}.fromkeys(seq_ids, [])
for seq_id in seq_ids:
blast_result_id = seq_id.split()[0]
try:
result[seq_id] = [(e['SUBJECT ID'], float(e['E-VALUE']))
for e in blast_result[blast_result_id][0]
if (float(e['E-VALUE']) <= max_evalue and
float(e['% IDENTITY']) >= min_percent_identity)]
except KeyError:
result[seq_id] = []
return result
def _get_blast_hits(self, blast_db, seqs):
""" blast each seq in seqs against blast_db and retain good hits
"""
max_evalue = self.Params['Max E value']
min_percent_identity = self.Params['Min percent identity']
if min_percent_identity < 1.0:
min_percent_identity *= 100.0
seq_ids = [s[0] for s in seqs]
result = {}
blast_result = blast_seqs(
seqs, Blastall, blast_db=blast_db,
params={'-p': 'blastn', '-n': 'T'},
add_seq_names=False)
if blast_result['StdOut']:
lines = [x for x in blast_result['StdOut']]
blast_result = BlastResult(lines)
else:
return {}.fromkeys(seq_ids, [])
for seq_id in seq_ids:
blast_result_id = seq_id.split()[0]
try:
result[seq_id] = [(e['SUBJECT ID'], float(e['E-VALUE']))
for e in blast_result[blast_result_id][0]
if (float(e['E-VALUE']) <= max_evalue and
float(e['% IDENTITY']) >= min_percent_identity)]
except KeyError:
result[seq_id] = []
return result
def blast_genome(seqs,
blast_db,
e_value,
max_hits,
word_size,
working_dir,
blast_mat_root,
extra_params=[],
DEBUG=True):
"""Blast sequences against all genes in a genome
seqs -- input sequences as strings
blast_db -- path to blast database
e_value -- e_value (float)
max_hits -- maximum sequences detected by BLAST to show
word_size -- word size for initial BLAST screen.
blast_mat_root -- location of BLAST matrix files
extra_params -- additional paramters to pass to BLAST
DEBUG -- display verbose debugging outout
"""
# set up params to use with blastp or
params = {
# matrix
"-M": "BLOSUM62",
# max procs
"-a": "1",
# expectation
"-e": e_value,
# max seqs to show
"-b": max_hits,
# Word size
"-W": word_size,
# max one line descriptions
"-v": max_hits,
# tabular output
"-m": "9",
# program
"-p": "blastn"
}
params.update(extra_params)
output = blast_seqs(seqs,
Blastall,
blast_db=blast_db,
params=params,
WorkingDir=working_dir,
add_seq_names=False,
blast_mat_root=blast_mat_root)
raw_output = [x for x in output['StdOut']]
return raw_output
def blast_genome(seqs, blast_db, e_value, max_hits, word_size, working_dir,
blast_mat_root, extra_params=[], DEBUG=True):
"""Blast sequences against all genes in a genome
seqs -- input sequences as strings
blast_db -- path to blast database
e_value -- e_value (float)
max_hits -- maximum sequences detected by BLAST to show
word_size -- word size for initial BLAST screen.
blast_mat_root -- location of BLAST matrix files
extra_params -- additional paramters to pass to BLAST
DEBUG -- display verbose debugging outout
"""
# set up params to use with blastp or
params = {
# matrix
"-M": "BLOSUM62",
# max procs
"-a": "1",
# expectation
"-e": e_value,
# max seqs to show
"-b": max_hits,
# Word size
"-W": word_size,
# max one line descriptions
"-v": max_hits,
# tabular output
"-m": "9",
# program
"-p": "blastn"
}
params.update(extra_params)
output = blast_seqs(seqs,
Blastall,
blast_db=blast_db,
params=params,
WorkingDir=working_dir,
add_seq_names=False,
blast_mat_root=blast_mat_root)
raw_output = [x for x in output['StdOut']]
return raw_output
