def blast(query_file, db_file, output_file='BLASTResult.xml'):
cmd = nb(num_threads=cpu_count(),
query=query_file,
db=db_file,
task='blastn',
outfmt=5,
out=output_file)
stdout, stderr = cmd()
return output_file
def blast(query_file, database):
cmd = nb(num_threads=cpu_count(),
query=query_file,
db=database,
task='blastn-short',
evalue=1e-5,
outfmt=5,
out='out/BlastResult.xml')
stdout, stderr = cmd()
def validate(candidate_file, input_file, n_seqs, min_len, min_covrage,
max_mismatch):
# remove gap in old alignment file
no_gap = 'validate.fasta'
with open(no_gap, 'w') as new, open(input_file, 'r') as old:
for line in old:
if line.startswith('>'):
new.write(line)
else:
new.write(line.replace('-', ''))
# build blast db
candidate_fasta = 'primer_candidate.fasta'
SeqIO.convert(candidate_file, 'fastq', candidate_fasta, 'fasta')
run('makeblastdb -in {} -dbtype nucl'.format(no_gap), shell=True)
# blast
blast_result_file = 'BlastResult.xml'
cmd = nb(num_threads=cpu_count(),
query=candidate_fasta,
db=no_gap,
task='blastn',
evalue=1e-5,
max_hsps=1,
max_target_seqs=n_seqs,
outfmt=5,
out=blast_result_file)
stdout, stderr = cmd()
# parse
min_bitscore_raw = min_len - max_mismatch
blast_result = [['ID', 'Hits', 'Sum_Bitscore_raw'], ]
blast_result.append(['All', n_seqs, min_len])
for query in SearchIO.parse(blast_result_file, 'blast-xml'):
if len(query) == 0:
blast_result.append([query.id, 0, 0])
continue
sum_bitscore_raw = 0
good_hits = 0
start = 0
for hit in query:
hsp_bitscore_raw = hit[0].bitscore_raw
if hsp_bitscore_raw >= min_bitscore_raw:
sum_bitscore_raw += hsp_bitscore_raw
good_hits += 1
start += sum(hit[0].hit_range) / 2
blast_result.append([query.id, good_hits/n_seqs, sum_bitscore_raw,
start/n_seqs])
# validate
# validate_result = [['ID', 'Hits', 'Sum_Bitscore_raw', 'Seq'], ]
validate_result = list()
for record in blast_result[2:]:
if record[1] >= min_covrage:
validate_result.append(record)
validate_result.sort(key=lambda x: x[1], reverse=True)
return validate_result
def blast(query_file, database):
cmd = nb(
num_threads=cpu_count(),
query=query_file,
db=database,
task='blastn-short',
evalue=1e-5,
outfmt=5,
out='out/BlastResult.xml'
)
stdout, stderr = cmd()
def blast(option):
if option == '1':
query_file = './output/all.fasta'
else:
query_file = sys.argv[1]
cmd = nb(
# num_threads=8,
query=query_file,
db=sys.argv[2],
task='megablast',
evalue=0.001,
outfmt=5,
# xml format
out='BlastResult.xml')
stdout, stderr = cmd()
return
def blast(option):
if option == '1':
query_file = './output/all.fasta'
else:
query_file = sys.argv[1]
cmd = nb(
# num_threads=8,
query=query_file,
db=sys.argv[2],
task='megablast',
evalue=0.001,
outfmt=5,
# xml format
out='BlastResult.xml'
)
stdout, stderr = cmd()
return
def blast(ref_file, query_file):
"""
max_target_seqs was reported to having bug."""
# MAX_TARGET_SEQS = 2
db_file = os.path.join(args.out, ref_file)
# hide output
with open(os.path.join(args.out, 'log.txt'), 'w') as log:
run('makeblastdb -in {0} -out {1} -dbtype nucl'.format(
ref_file, db_file),
stdout=log,
shell=True)
result = os.path.join(args.out, 'BlastResult.xml')
cmd = nb(
num_threads=cpu_count(),
query=query_file,
db=db_file,
task='blastn',
evalue=args.evalue,
max_hsps=1,
# max_target_seqs=MAX_TARGET_SEQS,
outfmt=5,
out=result)
stdout, stderr = cmd()
return result