def run_tblastn(db_path, q_file, file_location):
command = [
"tblastn", "-query", q_file, "-db", db_path, "-outfmt",
"""7 qacc sacc evalue qstart qend sstart send qlen sframe""",
"-evalue", "1e-1", "-out", file_location
]
run_cmd(command=command, wait=True)
return read_blast_output(file_location, db_path)
def make_blast_db(genome, temp_dir):
name = genome.split("/")[-1]
out_dir = os.path.join(temp_dir, name)
if os.path.exists(out_dir + ".nhr"):
print("\n\t[-] BLAST db already exists:\t{}\n".format(
os.path.join(temp_dir, name)))
return out_dir
command = "makeblastdb -in " + genome + " -dbtype nucl -parse_seqids -out " + out_dir
run_cmd(command=command, wait=True)
return out_dir
def parse_blastdb(db_path, contig, start, end):
region = str(start) + "-" + str(end)
command = "blastdbcmd -db " + db_path + " -dbtype nucl -entry " + contig + " -range " + region
results = []
for line in run_cmd(command=command, wait=False):
line = line.strip("\n")
if not line.startswith(">"):
results.append(line)
return "".join(results)
def get_exonerate_object(output_path, command):
line_count = 0
with open(output_path, "w") as ex:
for line in run_cmd(command=command, wait=False):
ex.write(line)
line_count += 1
if line_count < 10:
return None
else:
return ExonerateObject(output_path)
def msa_operations(command):
read_flag = 0
seq, msa_list = [], []
for line in run_cmd(command=command, wait=False):
if read_flag == 0:
if line.startswith(">"):
read_flag = 1
if read_flag == 1:
if line.startswith(">"):
if len(msa_list) > 0:
msa_list.append("".join(seq))
header = line.rstrip("\n").split()[0]
msa_list.append(header)
seq = []
else:
seq.append(line.rstrip("\n"))
msa_list.append("".join(seq))
return msa_list
def many_hmm_scores(hmm_file, query_file, test_this_function=None):
if test_this_function is None:
command = ["hmmsearch", "--noali", hmm_file, query_file]
else:
command = test_this_function
read_count = 0
score_list = []
for line in run_cmd(command=command, wait=False):
if "E-value" in line or read_count == 1:
read_count += 1
elif read_count == 2:
line = line.strip("\n").split() # line[8] is protein name
if len(line) > 0:
try:
score_list.append(float(line[1]))
except ValueError:
print("VALUE ERROR", line)
return score_list
else:
return score_list
def grap_output(protein_id, orthologous_file):
command = ["grep", """{}""".format(protein_id), orthologous_file]
for line in run_cmd(command=command, wait=False):
group = line.strip().split(":")[0]
return group