def reverse(master_file, organism):
"""
Reverse blast a fasta file of multiple sequences against the database
of an organism.
"""
# grab just the name
filename = os.path.splitext(master_file)[0]
fastas = split_fasta(master_file)
print("Total number of sequences before blasting: " + str(len(fastas)))
# Run individual blasts
processes = [query(f + ".fasta", f +"_blast.txt", entrez_query=organism) for f in fastas]
good_fastas = []
bad_fastas = []
for f in fastas:
found = organism_in_blast(organism, f+ "_blast.txt")
if found:
good_fastas.append(f)
else:
bad_fastas.append(f)
g = open(filename + "_reversed.fasta", 'w')
for fasta in good_fastas:
f = open(fasta + ".fasta", "r")
g.write(f.read())
f.close()
g.close()
print("Final number of sequences after blasting: " + str(len(good_fastas)))
for f in bad_fastas:
os.remove(f + ".fasta")
os.remove(f + "_blast.txt")
print("Done!")
def seeds(fasta, as_homologset=True, rm_blast=False, **kwargs):
""" Blast a set of seed sequences.
Arguments:
---------
fasta : str
filename for fasta containing seed sequences.
as_homologset: bool [default=true]
Convert blast results to homolog set.
kwargs are passed to blasting method.
"""
# grab just the name
filename = os.path.splitext(fasta)[0]
fastas = split_fasta(fasta)
print("Total number of sequences before blasting: " + str(len(fastas)))
# Make a directory for storing the blast results.
cwd = os.getcwd()
blastpath = os.path.join(cwd, "blast")
os.mkdir(blastpath)
# Run individual blasts
outnames = []
for f in fastas:
# Make filenames
iname = f + ".fasta"
oname = os.path.join(blastpath, f + "_blast.txt")
# Send query to NCBI
process = query(iname, oname, kwargs)
outnames.append(oname)
# If homolog_set should be made, return homolog_set
if as_homologset:
# Convert to homologset
homologset = to_homologset(outnames, tag_list=DEFAULTS)
return homologset
def seeds(fasta, as_homologset=True, rm_blast=False, **kwargs):
""" Blast a set of seed sequences.
Arguments:
---------
fasta : str
filename for fasta containing seed sequences.
as_homologset: bool [default=true]
Convert blast results to homolog set.
kwargs are passed to blasting method.
"""
# grab just the name
filename = os.path.splitext(fasta)[0]
fastas = split_fasta(fasta)
print("Total number of sequences before blasting: " + str(len(fastas)))
# Make a directory for storing the blast results.
cwd = os.getcwd()
blastpath = os.path.join(cwd, "blast")
os.mkdir(blastpath)
# Run individual blasts
outnames = []
for f in fastas:
# Make filenames
iname = f+".fasta"
oname = os.path.join(blastpath, f+"_blast.txt")
# Send query to NCBI
process = query(iname, oname, kwargs)
outnames.append(oname)
# If homolog_set should be made, return homolog_set
if as_homologset:
# Convert to homologset
homologset = to_homologset(outnames, tag_list=DEFAULTS)
return homologset
def reverse(master_file, organism):
"""
Reverse blast a fasta file of multiple sequences against the database
of an organism.
"""
# grab just the name
filename = os.path.splitext(master_file)[0]
fastas = split_fasta(master_file)
print("Total number of sequences before blasting: " + str(len(fastas)))
# Run individual blasts
processes = [
query(f + ".fasta", f + "_blast.txt", entrez_query=organism)
for f in fastas
]
good_fastas = []
bad_fastas = []
for f in fastas:
found = organism_in_blast(organism, f + "_blast.txt")
if found:
good_fastas.append(f)
else:
bad_fastas.append(f)
g = open(filename + "_reversed.fasta", 'w')
for fasta in good_fastas:
f = open(fasta + ".fasta", "r")
g.write(f.read())
f.close()
g.close()
print("Final number of sequences after blasting: " + str(len(good_fastas)))
for f in bad_fastas:
os.remove(f + ".fasta")
os.remove(f + "_blast.txt")
print("Done!")
