def __main__():
if len(sys.argv) >= 4:
glimmerfile = open(sys.argv [1], "r")
sequence = open(sys.argv[2])
orf2seq = open(sys.argv [3], "w")
else:
print "Missing input values."
sys.exit()
fastafile = Bio.SeqIO.parse(sequence, "fasta")
sequences = {}
for entry in fastafile:
sequences[entry.description] = entry
for line in glimmerfile:
if line.startswith('>'):
print line[1:].strip()
entry = sequences[ line[1:].strip() ]
else:
orf_start = int(line[8:17])
orf_end = int(line[18:26])
orf_name = line[0:8]
if orf_start <= orf_end:
new_line = record(entry.seq[orf_start-1 : orf_end], id = orf_name, description = entry.description).format("fasta") + "\n"
else:
new_line = record(entry.seq[orf_end-1 : orf_start].reverse_complement(), id = orf_name, description = entry.description).format("fasta") + "\n"
orf2seq.write(new_line)
orf2seq.close()
glimmerfile.close()
def glimmer2sequence(sequence_path,
glimmer_path,
output_path,
to_protein=False,
translation_table=11):
fastafile = Bio.SeqIO.parse(open(sequence_path), "fasta")
glimmerfile = open(glimmer_path, "r")
orf2seq = open(output_path, "w")
sequences = {}
for entry in fastafile:
sequences[entry.description] = entry
for line in glimmerfile:
if line.startswith('>'):
entry = sequences[line[1:].strip()]
else:
columns = line.strip('\t').split()
try:
orf_start = int(columns[1])
orf_end = int(columns[2])
except:
sys.stderr.write(
"Error: Failed to convert %s or %s to an integer. Is the input really a glimmer prediction file?\n"
% (columns[1], columns[2]))
continue
orf_name = columns[0]
if orf_start <= orf_end:
sequence = entry.seq[orf_start - 1:orf_end]
if to_protein:
sequence = sequence.translate(to_stop=True,
table=translation_table)
new_line = record(
sequence, id=orf_name,
description=entry.description).format("fasta") + "\n"
else:
sequence = entry.seq[orf_end -
1:orf_start].reverse_complement()
if to_protein:
sequence = sequence.translate(to_stop=True,
table=translation_table)
new_line = record(
sequence, id=orf_name,
description=entry.description).format("fasta") + "\n"
orf2seq.write(new_line)
orf2seq.close()
glimmerfile.close()
def glimmer2sequence(sequence_path, glimmer_path, output_path, to_protein = False, translation_table = 11):
fastafile = Bio.SeqIO.parse(open(sequence_path), "fasta")
glimmerfile = open(glimmer_path, "r")
orf2seq = open(output_path, "w")
sequences = {}
for entry in fastafile:
sequences[entry.description] = entry
for line in glimmerfile:
if line.startswith('>'):
entry = sequences[ line[1:].strip() ]
else:
columns = line.strip('\t').split()
try:
orf_start = int(columns[1])
orf_end = int(columns[2])
except:
sys.stderr.write("Error: Failed to convert %s or %s to an integer. Is the input really a glimmer prediction file?\n" % (columns[1], columns[2]))
continue
orf_name = columns[0]
if orf_start <= orf_end:
sequence = entry.seq[orf_start-1 : orf_end]
if to_protein:
sequence = sequence.translate(to_stop=True, table = translation_table)
new_line = record(sequence, id = orf_name, description = entry.description).format("fasta") + "\n"
else:
sequence = entry.seq[orf_end-1 : orf_start].reverse_complement()
if to_protein:
sequence = sequence.translate(to_stop=True, table = translation_table)
new_line = record(sequence, id = orf_name, description = entry.description).format("fasta") + "\n"
orf2seq.write(new_line)
orf2seq.close()
glimmerfile.close()
