def main():
args = parse_args()
dihedrals = read_dihedrals()
fasta = FASTA(args.fasta)
fasta.read()
(peptides, mhcSeq, mhcAllele) = totalNineMers(fasta)
#grooves = readGrooves(args.grooves, mhcSeq, peptides)
universalGrooves = universalGroove(args.grooves, mhcSeq, peptides)
intersectGrooves = IntersectionGroove(args.grooves, mhcSeq, peptides)
#for u in universalGrooves:
# print (u, universalGrooves[u])
#for u in intersectGrooves:
# print (intersectGrooves[u])
labels = read_rmsd_file(args.rms)
pdbids = read_datafile(args.t)
outputfilehandler = open(args.pdbids, 'w')
for pdbid in pdbids:
if pdbid in dihedrals:
if args.pep:
finalSeqCode = oneHotEncoding(peptides[pdbid])
finalLabelCode = dihedrals[pdbid]
if args.label == 'x':
print(', '.join(finalSeqCode))
outputfilehandler.write(pdbid + '\n')
elif args.label == 'y':
print(', '.join(finalLabelCode))
outputfilehandler.write(pdbid + '\n')
else:
finalSeqCode = oneHotEncoding(universalGrooves[pdbid] +
peptides[pdbid])
finalLabelCode = dihedrals[pdbid]
if args.label == 'x':
print(', '.join(finalSeqCode))
outputfilehandler.write(pdbid + '\n')
elif args.label == 'y':
print(', '.join(finalLabelCode))
outputfilehandler.write(pdbid + '\n')
outputfilehandler.close()
def read_fasta(args):
fasta = FASTA(args.fasta)
fasta.read()
headers = fasta.get_headers()
pep_chain = {}
pep_seq = {}
for header in headers:
fields = header.split('|')
pdbid = fields[0]
chainid = fields[1]
seq = fasta.get_sequence(header)
if len(seq) == 9:
pep_chain[pdbid] = chainid
pep_seq[pdbid] = seq
return (pep_chain, pep_seq)
def main():
args = parse_args()
fasta = FASTA(args.fasta)
fasta.read()
(peptides, mhcSeq, mhcAllele) = totalNineMers(fasta)
#grooves = readGrooves(args.grooves, mhcSeq, peptides)
universalGrooves = universalGroove(args.grooves, mhcSeq, peptides)
intersectGrooves = IntersectionGroove(args.grooves, mhcSeq, peptides)
labels = read_rmsd_file(args.rms)
pdbids = read_datafile(args.t)
aaindex = Aaindex()
#for result in aaindex.search('charge'):
# print(result)
record = aaindex.get('FASG890101')
#print (record.title)
index_data = record.index_data
#print (index_data)
charge = aaindex.get('KLEP840101')
charge_data = charge.index_data
#print (charge_data)
for l in labels:
(pdbid1, pdbid2) = l.split('_')
#if pdbid1 in pdbids and pdbid2 in pdbids:
if pdbid1 in pdbids or pdbid2 in pdbids:
if args.pep:
finalSeqCode, finalLabelCode = oneHotEncoding(peptides[pdbid1]+'|'+peptides[pdbid2], labels[l], index_data, charge_data)
if args.label == 'x':
print (', '.join(finalSeqCode))
elif args.label == 'y':
print (', '.join(finalLabelCode))
else:
finalSeqCode, finalLabelCode = oneHotEncoding(universalGrooves[pdbid1]+peptides[pdbid1]+'|'+universalGrooves[pdbid2]+peptides[pdbid2], labels[l], index_data, charge_data)
if args.label == 'x':
print (', '.join(finalSeqCode))
elif args.label == 'y':
print (', '.join(finalLabelCode))
def main():
args = parse_args()
fasta = FASTA(args.fasta)
fasta.read()
peptides = totalNineMers(fasta)
pdbids = peptides.keys()
testsetlen = int(args.percent * len(pdbids))
trainset = []
testset = []
for i in range(0, len(pdbids)):
r = random()
if len(testset) < testsetlen and r < 0.5:
testset.append(pdbids[i])
else:
trainset.append(pdbids[i])
write_to_file('train/90_10/train.txt', trainset)
write_to_file('test/90_10/test.txt', testset)
def main():
args = parse_args()
fasta = FASTA(args.fasta)
fasta.read()
peptides, alleles = totalNineMers(fasta)
pdbids = peptides.keys()
testsetlen = int(args.percent * len(pdbids))
trainset = []
testset = []
for p in pdbids:
r = random()
if len(testset) < testsetlen and r < 0.5 and alleles[p] == 'A0201':
testset.append(p)
else:
trainset.append(p)
write_to_file('train.txt', trainset)
write_to_file('test.txt', testset)
def main():
args = parse_args()
fasta = FASTA(args.fasta)
fasta.read()
(peptides, mhcSeq, mhcAllele) = totalNineMers(fasta)
#grooves = readGrooves(args.grooves, mhcSeq, peptides)
universalGrooves = universalGroove(args.grooves, mhcSeq, peptides)
intersectGrooves = IntersectionGroove(args.grooves, mhcSeq, peptides)
#for u in universalGrooves:
# print (u, universalGrooves[u])
#for u in intersectGrooves:
# print (intersectGrooves[u])
labels = read_rmsd_file(args.rms)
pdbids = read_datafile(args.t)
for l in labels:
(pdbid1, pdbid2) = l.split('_')
#if pdbid1 in pdbids and pdbid2 in pdbids:
if pdbid1 in pdbids or pdbid2 in pdbids:
if args.pep:
finalSeqCode, finalLabelCode = oneHotEncoding(
peptides[pdbid1] + '|' + peptides[pdbid2], labels[l])
if args.label == 'x':
print(', '.join(finalSeqCode))
elif args.label == 'y':
print(', '.join(finalLabelCode))
else:
finalSeqCode, finalLabelCode = oneHotEncoding(
universalGrooves[pdbid1] + peptides[pdbid1] + '|' +
universalGrooves[pdbid2] + peptides[pdbid2], labels[l])
if args.label == 'x':
print(', '.join(finalSeqCode))
elif args.label == 'y':
print(', '.join(finalLabelCode))
