def main(Pt):
print (Pt)
filein = '/home/wzt/project/GeneFusion/Data2/{}/{}.mupexi'.format(Pt, Pt)
fileout = '/home/wzt/project/GeneFusion/Data2/{}/{}.filter.mupexi'.format(Pt, Pt)
with open(filein,'r') as fin,open(fileout,'w') as fout:
fout.write('HLA\tSample\tmismatch\t')
fout.write('MTpep\tMTpep_score\tMTpep_aff\tMTpep_rank\tMTpep_comb\t')
fout.write('WTpep\tWTpep_score\tWTpep_aff\tWTpep_rank\tWTpep_comb\t')
fout.write('Hydro_Model\tSelf_similar\tR\tA\n')
for line in fin:
if line.startswith('#') or line.startswith('HLA_allele'):
continue
lines = line.strip().split('\t')
if isfloat(lines[11]) <= 2 and isfloat(lines[26]) * isfloat(lines[16]) >= 1 and lines[25] == 'No':
hla = lines[0]
mtpep,mtpep_score, mtpep_aff, mtpep_rank = lines[7],lines[12],lines[10],lines[11]
wtpep,wtpep_score, wtpep_aff, wtpep_rank = lines[1], lines[6], lines[4], lines[5]
mtpep_tap, mtpep_cleavage, mtpep_comb = cal_netctlpan(hla, mtpep)
wtpep_tap, wtpep_cleavage, wtpep_comb = cal_netctlpan(hla, wtpep)
A = Neoantigen(mtpep, wtpep, mtpep_aff, wtpep_aff).getA()
R = getR(mtpep, iedb_seq)
H = getH(mtpep, mymodel)
self_similar = cal_similarity(mut_pep=mtpep, wild_pep=wtpep)
mismatch = lines[17]
out = '\t'.join((hla, Pt, str(mismatch), mtpep, mtpep_score, mtpep_aff, mtpep_rank, mtpep_comb,
wtpep, wtpep_score,wtpep_aff, wtpep_rank, wtpep_comb,str(H),str(self_similar),str(R),str(A)))
fout.write('{}\n'.format(out))
def parseMHC(SRR):
os.chdir('/home/wzt/project/GeneFusion/Data1/{}'.format(SRR))
fileout = 'fusion_score.tsv'
filein = '{}.netMHC.txt'.format(SRR)
if os.path.isfile(filein) and os.path.getsize(filein) > 0:
with open(fileout,'w') as fout,open(filein,'r') as fin:
fout.write('HLA\tSample\tmismatch\t')
fout.write('MTpep\tMTpep_score\tMTpep_aff\tMTpep_rank\tMTpep_comb\t')
fout.write('WTpep\tWTpep_score\tWTpep_aff\tWTpep_rank\tWTpep_comb\t')
fout.write('Hydro_Model\tSelf_similar\tR\tA\n')
for line in fin:
if re.search('=\s+WB',line) or re.search('=\s+SB',line):
lines = line.strip().split()
mtpep,mtpep_score, mtpep_aff, mtpep_rank = lines[2],lines[11], lines[12], lines[13]
wtpep,mismatch = getwildpep(mtpep)
hla = lines[1].replace('*','')
if int(mismatch) == 0:
continue
sample = SRR + '_' + lines[10]
wtpep_score, wtpep_aff, wtpep_rank = cal_netMHCpan(hla, wtpep)
mtpep_tap, mtpep_cleavage, mtpep_comb = cal_netctlpan(hla, mtpep)
wtpep_tap, wtpep_cleavage, wtpep_comb = cal_netctlpan(hla, wtpep)
A = Neoantigen(mtpep,wtpep,mtpep_aff,wtpep_aff).getA()
R = getR(mtpep,iedb_seq)
H = getH(mtpep, mymodel)
self_similar = cal_similarity(mut_pep=mtpep, wild_pep=wtpep)
out = '\t'.join((hla, sample, str(mismatch), mtpep, mtpep_score, mtpep_aff, mtpep_rank, mtpep_comb,
wtpep,wtpep_score,wtpep_aff,wtpep_rank,wtpep_comb,str(H),str(self_similar),str(R),str(A)))
out = out + '\n'
fout.write(out)
def parsernetMHCpan(SRR):
print('\n######## Running neoAntigen Scoring ############')
os.chdir('/home/wzt/project/GeneFusion/Cell_line/Data2/{}'.format(SRR))
filein = 'netMHC.txt'
fileout = '/tmp/{}NeoScore.txt'.format(SRR)
ref = ''
iedb_seq = getIEDBseq()
mymodel = getModel()
with open('/home/wzt/database/STAR_Fusion/GRCh38/ctat/ref_annot_fusion.pep','r') as fin:
for t,seq in SimpleFastaParser(fin):
ref = seq
break
with open(filein,'r') as fin,open(fileout,'w') as fout:
fout.write('HLA\tSample\tmismatch\t')
fout.write('MTpep\tMTpep_score\tMTpep_aff\tMTpep_rank\tMTpep_comb\t')
fout.write('WTpep\tWTpep_score\tWTpep_aff\tWTpep_rank\tWTpep_comb\t')
fout.write('Hydro_Model\tR\tScore1\tScore2\n')
for line in fin:
if re.search('=\s+WB',line) or re.search('=\s+SB',line):
lines = line.strip().split()
mtpep = lines[2]
if ref.find(mtpep) != -1 or len(mtpep) == 8:
continue
sample = lines[10]
mtpep, mtpep_score, mtpep_aff, mtpep_rank = lines[2], lines[11], lines[12], lines[13]
wtpep, mismatch = getWildpep(mtpep)
hla = lines[1].replace('*', '')
wtpep_score, wtpep_aff, wtpep_rank = cal_netMHCpan(hla, wtpep)
mtpep_tap, mtpep_cleavage, mtpep_comb = cal_netctlpan(hla, mtpep)
wtpep_tap, wtpep_cleavage, wtpep_comb = cal_netctlpan(hla, wtpep)
A = Neoantigen(mtpep, wtpep, mtpep_aff, wtpep_aff).getA()
R = getR(mtpep, iedb_seq)
H = getH(mtpep, mymodel)
Rm = cal(float(mtpep_rank))
Rn = cal(float(wtpep_rank))
RA = float(A) * float(R)
score1 = f1(Rm=Rm,Rn=Rn,H=float(H),RA=RA,mismatch=float(mismatch),comb=float(mtpep_comb))
if score1 < 0 :
score1 = 0
score2 = f2(Rm=Rm,Rn=Rn,mismatch=float(mismatch),comb=float(mtpep_comb))
if score2 < 0 :
score2 = 0
out = '\t'.join((hla, sample, str(mismatch), mtpep, mtpep_score, mtpep_aff, mtpep_rank, mtpep_comb,
wtpep, wtpep_score, wtpep_aff, wtpep_rank, wtpep_comb, str(H), str(RA)))
fout.write('{}\t{}\t{}\n'.format(out,str(score1),str(score2)))
filein = '/tmp/{}NeoScore.txt'.format(SRR)
fileout = 'NeoScore.txt'
if os.path.isfile(filein) and os.path.getsize(filein) > 0:
dat = pd.read_csv(filein,sep='\t',header=0)
dat.sort_values(by='Score2',ascending=False,inplace=True)
dat.to_csv(fileout,sep='\t',header=True,index=False)
print('\n######## Complete Successfuly ############')
def main(line):
lines = line.strip().split('\t')
index = lines[-1]
hla = lines[0].replace('*', '')
sample = lines[2] + '_' + lines[7]
mtpep = lines[1]
mtpep_score, mtpep_aff, mtpep_rank = lines[3], lines[4], lines[5]
wtpep = getwildpep(mtpep)
wtpep_score, wtpep_aff, wtpep_rank = cal_netMHCpan(hla, wtpep, index)
mtpep_tap, mtpep_cleavage, mtpep_comb = cal_netctlpan(hla, mtpep, index)
wtpep_tap, wtpep_cleavage, wtpep_comb = cal_netctlpan(hla, wtpep, index)
A = Neoantigen(mtpep, wtpep, mtpep_aff, wtpep_aff).getA()
R = getR(mtpep, iedb_seq)
H = getH(mtpep, mymodel)
self_similar = cal_similarity(mut_pep=mtpep, wild_pep=wtpep)
mismatch = cal_mismatch(mtpep, wtpep)
out = '\t'.join(
(hla, sample, str(mismatch), mtpep, mtpep_score, mtpep_aff, mtpep_rank,
mtpep_comb, wtpep, wtpep_score, wtpep_aff, wtpep_rank, wtpep_comb,
str(H), str(self_similar), str(R), str(A)))
out = out + '\n'
return out