def predict_binding(df, predictor='netmhcpan', alleles=[],
verbose=False, cpus=1, cutoff=.95, cutoff_method='default'):
"""
Predict binding scores for mutated and wt peptides (if present) from supplied variants.
Args:
df: pandas dataframe with peptide sequences, requires at least 2 columns
'peptide' - the mutant peptide
'wt' - a corresponding wild type peptide
this data could be generated from get_mutant_sequences or from an external program
predictor: mhc binding prediction method
alleles: list of alleles
Returns:
dataframe with mutant and wt binding scores for all alleles
"""
P = base.get_predictor(predictor, scoring='ligand')
print (P)
print ('predicting mhc binding for %s peptides with %s' %(len(df), P.name))
peps = list(df.peptide)
res = P.predict_peptides(peps, alleles=alleles, cpus=cpus,
cutoff=cutoff, cutoff_method=cutoff_method, drop_columns=True)
if res is None:
print ('no binding predictions!')
return
#predict closest matching peptide affinity
if verbose == True:
print ('predicting wt peptides')
wtpeps = list(df.closest)
#print wild type peptides
b_wt = P.predict_peptides(wtpeps, alleles=alleles, cpus=cpus,
cutoff=cutoff, cutoff_method=cutoff_method, drop_columns=True)
#combine mutant and matching binding predictions
res = combine_wt_scores(res, b_wt, P.scorekey)
res = res.drop(['pos','name'],1)
#combine binding results with main dataframe
res = df.merge(res, on='peptide')
res['binding_diff'] = res[P.scorekey]/res.matched_score
#anchor position mutated in any 9-mers
res['anchor'] = res.apply(anchor_mutated, 1)
#hydrophobicity and net charge
res = analysis.peptide_properties(res, 'peptide')
res['length'] = res.peptide.str.len()
#merge promiscuity measure into results
#if len(pb) > 0:
# res = res.merge(pb[['peptide','alleles']], on='peptide',how='left')
#else:
# res['alleles'] = 0
#rename some columns
res = res.rename(columns={'rank':'binding_rank','alleles':'promiscuity'})
res = res.sort_values('binding_rank', ascending=True)
return res
def analysis(self):
"""Do analysis of prediction results."""
preds = self.preds
cutoffs = self.cutoffs
if len(cutoffs) < len(preds) :
cutoffs = [cutoffs[0] for p in preds]
cutoff_method = self.cutoff_method
i=0
prom_binders = {}
print ('analysing results..')
for P in self.preds:
p = P.name
cutoff = cutoffs[i]
n = self.n
print (P.path)
if P.data is not None:
b = P.get_binders(cutoff=cutoff, cutoff_method=cutoff_method)
elif P.path is not None:
b = P.get_binders(path=P.path, cutoff=cutoff, cutoff_method=cutoff_method)
else:
print ('empty results?')
continue
if b is None:
continue
print ('%s: %s binders found' %(P, len(b)))
if len(b) == 0:
print ('no binders found, check your cutoff value')
return
pb = P.promiscuous_binders(binders=b, n=n, cutoff=cutoff, cutoff_method=cutoff_method)
print ('found %s promiscuous binders at cutoff=%s, n=%s' %(len(pb),cutoff,n))
pb.to_csv(os.path.join(self.path,'final_%s_%s.csv' %(p,n)), float_format='%g')
prom_binders[p] = pb
if len(pb)>0:
print ('top promiscuous binders:')
print (pb[:10])
else:
continue
if self.sequences is not None:
x = analysis.get_nmer(pb, self.sequences, how='split', length=20)
x = analysis.peptide_properties(x, 'n-mer')
x.to_csv(os.path.join(self.path,'final_%s_%s.csv' %(p,n)), float_format='%g')
#do further analysis if using protein sequences
cl = analysis.find_clusters(pb)
if len(cl) > 0:
#make peptide lists
cl = analysis.get_nmer(cl, self.sequences, how='split', length=20)
cl = analysis.peptide_properties(cl, 'n-mer')
cl.to_csv(os.path.join(self.path,'clusters_%s.csv' %p))
#make summary table
summary = self.get_summary(P, pb, self.sequences, clusters=cl)
summary.to_csv(os.path.join(self.path,'summary_%s.csv' %p))
print ('-----------------------------')
i+=1
if len(prom_binders) > 1:
print ('finding combined list of binders')
comb = self.combine(prom_binders)
comb.to_csv(os.path.join(self.path,'combined.csv'), float_format='%g')
return
def predict_variants(df,
predictor='tepitope',
alleles=[],
verbose=False,
cpus=1,
cutoff=.95,
cutoff_method='default'):
"""
Predict binding scores for mutated and wt peptides (if present) from supplied variants.
Args:
df: pandas dataframe with peptide sequences, requires at least 2 columns
'peptide' - the mutant peptide
'wt' - a corresponding wild type peptide
this data could be generated from get_mutant_sequences or from an external source
predictor: mhc binding prediction method
alleles: list of alleles
Returns:
dataframe with mutant and wt binding scores for all alleles plus other score metrics
"""
#find matches to self proteome, adds penalty score column to df
#we should only blast non-duplicates....
if verbose == True:
print('finding matches to self proteome')
df = self_matches(df, cpus=cpus)
if verbose == True:
print('finding matches to viral proteomes')
df = virus_matches(df, cpus=cpus)
#get similarity scores for wt and closest match to proteome
df['wt_similarity'] = df.apply(wt_similarity, 1)
df['self_similarity'] = df.apply(self_similarity, 1)
df['virus_similarity'] = df.apply(virus_similarity, 1)
#get closest peptide in another column, either wt or nearest self
df['closest'] = df.apply(get_closest_match, 1)
P = base.get_predictor(predictor)
if verbose == True:
print(P)
print('predicting mhc binding for %s peptides with %s' %
(len(df), P.name))
peps = list(df.peptide)
res = P.predict_peptides(peps,
alleles=alleles,
cpus=cpus,
cutoff=cutoff,
cutoff_method=cutoff_method,
drop_columns=True)
pb = P.promiscuous_binders(n=1, cutoff=.95)
if res is None:
print('no binding predictions!')
return
#predict closest matching peptide affinity
if verbose == True:
print('predicting wt peptides')
wtpeps = list(df.closest)
#print wild type peptides
b_wt = P.predict_peptides(wtpeps,
alleles=alleles,
cpus=cpus,
cutoff=cutoff,
cutoff_method=cutoff_method,
drop_columns=True)
#combine mutant and matching binding predictions
res = combine_wt_scores(res, b_wt, P.scorekey)
res = res.drop(['pos', 'name'], 1)
#combine binding results with main dataframe
res = df.merge(res, on='peptide')
res['binding_diff'] = res[P.scorekey] / res.matched_score
#hydrophobicity and net charge
res = analysis.peptide_properties(res, 'peptide')
#print(res)
#exclude exact matches to self
print('%s peptides with exact matches to self' %
len(res[res.self_mismatches == 0]))
#merge promiscuity measure into results
if len(pb) > 0:
res = res.merge(pb[['peptide', 'alleles']], on='peptide', how='left')
else:
print('no promiscuous binders')
res['alleles'] = 0
#rename some columns
res = res.rename(columns={
'rank': 'binding_rank',
'alleles': 'promiscuity'
})
return res