def predict(self, peptides, alleles=None, binary=False, **kwargs):
# test whether one peptide or a list
if not isinstance(peptides, list):
peptides = [peptides]
# if no alleles are specified do predictions for all supported alleles
if alleles is None:
alleles = self.supportedAlleles
else:
# filter for supported alleles
alleles = filter(lambda a: a in self.supportedAlleles, alleles)
# fetch peptides as strings
peptides = [str(peptide) for peptide in peptides]
# write peptides temporarily, new line separated
tmp_input_file = tempfile.NamedTemporaryFile().name
with open(tmp_input_file, 'wb') as file:
for peptide in peptides:
file.write(peptide + "\n")
alleles = self.convert_alleles(alleles)
result = {}
# predict binding affinities
for a in alleles:
allele_repr = self.revert_allele_repr(a)
result[allele_repr] = {}
tmp_output_file = tempfile.NamedTemporaryFile().name
mhcnuggets_predict(class_='I',
peptides_path=tmp_input_file,
mhc=a,
output=tmp_output_file + a)
# read predicted binding affinities back
with open(tmp_output_file + a, 'rb') as csvfile:
reader = csv.reader(csvfile, delimiter=' ', quotechar='|')
# skip header
reader.next()
# assign binding affinities
for row in reader:
content = row[0].split(',')
peptide = content[0]
binding_affinity = content[1]
if binary:
if binding_affinity <= 500:
result[allele_repr][peptide] = 1.0
else:
result[allele_repr][peptide] = 0.0
else:
result[allele_repr][peptide] = binding_affinity
# create EpitopePredictionResult object. This is a multi-indexed DataFrame
# with Peptide and Method as multi-index and alleles as columns
df_result = EpitopePredictionResult.from_dict(result)
df_result.index = pandas.MultiIndex.from_tuples(
[tuple((i, self.name)) for i in df_result.index],
names=['Seq', 'Method'])
return df_result
def predict(self, peptides, alleles=None, binary=False, **kwargs):
# test whether one peptide or a list
if not isinstance(peptides, list):
peptides = [peptides]
# if no alleles are specified do predictions for all supported alleles
if alleles is None:
alleles = self.supportedAlleles
else:
# filter for supported alleles
alleles = filter(lambda a: a in self.supportedAlleles, alleles)
alleles = self.convert_alleles(alleles)
# prepare results dictionary
result = defaultdict(defaultdict)
# keep input peptide objects for later use
peptide_objects = {}
for peptide in peptides:
peptide_objects[str(peptide)] = peptide
# group peptides by length
pep_groups = peptide_objects.keys()
pep_groups.sort(key=len)
for length, peps in itertools.groupby(pep_groups, key=len):
if length not in self.supportedLength:
logging.warn(
"Peptide length must be at least %i or at most %i for %s but is %i"
% (min(self.supportedLength), max(
self.supportedLength), self.name, length))
continue
peps = list(peps)
# write peptides temporarily, new line separated
tmp_input_file = tempfile.NamedTemporaryFile().name
with open(tmp_input_file, 'wb') as file:
for peptide in peps:
file.write(peptide + "\n")
# predict bindings
for a in alleles:
allele_repr = self.revert_allele_repr(a)
# workaround for mhcnuggets file i/o buffer bug
mhcnuggets_output = cStringIO.StringIO()
with capture_stdout(mhcnuggets_output):
mhcnuggets_predict(class_='II',
peptides_path=tmp_input_file,
mhc=a)
# read predicted binding affinities back
mhcnuggets_output.seek(0)
reader = csv.reader(mhcnuggets_output,
delimiter=' ',
quotechar='|')
# skip log statements from mhcnuggets and header
for row in reader:
if row[0] == 'peptide,ic50':
break
print ' '.join(row)
for row in reader:
content = row[0].split(',')
# get original peptide object
peptide = peptide_objects[content[0]]
binding_affinity = content[1]
if binary:
if binding_affinity <= 500:
result[allele_repr][peptide] = 1.0
else:
result[allele_repr][peptide] = 0.0
else:
result[allele_repr][peptide] = binding_affinity
if not result:
raise ValueError(
"No predictions could be made with " + self.name +
" for given input. Check your epitope length and HLA allele combination."
)
# create EpitopePredictionResult object. This is a multi-indexed DataFrame
# with Peptide and Method as multi-index and alleles as columns
df_result = EpitopePredictionResult.from_dict(result)
df_result.index = pandas.MultiIndex.from_tuples(
[tuple((i, self.name)) for i in df_result.index],
names=['Seq', 'Method'])
return df_result