def setUp(self):
self.proteins=[]
self.alleles = [Allele("HLA-A*01:01"),Allele("HLA-B*07:02"), Allele("HLA-C*03:01")]
self.peptides = [Peptide(p) for p in """SFSIFLLAL
GHRMAWDMM
VYEADDVIL
CFTPSPVVV
FLLLADARV
GPADGMVSK
YLYDHLAPM
GLRDLAVAV
GPTPLLYRL
TWVLVGGVL
IELGGKPAL
LAGGVLAAV
QYLAGLSTL
NFVSGIQYL
VLSDFKTWL
ARPDYNPPL
KLLPRLPGV
RHTPVNSWL
GLYLFNWAV
ALYDVVSTL
RRCRASGVL
WPLLLLLLA
VTYSLTGLW
YFVIFFVAA""".split()]
self.result= EpitopePredictorFactory("BIMAS").predict(self.peptides, self.alleles)
self.thresh = {"A*01:01":10,"B*07:02":10,"C*03:01":10}
def test_unsupported_allele_length_combination(self):
"""
Tests default functions
needs GLPK installed
:return:
"""
epi_pred = EpitopePredictorFactory("Syfpeithi")
cl_pred = CleavageSitePredictorFactory("PCM")
alleles = [
Allele("HLA-A*02:01", prob=0.5),
Allele("HLA-A*26:01", prob=0.5)
]
sbws = EpitopeAssemblyWithSpacer(self.epis,
cl_pred,
epi_pred,
alleles,
solver="cbc")
sol = sbws.solve()
print sol
assert all(i == str(j)
for i, j in zip(["GHRMAWDMM", "HH", "VYEADDVIL"], sol))
def test_unsupported_allele_length_combination_exception(self):
"""
Tests default functions
needs GLPK installed
:return:
"""
epi_pred = EpitopePredictorFactory("Syfpeithi")
cl_pred = CleavageSitePredictorFactory("PCM")
alleles = [Allele("HLA-A*26:01", prob=0.5)]
sbws = EpitopeAssemblyWithSpacer(self.epis,
cl_pred,
epi_pred,
alleles,
solver="cbc")
self.assertRaises(ValueError, sbws.solve)
def revert_allele_repr(self, name):
if name.startswith("H-2-"):
return MouseAllele(name)
else:
# since we need to support single and double mhc2 alleles
name_split = name.split('-')
if len(name_split) > 2:
return CombinedAllele(name_split[0] + '-' +
name_split[1][:4] + '*' +
name_split[1][4:] + '-' +
name_split[2][:4] + '*' +
name_split[2][4:])
else:
return Allele(name_split[0] + '-' + name_split[1][:4] +
'*' + name_split[1][4:])
def setUp(self):
epis ="""GHRMAWDMM
VYEADDVIL""".split("\n")
self.epis = map(lambda x: Peptide(x.strip()),epis)
self.alleles =[Allele("HLA-A*02:01",prob=0.5)]
def predict(self, peptides, alleles=None, **kwargs):
"""
Returns predictions for given peptides an :class:`~Fred2.Core.Allele.Allele`. If no
:class:`~Fred2.Core.Allele.Allele` are given, predictions for all available models are made.
:param peptides: A single :class:`~Fred2.Core.Peptide.Peptide` or a list of :class:`~Fred2.Core.Peptide.Peptide`
:type peptides: list(:class:`~Fred2.Core.Peptide.Peptide`) or :class:`~Fred2.Core.Peptide.Peptide`
:param alleles: A list of :class:`~Fred2.Core.Allele.Allele`
:type alleles: list(:class:`~Fred2.Core.Allele.Allele`) or class:`~Fred2.Core.Allele.Allele`
:param kwargs: optional parameter (not used yet)
:return: Returns a :class:`~Fred2.Core.Result.EpitopePredictionResult` object with the prediction results
:rtype: :class:`~Fred2.Core.Result.EpitopePredictionResult`
"""
def __load_allele_model(allele, length):
allele_model = "%s_%i" % (allele, length)
return getattr(
__import__("Fred2.Data.pssms." + self.name + ".mat." +
allele_model,
fromlist=[allele_model]), allele_model)
if isinstance(peptides, Peptide):
pep_seqs = {str(peptides): peptides}
else:
pep_seqs = {}
for p in peptides:
if not isinstance(p, Peptide):
raise ValueError("Input is not of type Protein or Peptide")
pep_seqs[str(p)] = p
if alleles is None:
al = [Allele("HLA-" + a) for a in self.supportedAlleles]
alleles_string = {
conv_a: a
for conv_a, a in itertools.izip(self.convert_alleles(al), al)
}
else:
if isinstance(alleles, Allele):
alleles = [alleles]
if any(not isinstance(p, Allele) for p in alleles):
raise ValueError("Input is not of type Allele")
alleles_string = {
conv_a: a
for conv_a, a in itertools.izip(self.convert_alleles(alleles),
alleles)
}
result = {}
for length, peps in itertools.groupby(pep_seqs.iterkeys(),
key=lambda x: len(x)):
peps = list(peps)
#dynamicaly import prediction PSSMS for alleles and predict
if length not in self.supportedLength:
warnings.warn("Peptide length of %i is not supported by %s" %
(length, self.name))
continue
for a in alleles_string.keys():
try:
pssm = __load_allele_model(a, length)
except ImportError:
warnings.warn("No model found for %s with length %i" %
(alleles_string[a], length))
continue
result[alleles_string[a]] = {}
##here is the prediction and result object missing##
for p in peps:
score = sum(pssm[i].get(p[i], 0.0)
for i in xrange(length)) + pssm.get(
-1, {}).get("con", 0)
score /= -length
score -= pssm[-1]["intercept"]
score /= pssm[-1]["slope"]
score = math.pow(10, score)
if score < 0.0001:
score = 0.0001
elif score > 1e6:
score = 1e6
result[alleles_string[a]][pep_seqs[p]] = score
#print a, score, result
if not result:
raise ValueError("No predictions could be made with " + self.name +
" for given input. Check your"
"epitope length and HLA allele combination.")
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, **kwargs):
"""
Returns predictions for given peptides an :class:`~Fred2.Core.Allele.Allele`. If no
:class:`~Fred2.Core.Allele.Allele` are given, predictions for all available models are made.
:param peptides: A single :class:`~Fred2.Core.Peptide.Peptide` or a list of :class:`~Fred2.Core.Peptide.Peptide`
:type peptides: list(:class:`~Fred2.Core.Peptide.Peptide`) or :class:`~Fred2.Core.Peptide.Peptide`
:param kwargs: optional parameter (not used yet)
:return: Returns a :class:`pandas.DataFrame` object with the prediction results
:rtype: :class:`pandas.DataFrame`
"""
def __load_allele_model(allele, length):
allele_model = "%s" % allele
return getattr(
__import__("Fred2.Data.pssms." + self.name + ".mat." +
allele_model,
fromlist=[allele_model]), allele_model)
if isinstance(peptides, Peptide):
pep_seqs = {str(peptides): peptides}
else:
pep_seqs = {}
for p in peptides:
if not isinstance(p, Peptide):
raise ValueError("Input is not of type Protein or Peptide")
pep_seqs[str(p)] = p
if alleles is None:
al = [Allele("HLA-" + a) for a in self.supportedAlleles]
alleles_string = {
conv_a: a
for conv_a, a in itertools.izip(self.convert_alleles(al), al)
}
else:
if isinstance(alleles, Allele):
alleles = [alleles]
if any(not isinstance(p, Allele) for p in alleles):
raise ValueError("Input is not of type Allele")
alleles_string = {
conv_a: a
for conv_a, a in itertools.izip(self.convert_alleles(alleles),
alleles)
}
result = {}
pep_groups = pep_seqs.keys()
pep_groups.sort(key=len)
for length, peps in itertools.groupby(pep_groups, key=len):
if self.supportedLength is not None and length not in self.supportedLength:
warnings.warn("Peptide length of %i is not supported by %s" %
(length, self.name))
continue
peps = list(peps)
for a, allele in alleles_string.iteritems():
if alleles_string[a] not in result:
result[allele] = {}
#load matrix
try:
pssm = __load_allele_model(a, length)
except ImportError:
pssm = []
importance = self.__importance if length <= 9 else \
self.__importance[:5] + ((length - 9) * [0.30]) + self.__importance[5:]
for p in peps:
score = sum(
self.__log_enrichment.get(p[i], 0.0) * importance[i]
for i in xrange(length) if i not in pssm)
result[allele][pep_seqs[p]] = score
if not result:
raise ValueError("No predictions could be made with " + self.name +
" for given input. Check your"
"epitope length and HLA allele combination.")
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 __main__():
parser = argparse.ArgumentParser(
"Write out information about supported models by Fred2 for installed predictor tool versions."
)
parser.add_argument('-p',
"--peptides",
help="File with one peptide per line")
parser.add_argument('-c',
"--mhcclass",
default=1,
help="MHC class I or II")
parser.add_argument('-l',
"--max_length",
help="Maximum peptide length",
type=int)
parser.add_argument('-ml',
"--min_length",
help="Minimum peptide length",
type=int)
parser.add_argument('-a',
"--alleles",
help="<Required> MHC Alleles",
required=True,
type=str)
parser.add_argument('-t',
'--tools',
help='Tools requested for peptide predictions',
required=True,
type=str)
parser.add_argument('-v',
'--versions',
help='<Required> File with used software versions.',
required=True)
args = parser.parse_args()
selected_methods = [item for item in args.tools.split(',')]
with open(args.versions, 'r') as versions_file:
tool_version = [(row[0].split()[0], str(row[1]))
for row in csv.reader(versions_file, delimiter=":")]
# NOTE this needs to be updated, if a newer version will be available via Fred2 and should be used in the future
tool_version.append(('syfpeithi', '1.0')) # how to handle this?
# get for each method the corresponding tool version
methods = {
method.strip(): version.strip()
for tool, version in tool_version for method in selected_methods
if tool.lower() in method.lower()
}
# get the alleles
alleles = [Allele(a) for a in args.alleles.split(";")]
peptide_lengths = []
if (args.peptides):
peptides = read_peptide_input(args.peptides)
peptide_lengths = set([len(pep) for pep in peptides])
else:
peptide_lengths = range(args.min_length, args.max_length + 1)
with open("model_report.txt", 'w') as output:
# check if requested tool versions are supported
for method, version in methods.items():
if version not in EpitopePredictorFactory.available_methods()[
method.lower()]:
raise ValueError("The specified version " + version + " for " +
method + " is not supported by Fred2.")
# check if requested alleles are supported
support_all_alleles = True
no_allele_support = True
for a in alleles:
supported = False
for method, version in methods.items():
predictor = EpitopePredictorFactory(method, version=version)
if a not in sorted(predictor.supportedAlleles):
output.write("Allele " + convert_allele_back(a) +
" is not supported by " + method + " " +
version + ".\n")
else:
supported = True
if not supported:
output.write(
"Allele " + convert_allele_back(a) +
" is not supported by any of the requested tools.\n")
logger.warning(
"Allele " + convert_allele_back(a) +
" is not supported by any of the requested tools.")
support_all_alleles = False
else:
no_allele_support = False
if support_all_alleles:
output.write(
"All selected alleles are supported by at least one of the requested tools.\n"
)
if no_allele_support:
output.write(
"None of the specified alleles is supported by any of the requested tools. Specify '--show_supported_models' to write out all supported models.\n"
)
raise ValueError(
"None of the specified alleles is supported by any of the requested tools. Specify '--show_supported_models' to write out all supported models."
)
output.write("\n")
# check if requested lengths are supported
support_all_lengths = True
no_length_support = True
for l in peptide_lengths:
supported = False
for method, version in methods.items():
predictor = EpitopePredictorFactory(method, version=version)
if l not in sorted(predictor.supportedLength):
output.write("Peptide length " + str(l) +
" is not supported by " + method + " " +
version + ".\n")
else:
supported = True
if not supported:
output.write(
"Peptide length " + str(l) +
" is not supported by any of the requested tools.\n")
logger.warning(
"Peptide length " + str(l) +
" is not supported by any of the requested tools.")
support_all_lengths = False
else:
no_length_support = False
if support_all_lengths:
output.write(
"All selected or provided peptide lengths are supported by at least one of the requested tools.\n"
)
if no_length_support:
output.write(
"None of the peptide lengths is supported by any of the requested tools. Specify '--show_supported_models' to write out all supported models.\n"
)
raise ValueError(
"None of the peptide lengths is supported by any of the requested tools. Specify '--show_supported_models' to write out all supported models."
)
def predict(self, peptides, alleles=None, **kwargs):
"""
Returns predictions for given peptides an alleles. If no alleles are given, predictions for all available models
are made.
:param peptides: A single :class:`~Fred2.Core.Peptide.Peptide` or a list of :class:`~Fred2.Core.Peptide.Peptide`
:type peptides: list(:class:`~Fred2.Core.Peptide.Peptide`) or :class:`~Fred2.Core.Peptide.Peptide`
:param alleles: A list of :class:`~Fred2.Core.Allele.Allele`
:type alleles: list(:class:`~Fred2.Core.Allele.Allele`) or :class:`~Fred2.Core.Allele.Allele`
:param kwargs: optional parameter (not used yet)
:return: Returns a :class:`~Fred2.Core.Result.EpitopePredictionResult` object with the prediction results
:rtype: :class:`~Fred2.Core.Result.EpitopePredictionResult`
"""
if isinstance(peptides, Peptide):
pep_seqs = {str(peptides): peptides}
else:
pep_seqs = {}
for p in peptides:
if not isinstance(p, Peptide):
raise ValueError("Input is not of type Protein or Peptide")
pep_seqs[str(p)] = p
if alleles is None:
al = [Allele("HLA-" + a) for a in self.supportedAlleles]
allales_string = {conv_a: a for conv_a, a in itertools.izip(self.convert_alleles(al), al)}
else:
if isinstance(alleles, Allele):
alleles = [alleles]
if any(not isinstance(p, Allele) for p in alleles):
raise ValueError("Input is not of type Allele")
allales_string = {conv_a: a for conv_a, a in itertools.izip(self.convert_alleles(alleles), alleles)}
# group peptides by length and
result = {}
model_path = pkg_resources.resource_filename("Fred2.Data.svms.%s" % self.name, "%s" % self.name)
# model_path = os.path.abspath("../Data/svms/%s/%s"%(self.name, self.name))
model = svmlight.read_model(model_path)
for length, peps in itertools.groupby(pep_seqs.iterkeys(), key=lambda x: len(x)):
# load svm model
peps = list(peps)
if length != 9:
warnings.warn("Peptide length of %i is not supported by UniTope" % length)
continue
for a in allales_string.keys():
if allales_string[a].name in self.supportedAlleles:
encoding = self.encode(peps, a)
pred = svmlight.classify(model, encoding.values())
result[allales_string[a]] = {}
for pep, score in itertools.izip(encoding.keys(), pred):
result[allales_string[a]][pep_seqs[pep]] = score
if not result:
raise ValueError("No predictions could be made for given input. Check your \
epitope length and HLA allele combination.")
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 setUp(self):
#Peptides of different length 9,10,11,12,13,14,15
self.peptides_mhcI = [Peptide("SYFPEITHI"), Peptide("IHTIEPFYS")]
self.peptides_fragment = [Peptide("IHTIEPFYSAA")]
self.mhcI = [Allele("HLA-B*15:01"), Allele("HLA-A*02:01")]
self.mhcII = [Allele("HLA-DRB1*07:01"), Allele("HLA-DRB1*15:01")]
def revert_allele_repr(self, name):
if name.startswith("H-2-"):
return MouseAllele(name)
else:
return Allele(name[:5] + '*' + name[5:7] + ':' + name[7:])
def revert_allele_repr(self, name):
if name.startswith("H-2-"):
return MouseAllele(name)
else:
return Allele(name)
def __main__():
parser = argparse.ArgumentParser(version=VERSION)
parser.add_argument('-c',
dest="mhcclass",
help='<Required> MHC class',
required=True)
parser.add_argument('-in',
dest="inf",
help='<Required> full path to the input file',
required=True)
parser.add_argument('-out',
dest="out",
help="<Required> full path to the output file",
required=True)
parser.add_argument(
'-allele',
dest="allele",
help=
"<Required> full path to an allele file, if 'in', allele file will be deduced from in file name",
required=True)
parser.add_argument(
'-dirallele',
dest="dirallele",
help=
"for use with '-allele in', describes full base path to the allele files"
)
options = parser.parse_args()
if len(sys.argv) <= 1:
parser.print_help()
sys.exit(1)
if not (options.inf or options.out or options.allele):
parser.print_help()
sys.exit(1)
target_alleles_set = set()
#Fred2.FileReader.read_lines is broken
#alleles = FileReader.read_lines(options.allele, type=Allele)
if options.allele == "in" and options.dirallele:
if "_W_" not in options.inf:
print "No class 1 type run detected."
sys.exit(0)
af = None
for sp in options.inf.split("_"):
if sp.startswith("BD"):
af = join(options.dirallele, sp.split("-")[1] + ".allele")
with open(af, 'r') as handle:
for line in handle:
target_alleles_set.add(Allele(line.strip().upper()))
else:
with open(options.allele, 'r') as handle:
for line in handle:
target_alleles_set.add(Allele(line.strip().upper()))
if not target_alleles_set:
parser.print_help()
sys.exit(1)
if options.mhcclass == "I":
ttn = EpitopePredictorFactory('netmhcpan', version='3.0')
lowerBound = 8
upperBound = 12
elif options.mhcclass == "II":
ttn = EpitopePredictorFactory('netmhcIIpan', version='3.1')
lowerBound = 15
upperBound = 25
pros = list()
peps = list()
f = oms.IdXMLFile()
f.load(options.inf, pros, peps)
pepstr = set()
for pep in peps:
for h in pep.getHits():
#if "decoy" not in h.getMetaValue("target_decoy"):
unmod = h.getSequence().toUnmodifiedString()
if lowerBound <= len(unmod) <= upperBound \
and 'U' not in unmod and 'B' not in unmod and 'X' not in unmod and 'Z' not in unmod:
pepstr.add(h.getSequence().toUnmodifiedString())
es = [Peptide(x) for x in pepstr]
try:
preds_n = ttn.predict(es, alleles=target_alleles_set)
except Exception as e:
print "something went wrong with the netMHC prediction", options.inf, "what:", str(
e)
sys.exit(1)
#only max
preds = dict()
for index, row in preds_n.iterrows():
score = row.max() #bigger_is_better
allele = str(row.idxmax())
categ = categorize(score)
seq = row.name[0].tostring()
if categ:
preds[seq] = (allele, categ, score)
npeps = list()
for pep in peps:
hits = pep.getHits()
nhits = list()
for h in hits:
if h.getSequence().toUnmodifiedString() in preds:
x = preds[h.getSequence().toUnmodifiedString()]
h.setMetaValue('binder', x[0])
h.setMetaValue(str(x[1]), x[2])
nhits.append(h)
else:
nhits.append(h)
pep.setHits(nhits)
f.store(options.out, pros, peps)
def setUp(self):
epis = """GHRMAWDMM
VYEADDVIL""".split("\n")
self.epis = [Peptide(x.strip()) for x in epis]
self.alleles = [Allele("HLA-A*02:01", prob=0.5)]
