def __init__(self,
results,
threshold=None,
k=10,
solver="glpk",
verbosity=0):
"""
:param result: Epitope prediction result object from which the epitope selection should be performed
:type result: :class:`~Fred2.Core.Result.EpitopePredictionResult`
:param dict(str,float) threshold: A dictionary scoring the binding thresholds for each HLA
:class:`~Fred2.Core.Allele.Allele` key = allele name; value = the threshold
:param int k: The number of epitopes to select
:param str solver: The solver to be used (default glpk)
:param int verbosity: Integer defining whether additional debugg prints are made >0 => debug mode
"""
#check input data
if not isinstance(results, EpitopePredictionResult):
raise ValueError(
"first input parameter is not of type EpitopePredictionResult")
_alleles = copy.deepcopy(results.columns.values.tolist())
#test if allele prob is set, if not set allele prob uniform
#if only partly set infer missing values (assuming uniformity of missing value)
prob = []
no_prob = []
for a in _alleles:
if a.prob is None:
no_prob.append(a)
else:
prob.append(a)
if len(no_prob) > 0:
#group by locus
no_prob_grouped = {}
prob_grouped = {}
for a in no_prob:
no_prob_grouped.setdefault(a.locus, []).append(a)
for a in prob:
prob_grouped.setdefault(a.locus, []).append(a)
for g, v in no_prob_grouped.items():
total_loc_a = len(v)
if g in prob_grouped:
remaining_mass = 1.0 - sum(a.prob for a in prob_grouped[g])
for a in v:
a.prob = remaining_mass / total_loc_a
else:
for a in v:
a.prob = 1.0 / total_loc_a
probs = {a.name: a.prob for a in _alleles}
if verbosity:
for a in _alleles:
print(a.name, a.prob)
#start constructing model
self.__solver = SolverFactory(solver)
self.__verbosity = verbosity
self.__changed = True
self.__alleleProb = _alleles
self.__k = k
self.__result = None
self.__thresh = {} if threshold is None else threshold
# Variable, Set and Parameter preparation
alleles_I = {}
variations = []
epi_var = {}
imm = {}
peps = {}
cons = {}
#unstack multiindex df to get normal df based on first prediction method
#and filter for binding epitopes
method = results.index.values[0][1]
res_df = results.xs(results.index.values[0][1], level="Method")
res_df = res_df[res_df.apply(
lambda x: any(x[a] > self.__thresh.get(a.name, -float("inf"))
for a in res_df.columns),
axis=1)]
for tup in res_df.itertuples():
p = tup[0]
seq = str(p)
peps[seq] = p
for a, s in itr.izip(res_df.columns, tup[1:]):
if method in ["smm", "smmpmbec", "arb", "comblibsidney"]:
try:
thr = min(
1.,
max(
0.0, 1.0 -
math.log(self.__thresh.get(a.name), 50000))
) if a.name in self.__thresh else -float("inf")
except:
thr = 0
if s >= thr:
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = min(1.,
max(0.0, 1.0 - math.log(s, 50000)))
else:
if s > self.__thresh.get(a.name, -float("inf")):
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = s
prots = set(pr for pr in p.get_all_proteins())
cons[seq] = len(prots)
for prot in prots:
variations.append(prot.gene_id)
epi_var.setdefault(prot.gene_id, set()).add(seq)
self.__peptideSet = peps
#calculate conservation
variations = set(variations)
total = len(variations)
for e, v in cons.items():
try:
cons[e] = v / total
except ZeroDivisionError:
cons[e] = 1
model = ConcreteModel()
#set definition
model.Q = Set(initialize=variations)
model.E = Set(initialize=set(peps.keys()))
model.A = Set(initialize=list(alleles_I.keys()))
model.E_var = Set(model.Q, initialize=lambda mode, v: epi_var[v])
model.A_I = Set(model.A, initialize=lambda model, a: alleles_I[a])
#parameter definition
model.k = Param(initialize=self.__k,
within=PositiveIntegers,
mutable=True)
model.p = Param(model.A, initialize=lambda model, a: probs[a])
model.c = Param(model.E,
initialize=lambda model, e: cons[e],
mutable=True)
#threshold parameters
model.i = Param(model.E,
model.A,
initialize=lambda model, e, a: imm[e, a])
model.t_allele = Param(initialize=0,
within=NonNegativeIntegers,
mutable=True)
model.t_var = Param(initialize=0,
within=NonNegativeIntegers,
mutable=True)
model.t_c = Param(initialize=0.0,
within=NonNegativeReals,
mutable=True)
# Variable Definition
model.x = Var(model.E, within=Binary)
model.y = Var(model.A, within=Binary)
model.z = Var(model.Q, within=Binary)
# Objective definition
model.Obj = Objective(
rule=lambda model: sum(model.x[e] * sum(model.p[a] * model.i[e, a]
for a in model.A)
for e in model.E),
sense=maximize)
#Obligatory Constraint (number of selected epitopes)
model.NofSelectedEpitopesCov = Constraint(
rule=lambda model: sum(model.x[e] for e in model.E) <= model.k)
#optional constraints (in basic model they are disabled)
model.IsAlleleCovConst = Constraint(
model.A,
rule=lambda model, a: sum(model.x[e]
for e in model.A_I[a]) >= model.y[a])
model.MinAlleleCovConst = Constraint(rule=lambda model: sum(
model.y[a] for a in model.A) >= model.t_allele)
model.IsAntigenCovConst = Constraint(
model.Q,
rule=lambda model, q: sum(model.x[e]
for e in model.E_var[q]) >= model.z[q])
model.MinAntigenCovConst = Constraint(
rule=lambda model: sum(model.z[q] for q in model.Q) >= model.t_var)
model.EpitopeConsConst = Constraint(
model.E,
rule=lambda model, e:
(1 - model.c[e]) * model.x[e] <= 1 - model.t_c)
#generate instance
self.instance = model
if self.__verbosity > 0:
print("MODEL INSTANCE")
self.instance.pprint()
#constraints
self.instance.IsAlleleCovConst.deactivate()
self.instance.MinAlleleCovConst.deactivate()
self.instance.IsAntigenCovConst.deactivate()
self.instance.MinAntigenCovConst.deactivate()
self.instance.EpitopeConsConst.deactivate()
def __init__(self,
results,
threshold=None,
dist_threshold=1.0,
distance={},
expression={},
uncertainty={},
overlap=0,
k=10,
k_taa=0,
solver="glpk",
verbosity=0,
include=[]):
"""
:param results: Epitope prediction result object from which the epitope selection should be performed
:type results: :class:`~Fred2.Core.Result.EpitopePredictionResult`
:param dict(str,float) threshold: A dictionary scoring the binding thresholds for each HLA
:class:`~Fred2.Core.Allele.Allele` key = allele name; value = the threshold
:param float dist_threshold: Distance threshold: an epitope gets excluded if an epitope has dist-2-self score
smaller or equal to this threshold for any HLA allele
:param dict((str,str),float) distance: A dictionary with key: (peptide sequence, HLA name)
and value the distance2self
:param dict(str, float) expression: A dictionary with key: gene ID, and value: Gene expression
in FPKM/RPKM or TPM
:param dict((str,str),float) uncertainty: A dictionary with key (peptide seq, HLA name), and value the
associated uncertainty of the immunogenicity prediction
:param int k: The number of epitopes to select
:param int k_taa: The number of TAA epitopes to select
:param str solver: The solver to be used (default glpk)
:param int verbosity: Integer defining whether additional debug prints are made >0 => debug mode
"""
# check input data
if not isinstance(results, EpitopePredictionResult):
raise ValueError(
"first input parameter is not of type EpitopePredictionResult")
_alleles = results.columns.values.tolist()
# generate abundance dictionary of HLA alleles default is 2.0 as values will be log2 transformed
probs = {
a.name: 2.0 if a.get_metadata("abundance", only_first=True) is None
else a.get_metadata("abundance", only_first=True)
for a in _alleles
}
# start constructing model
self.__solver = SolverFactory(solver)
self.__verbosity = verbosity
self.__changed = True
self.__alleleProb = _alleles
self.__k = k
self.__k_taa = k_taa
self.__result = None
self.__thresh = {} if threshold is None else threshold
self.__included = include
self.overlap = overlap
# variable, set and parameter preparation
alleles_I = {}
variations = []
epi_var = {}
imm = {}
peps = {}
taa = []
var_epi = {}
cons = {}
for a in _alleles:
alleles_I.setdefault(a.name, set())
# unstack multiindex df to get normal df based on first prediction method
# and filter for binding epitopes
method = results.index.values[0][1]
res_df = results.xs(results.index.values[0][1], level="Method")
# if predcitions are not available for peptides/alleles, replace by 0
res_df.fillna(0, inplace=True)
res_df = res_df[res_df.apply(
lambda x: any(x[a] > self.__thresh.get(a.name, -float("inf"))
for a in res_df.columns),
axis=1)]
res_df.fillna(0, inplace=True)
# transform scores to 1-log50k(IC50) scores if neccassary
# and generate mapping dictionaries for Set definitions
for tup in res_df.itertuples():
p = tup[0]
seq = str(p)
if any(
distance.get((seq, a.name), 1.0) <= dist_threshold
for a in _alleles):
continue
peps[seq] = p
if p.get_metadata("taa", only_first=True):
taa.append(seq)
for a, s in itr.izip(res_df.columns, tup[1:]):
if method in ["smm", "smmpmbec", "arb", "comblibsidney"]:
try:
thr = min(
1.,
max(
0.0, 1.0 -
math.log(self.__thresh.get(a.name), 50000))
) if a.name in self.__thresh else -float("inf")
except:
thr = 0
if s >= thr:
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = min(1.,
max(0.0, 1.0 - math.log(s, 50000)))
else:
if s > self.__thresh.get(a.name, -float("inf")):
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = s
prots = set(pr for pr in p.get_all_proteins())
cons[seq] = len(prots)
for prot in prots:
variations.append(prot.gene_id)
epi_var.setdefault(prot.gene_id, set()).add(seq)
var_epi.setdefault(str(seq), set()).add(prot.gene_id)
self.__peptideSet = peps
# calculate conservation
variations = set(variations)
total = len(variations)
for e, v in cons.iteritems():
try:
cons[e] = v / total
except ZeroDivisionError:
cons[e] = 1
model = ConcreteModel()
######################################
#
# MODEL DEFINITIONS
#
######################################
# set definition
model.Q = Set(initialize=variations)
model.E = Set(initialize=set(peps.keys()))
model.TAA = Set(initialize=set(taa))
model.A = Set(initialize=alleles_I.keys())
model.G = Set(model.E, initialize=lambda model, e: var_epi[e])
model.E_var = Set(model.Q, initialize=lambda mode, v: epi_var[v])
model.A_I = Set(model.A, initialize=lambda model, a: alleles_I[a])
if self.__included is not None:
if len(self.__included) > k:
raise ValueError(
"More epitopes to include than epitopes to select! "
"Either raise k or reduce epitopes to include.")
model.Include = Set(within=model.E, initialize=self.__included)
if overlap > 0:
def longest_common_substring(model):
result = []
for s1, s2 in itr.combinations(model.E, 2):
if s1 != s2:
if s1 in s2 or s2 in s1:
result.append((s1, s2))
m = [[0] * (1 + len(s2)) for i in xrange(1 + len(s1))]
longest, x_longest = 0, 0
for x in xrange(1, 1 + len(s1)):
for y in xrange(1, 1 + len(s2)):
if s1[x - 1] == s2[y - 1]:
m[x][y] = m[x - 1][y - 1] + 1
if m[x][y] > longest:
longest = m[x][y]
x_longest = x
else:
m[x][y] = 0
if len(s1[x_longest - longest:x_longest]) >= overlap:
result.append((s1, s2))
return set(result)
model.O = Set(dimen=2, initialize=longest_common_substring)
# parameter definition
model.k = Param(initialize=self.__k,
within=PositiveIntegers,
mutable=True)
model.k_taa = Param(initialize=self.__k_taa,
within=NonNegativeIntegers,
mutable=True)
model.p = Param(
model.A,
initialize=lambda model, a: max(0, math.log(probs[a] + 0.001, 2)))
model.c = Param(model.E,
initialize=lambda model, e: cons[e],
mutable=True)
model.sigma = Param(model.E,
model.A,
initialize=lambda model, e, a: uncertainty.get(
(e, a), 0))
model.i = Param(model.E,
model.A,
initialize=lambda model, e, a: imm[e, a])
model.t_allele = Param(initialize=0,
within=NonNegativeIntegers,
mutable=True)
model.t_var = Param(initialize=0,
within=NonNegativeIntegers,
mutable=True)
model.t_c = Param(initialize=0.0,
within=NonNegativeReals,
mutable=True)
model.abd = Param(model.Q,
initialize=lambda model, g: max(
0, math.log(expression.get(g, 2) + 0.001, 2)))
model.eps1 = Param(initialize=1e6, mutable=True)
model.eps2 = Param(initialize=1e6, mutable=True)
# variable Definition
model.x = Var(model.E, within=Binary)
model.y = Var(model.A, within=Binary)
model.z = Var(model.Q, within=Binary)
# objective definition
model.Obj1 = Objective(rule=lambda model: -sum(model.x[e] * sum(
model.abd[g] for g in model.G[e]) * sum(model.p[a] * model.i[e, a]
for a in model.A)
for e in model.E),
sense=minimize)
model.Obj2 = Objective(
rule=lambda model: sum(model.x[e] * sum(model.sigma[e, a]
for a in model.A)
for e in model.E),
sense=minimize)
# constraints
# obligatory Constraint (number of selected epitopes)
model.NofSelectedEpitopesCov1 = Constraint(
rule=lambda model: sum(model.x[e] for e in model.E) >= model.k)
model.NofSelectedEpitopesCov2 = Constraint(
rule=lambda model: sum(model.x[e] for e in model.E) <= model.k)
model.NofSelectedTAACov = Constraint(rule=lambda model: sum(
model.x[e] for e in model.TAA) <= model.k_taa)
# optional constraints (in basic model they are disabled)
model.IsAlleleCovConst = Constraint(
model.A,
rule=lambda model, a: sum(model.x[e]
for e in model.A_I[a]) >= model.y[a])
model.MinAlleleCovConst = Constraint(rule=lambda model: sum(
model.y[a] for a in model.A) >= model.t_allele)
model.IsAntigenCovConst = Constraint(
model.Q,
rule=lambda model, q: sum(model.x[e]
for e in model.E_var[q]) >= model.z[q])
model.MinAntigenCovConst = Constraint(
rule=lambda model: sum(model.z[q] for q in model.Q) >= model.t_var)
model.EpitopeConsConst = Constraint(
model.E,
rule=lambda model, e:
(1 - model.c[e]) * model.x[e] <= 1 - model.t_c)
if overlap > 0:
model.OverlappingConstraint = Constraint(
model.O,
rule=lambda model, e1, e2: model.x[e1] + model.x[e2] <= 1)
# constraints for Pareto optimization
model.ImmConst = Constraint(rule=lambda model: sum(model.x[e] * sum(
model.abd[g] for g in model.G[e]) * sum(model.p[a] * model.i[
e, a] for a in model.A) for e in model.E) <= model.eps1)
model.UncertaintyConst = Constraint(
rule=lambda model: sum(model.x[e] * sum(model.sigma[
e, a] for a in model.A) for e in model.E) <= model.eps2)
self.__objectives = [model.Obj1, model.Obj2]
self.__constraints = [model.UncertaintyConst, model.ImmConst]
self.__epsilons = [model.eps2, model.eps1]
# include constraint
model.IncludeEpitopeConstraint = Constraint(
model.Include, rule=lambda model, e: model.x[e] >= 1)
# generate instance
self.instance = model
if self.__verbosity > 0:
print "MODEL INSTANCE"
self.instance.pprint()
# constraints
self.instance.Obj2.deactivate()
self.instance.ImmConst.deactivate()
self.instance.UncertaintyConst.deactivate()
self.instance.IsAlleleCovConst.deactivate()
self.instance.MinAlleleCovConst.deactivate()
self.instance.IsAntigenCovConst.deactivate()
self.instance.MinAntigenCovConst.deactivate()
self.instance.EpitopeConsConst.deactivate()
def __init__(self, results, threshold=None, k=10, solver="glpk", verbosity=0):
"""
:param result: Epitope prediction result object from which the epitope selection should be performed
:type result: :class:`~Fred2.Core.Result.EpitopePredictionResult`
:param dict(str,float) threshold: A dictionary scoring the binding thresholds for each HLA
:class:`~Fred2.Core.Allele.Allele` key = allele name; value = the threshold
:param int k: The number of epitopes to select
:param str solver: The solver to be used (default glpk)
:param int verbosity: Integer defining whether additional debugg prints are made >0 => debug mode
"""
#check input data
if not isinstance(results, EpitopePredictionResult):
raise ValueError("first input parameter is not of type EpitopePredictionResult")
_alleles = copy.deepcopy(results.columns.values.tolist())
#test if allele prob is set, if not set allele prob uniform
#if only partly set infer missing values (assuming uniformity of missing value)
prob = []
no_prob = []
for a in _alleles:
if a.prob is None:
no_prob.append(a)
else:
prob.append(a)
if len(no_prob) > 0:
#group by locus
no_prob_grouped = {}
prob_grouped = {}
for a in no_prob:
no_prob_grouped.setdefault(a.locus, []).append(a)
for a in prob:
prob_grouped.setdefault(a.locus, []).append(a)
for g, v in no_prob_grouped.iteritems():
total_loc_a = len(v)
if g in prob_grouped:
remaining_mass = 1.0 - sum(a.prob for a in prob_grouped[g])
for a in v:
a.prob = remaining_mass/total_loc_a
else:
for a in v:
a.prob = 1.0/total_loc_a
probs = {a.name:a.prob for a in _alleles}
if verbosity:
for a in _alleles:
print a.name, a.prob
#start constructing model
self.__solver = SolverFactory(solver)
self.__verbosity = verbosity
self.__changed = True
self.__alleleProb = _alleles
self.__k = k
self.__result = None
self.__thresh = {} if threshold is None else threshold
# Variable, Set and Parameter preparation
alleles_I = {}
variations = []
epi_var = {}
imm = {}
peps = {}
cons = {}
#unstack multiindex df to get normal df based on first prediction method
#and filter for binding epitopes
method = results.index.values[0][1]
res_df = results.xs(results.index.values[0][1], level="Method")
res_df = res_df[res_df.apply(lambda x: any(x[a] > self.__thresh.get(a.name, -float("inf"))
for a in res_df.columns), axis=1)]
for tup in res_df.itertuples():
p = tup[0]
seq = str(p)
peps[seq] = p
for a, s in itr.izip(res_df.columns, tup[1:]):
if method in ["smm", "smmpmbec", "arb", "comblibsidney"]:
try:
thr = min(1., max(0.0, 1.0 - math.log(self.__thresh.get(a.name),
50000))) if a.name in self.__thresh else -float("inf")
except:
thr = 0
if s >= thr:
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = min(1., max(0.0, 1.0 - math.log(s, 50000)))
else:
if s > self.__thresh.get(a.name, -float("inf")):
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = s
prots = set(pr for pr in p.get_all_proteins())
cons[seq] = len(prots)
for prot in prots:
variations.append(prot.gene_id)
epi_var.setdefault(prot.gene_id, set()).add(seq)
self.__peptideSet = peps
#calculate conservation
variations = set(variations)
total = len(variations)
for e, v in cons.iteritems():
try:
cons[e] = v / total
except ZeroDivisionError:
cons[e] = 1
model = ConcreteModel()
#set definition
model.Q = Set(initialize=variations)
model.E = Set(initialize=set(peps.keys()))
model.A = Set(initialize=alleles_I.keys())
model.E_var = Set(model.Q, initialize=lambda mode, v: epi_var[v])
model.A_I = Set(model.A, initialize=lambda model, a: alleles_I[a])
#parameter definition
model.k = Param(initialize=self.__k, within=PositiveIntegers, mutable=True)
model.p = Param(model.A, initialize=lambda model, a: probs[a])
model.c = Param(model.E, initialize=lambda model, e: cons[e],mutable=True)
#threshold parameters
model.i = Param(model.E, model.A, initialize=lambda model, e, a: imm[e, a])
model.t_allele = Param(initialize=0, within=NonNegativeIntegers, mutable=True)
model.t_var = Param(initialize=0, within=NonNegativeIntegers, mutable=True)
model.t_c = Param(initialize=0.0, within=NonNegativeReals, mutable=True)
# Variable Definition
model.x = Var(model.E, within=Binary)
model.y = Var(model.A, within=Binary)
model.z = Var(model.Q, within=Binary)
# Objective definition
model.Obj = Objective(
rule=lambda model: sum(model.x[e] * sum(model.p[a] * model.i[e, a] for a in model.A) for e in model.E),
sense=maximize)
#Obligatory Constraint (number of selected epitopes)
model.NofSelectedEpitopesCov = Constraint(rule=lambda model: sum(model.x[e] for e in model.E) <= model.k)
#optional constraints (in basic model they are disabled)
model.IsAlleleCovConst = Constraint(model.A,
rule=lambda model, a: sum(model.x[e] for e in model.A_I[a]) >= model.y[a])
model.MinAlleleCovConst = Constraint(rule=lambda model: sum(model.y[a] for a in model.A) >= model.t_allele)
model.IsAntigenCovConst = Constraint(model.Q,
rule=lambda model, q: sum(model.x[e] for e in model.E_var[q]) >= model.z[q])
model.MinAntigenCovConst = Constraint(rule=lambda model: sum(model.z[q] for q in model.Q) >= model.t_var)
model.EpitopeConsConst = Constraint(model.E,
rule=lambda model, e: (1 - model.c[e]) * model.x[e] <= 1 - model.t_c)
#generate instance
self.instance = model
if self.__verbosity > 0:
print "MODEL INSTANCE"
self.instance.pprint()
#constraints
self.instance.IsAlleleCovConst.deactivate()
self.instance.MinAlleleCovConst.deactivate()
self.instance.IsAntigenCovConst.deactivate()
self.instance.MinAntigenCovConst.deactivate()
self.instance.EpitopeConsConst.deactivate()
def __init__(self, results, threshold=None, dist_threshold=1.0, distance={}, expression={}, uncertainty={}, overlap=0, k=10, k_taa=0,
solver="glpk", verbosity=0, include=[]):
"""
:param results: Epitope prediction result object from which the epitope selection should be performed
:type results: :class:`~Fred2.Core.Result.EpitopePredictionResult`
:param dict(str,float) threshold: A dictionary scoring the binding thresholds for each HLA
:class:`~Fred2.Core.Allele.Allele` key = allele name; value = the threshold
:param float dist_threshold: Distance threshold: an epitope gets excluded if an epitope has dist-2-self score
smaller or equal to this threshold for any HLA allele
:param dict((str,str),float) distance: A dictionary with key: (peptide sequence, HLA name)
and value the distance2self
:param dict(str, float) expression: A dictionary with key: gene ID, and value: Gene expression
in FPKM/RPKM or TPM
:param dict((str,str),float) uncertainty: A dictionary with key (peptide seq, HLA name), and value the
associated uncertainty of the immunogenicity prediction
:param int k: The number of epitopes to select
:param int k_taa: The number of TAA epitopes to select
:param str solver: The solver to be used (default glpk)
:param int verbosity: Integer defining whether additional debug prints are made >0 => debug mode
"""
# check input data
if not isinstance(results, EpitopePredictionResult):
raise ValueError("first input parameter is not of type EpitopePredictionResult")
_alleles = results.columns.values.tolist()
# generate abundance dictionary of HLA alleles default is 2.0 as values will be log2 transformed
probs = {a.name:2.0 if a.get_metadata("abundance", only_first=True) is None else
a.get_metadata("abundance", only_first=True) for a in _alleles}
# start constructing model
self.__solver = SolverFactory(solver)
self.__verbosity = verbosity
self.__changed = True
self.__alleleProb = _alleles
self.__k = k
self.__k_taa = k_taa
self.__result = None
self.__thresh = {} if threshold is None else threshold
self.__included = include
self.overlap=overlap
# variable, set and parameter preparation
alleles_I = {}
variations = []
epi_var = {}
imm = {}
peps = {}
taa = []
var_epi = {}
cons = {}
for a in _alleles:
alleles_I.setdefault(a.name, set())
# unstack multiindex df to get normal df based on first prediction method
# and filter for binding epitopes
method = results.index.values[0][1]
res_df = results.xs(results.index.values[0][1], level="Method")
# if predcitions are not available for peptides/alleles, replace by 0
res_df.fillna(0, inplace=True)
res_df = res_df[res_df.apply(lambda x: any(x[a] > self.__thresh.get(a.name, -float("inf"))
for a in res_df.columns), axis=1)]
res_df.fillna(0, inplace=True)
# transform scores to 1-log50k(IC50) scores if neccassary
# and generate mapping dictionaries for Set definitions
for tup in res_df.itertuples():
p = tup[0]
seq = str(p)
if any(distance.get((seq, a.name), 1.0) <= dist_threshold for a in _alleles):
continue
peps[seq] = p
if p.get_metadata("taa",only_first=True):
taa.append(seq)
for a, s in itr.izip(res_df.columns, tup[1:]):
if method in ["smm", "smmpmbec", "arb", "comblibsidney"]:
try:
thr = min(1., max(0.0, 1.0 - math.log(self.__thresh.get(a.name),
50000))) if a.name in self.__thresh else -float("inf")
except:
thr = 0
if s >= thr:
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = min(1., max(0.0, 1.0 - math.log(s, 50000)))
else:
if s > self.__thresh.get(a.name, -float("inf")):
alleles_I.setdefault(a.name, set()).add(seq)
imm[seq, a.name] = s
prots = set(pr for pr in p.get_all_proteins())
cons[seq] = len(prots)
for prot in prots:
variations.append(prot.gene_id)
epi_var.setdefault(prot.gene_id, set()).add(seq)
var_epi.setdefault(str(seq), set()).add(prot.gene_id)
self.__peptideSet = peps
# calculate conservation
variations = set(variations)
total = len(variations)
for e, v in cons.iteritems():
try:
cons[e] = v / total
except ZeroDivisionError:
cons[e] = 1
model = ConcreteModel()
######################################
#
# MODEL DEFINITIONS
#
######################################
# set definition
model.Q = Set(initialize=variations)
model.E = Set(initialize=set(peps.keys()))
model.TAA = Set(initialize=set(taa))
model.A = Set(initialize=alleles_I.keys())
model.G = Set(model.E, initialize=lambda model, e: var_epi[e])
model.E_var = Set(model.Q, initialize=lambda mode, v: epi_var[v])
model.A_I = Set(model.A, initialize=lambda model, a: alleles_I[a])
if self.__included is not None:
if len(self.__included) > k:
raise ValueError("More epitopes to include than epitopes to select! "
"Either raise k or reduce epitopes to include.")
model.Include = Set(within=model.E, initialize=self.__included)
if overlap > 0:
def longest_common_substring(model):
result = []
for s1,s2 in itr.combinations(model.E,2):
if s1 != s2:
if s1 in s2 or s2 in s1:
result.append((s1,s2))
m = [[0] * (1 + len(s2)) for i in xrange(1 + len(s1))]
longest, x_longest = 0, 0
for x in xrange(1, 1 + len(s1)):
for y in xrange(1, 1 + len(s2)):
if s1[x - 1] == s2[y - 1]:
m[x][y] = m[x - 1][y - 1] + 1
if m[x][y] > longest:
longest = m[x][y]
x_longest = x
else:
m[x][y] = 0
if len(s1[x_longest - longest: x_longest]) >= overlap:
result.append((s1,s2))
return set(result)
model.O = Set(dimen=2, initialize=longest_common_substring)
# parameter definition
model.k = Param(initialize=self.__k, within=PositiveIntegers, mutable=True)
model.k_taa = Param(initialize=self.__k_taa, within=NonNegativeIntegers, mutable=True)
model.p = Param(model.A, initialize=lambda model, a: max(0, math.log(probs[a]+0.001,2)))
model.c = Param(model.E, initialize=lambda model, e: cons[e],mutable=True)
model.sigma = Param (model. E, model.A, initialize=lambda model, e, a: uncertainty.get((e,a), 0))
model.i = Param(model.E, model.A, initialize=lambda model, e, a: imm[e, a])
model.t_allele = Param(initialize=0, within=NonNegativeIntegers, mutable=True)
model.t_var = Param(initialize=0, within=NonNegativeIntegers, mutable=True)
model.t_c = Param(initialize=0.0, within=NonNegativeReals, mutable=True)
model.abd = Param(model.Q, initialize=lambda model, g: max(0, math.log(expression.get(g, 2)+0.001, 2)))
model.eps1 = Param(initialize=1e6, mutable=True)
model.eps2 = Param(initialize=1e6, mutable=True)
# variable Definition
model.x = Var(model.E, within=Binary)
model.y = Var(model.A, within=Binary)
model.z = Var(model.Q, within=Binary)
# objective definition
model.Obj1 = Objective(
rule=lambda model: -sum(model.x[e] * sum(model.abd[g] for g in model.G[e])
* sum(model.p[a] * model.i[e, a] for a in model.A) for e in model.E),
sense=minimize)
model.Obj2 = Objective(
rule=lambda model: sum(model.x[e]*sum(model.sigma[e,a] for a in model.A) for e in model.E),
sense=minimize)
# constraints
# obligatory Constraint (number of selected epitopes)
model.NofSelectedEpitopesCov1 = Constraint(rule=lambda model: sum(model.x[e] for e in model.E) >= model.k)
model.NofSelectedEpitopesCov2 = Constraint(rule=lambda model: sum(model.x[e] for e in model.E) <= model.k)
model.NofSelectedTAACov = Constraint(rule=lambda model: sum(model.x[e] for e in model.TAA) <= model.k_taa)
# optional constraints (in basic model they are disabled)
model.IsAlleleCovConst = Constraint(model.A,
rule=lambda model, a: sum(model.x[e] for e in model.A_I[a]) >= model.y[a])
model.MinAlleleCovConst = Constraint(rule=lambda model: sum(model.y[a] for a in model.A) >= model.t_allele)
model.IsAntigenCovConst = Constraint(model.Q,
rule=lambda model, q: sum(model.x[e] for e in model.E_var[q]) >= model.z[q])
model.MinAntigenCovConst = Constraint(rule=lambda model: sum(model.z[q] for q in model.Q) >= model.t_var)
model.EpitopeConsConst = Constraint(model.E,
rule=lambda model, e: (1 - model.c[e]) * model.x[e] <= 1 - model.t_c)
if overlap > 0:
model.OverlappingConstraint = Constraint(model.O, rule=lambda model, e1, e2: model.x[e1]+model.x[e2] <= 1)
# constraints for Pareto optimization
model.ImmConst = Constraint(rule=lambda model: sum(model.x[e] * sum(model.abd[g] for g in model.G[e])
* sum(model.p[a] * model.i[e, a]
for a in model.A) for e in model.E) <= model.eps1)
model.UncertaintyConst = Constraint(rule=lambda model:sum(model.x[e]*sum(model.sigma[e,a]
for a in model.A)
for e in model.E) <= model.eps2)
self.__objectives = [model.Obj1, model.Obj2]
self.__constraints = [model.UncertaintyConst, model.ImmConst]
self.__epsilons = [model.eps2, model.eps1]
# include constraint
model.IncludeEpitopeConstraint = Constraint(model.Include, rule=lambda model, e: model.x[e] >= 1)
# generate instance
self.instance = model
if self.__verbosity > 0:
print "MODEL INSTANCE"
self.instance.pprint()
# constraints
self.instance.Obj2.deactivate()
self.instance.ImmConst.deactivate()
self.instance.UncertaintyConst.deactivate()
self.instance.IsAlleleCovConst.deactivate()
self.instance.MinAlleleCovConst.deactivate()
self.instance.IsAntigenCovConst.deactivate()
self.instance.MinAntigenCovConst.deactivate()
self.instance.EpitopeConsConst.deactivate()
