def getBayesModel(G,p, mixPrior = None):
"""
Constructs a PWM CSI BayesMixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: BayesMixtureModel object
"""
if not mixPrior:
piPrior = mixture.DirichletPrior(G,[1.0]*G)
compPrior= []
for i in range(p):
compPrior.append( mixture.DirichletPrior(4,[1.02,1.02,1.02,1.02]) )
# arbitrary values of struct and comp parameters. Values should be
# reset by user using the structPriorHeuristic method.
mixPrior = mixture.MixtureModelPrior(0.05,0.05,piPrior, compPrior)
DNA = mixture.Alphabet(['A','C','G','T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append( mixture.DiscreteDistribution(4,phi,DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.BayesMixtureModel(G,pi, comps, mixPrior, struct =1)
return m
def getBayesModel(G, p, mixPrior=None):
"""
Constructs a PWM CSI BayesMixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: BayesMixtureModel object
"""
if not mixPrior:
piPrior = mixture.DirichletPrior(G, [1.0] * G)
compPrior = []
for i in range(p):
compPrior.append(
mixture.DirichletPrior(4, [1.02, 1.02, 1.02, 1.02]))
# arbitrary values of struct and comp parameters. Values should be
# reset by user using the structPriorHeuristic method.
mixPrior = mixture.MixtureModelPrior(0.05, 0.05, piPrior, compPrior)
DNA = mixture.Alphabet(['A', 'C', 'G', 'T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append(mixture.DiscreteDistribution(4, phi, DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.BayesMixtureModel(G, pi, comps, mixPrior, struct=1)
return m
def getModel(G,p):
"""
Constructs a PWM MixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: MixtureModel object
"""
DNA = mixture.Alphabet(['A','C','G','T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append( mixture.DiscreteDistribution(4,phi,DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.MixtureModel(G,pi, comps)
return m
def getModel(G, p):
"""
Constructs a PWM MixtureModel.
@param G: number of components
@param p: number of positions of the binding site
@return: MixtureModel object
"""
DNA = mixture.Alphabet(['A', 'C', 'G', 'T'])
comps = []
for i in range(G):
dlist = []
for j in range(p):
phi = mixture.random_vector(4)
dlist.append(mixture.DiscreteDistribution(4, phi, DNA))
comps.append(mixture.ProductDistribution(dlist))
pi = mixture.random_vector(G)
m = mixture.MixtureModel(G, pi, comps)
return m
math_sigma = random.uniform( 1.0,28.0)
missing_math = mixture.NormalDistribution(-9999.9,0.00001)
dist_math = mixture.NormalDistribution(math_mu, math_sigma)
mix_math = mixture.MixtureModel(2,[0.999,0.001],[dist_math, missing_math],compFix=[0,2])
spelling_mu = float(random.randint(80,120))
spelling_sigma =random.uniform( 1.0,28.0)
missing_spelling = mixture.NormalDistribution(-9999.9,0.00001)
dist_spelling = mixture.NormalDistribution(spelling_mu, spelling_sigma)
mix_spelling = mixture.MixtureModel(2,[0.999,0.001],[dist_spelling, missing_spelling],compFix=[0,2])
# diagnoses for cormobidit disorders
#"ODD" "CONDUCT" "SOC PHO" "SEP ANX" "SPEC PHO" "ENUR NOC" "ENUR DIU" "ENCOPRES" "TOURET" "TIC CRON" "TIC TRAN"
comor= []
for j in range(COMOR):
p_comor = [0.0] + mixture.random_vector(3)
comor_missing = mixture.MultinomialDistribution(1,4,[1.0,0.0,0.0,0.0],DIAG)
comor_mult = mixture.MultinomialDistribution(1,4,p_comor,DIAG)
comor_mix = mixture.MixtureModel(2,[0.999,0.001],[comor_mult,comor_missing],compFix=[0,2])
comor.append(comor_mix)
pd_comor = mixture.ProductDistribution(comor)
# the drd4 VNTR are represented as a discrete distribution over the observed lengths,
# the specific repeat sequence tpyes are not considered at this time
p_drd4_vntr_len = [0.0]+ mixture.random_vector(10)
dist_drd4_vntr_len = mixture.MultinomialDistribution(1, 11, p_drd4_vntr_len,VNTR)
vntr_missing = mixture.MultinomialDistribution(1, 11, [1.0]+[0.0]*10,VNTR)
mix_drd4_vntr_len = mixture.MixtureModel(2,[0.999,0.001],[dist_drd4_vntr_len,vntr_missing],compFix=[0,2])
[dist_math, missing_math],
compFix=[0, 2])
spelling_mu = float(random.randint(80, 120))
spelling_sigma = random.uniform(1.0, 28.0)
missing_spelling = mixture.NormalDistribution(-9999.9, 0.00001)
dist_spelling = mixture.NormalDistribution(spelling_mu, spelling_sigma)
mix_spelling = mixture.MixtureModel(2, [0.999, 0.001],
[dist_spelling, missing_spelling],
compFix=[0, 2])
# diagnoses for cormobidit disorders
#"ODD" "CONDUCT" "SOC PHO" "SEP ANX" "SPEC PHO" "ENUR NOC" "ENUR DIU" "ENCOPRES" "TOURET" "TIC CRON" "TIC TRAN"
comor = []
for j in range(COMOR):
p_comor = [0.0] + mixture.random_vector(3)
comor_missing = mixture.MultinomialDistribution(
1, 4, [1.0, 0.0, 0.0, 0.0], DIAG)
comor_mult = mixture.MultinomialDistribution(1, 4, p_comor, DIAG)
comor_mix = mixture.MixtureModel(2, [0.999, 0.001],
[comor_mult, comor_missing],
compFix=[0, 2])
comor.append(comor_mix)
pd_comor = mixture.ProductDistribution(comor)
# the drd4 VNTR are represented as a discrete distribution over the observed lengths,
# the specific repeat sequence tpyes are not considered at this time
p_drd4_vntr_len = [0.0] + mixture.random_vector(10)
dist_drd4_vntr_len = mixture.MultinomialDistribution(
1, 11, p_drd4_vntr_len, VNTR)
