def test_genotypes_exact():
"""
Test whether genotype knockoffs with true HMM are accurate
"""
p = 10
K = 3
M = 3
n_train = 1000
n_test = 100000
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n_train)
_, Xfp_file = tempfile.mkstemp()
fp.writeXtoInp(X, Xfp_file)
fastphase = "fastphase" # Name of fastPhase executable
_, out_path = tempfile.mkstemp()
fp.runFastPhase(Xfp_file, out_path, fastphase=fastphase, K=5, numit=25)
r_file = out_path + "_rhat.txt"
alpha_file = out_path + "_alphahat.txt"
theta_file = out_path + "_thetahat.txt"
char_file = out_path + "_origchars"
hmm = fp.loadHMM(r_file, alpha_file, theta_file, char_file)
knockoffs = knockoffGenotypes(hmm["r"],
hmm["alpha"],
hmm["theta"],
seed=123)
hmm_hat = fp.loadHMM(r_file,
alpha_file,
theta_file,
char_file,
compact=False)
modelX_hat = models.HMM(hmm_hat["pInit"], hmm_hat["Q"], hmm_hat["pEmit"])
X_new = modelX_hat.sample(n_test)
Xk_new = knockoffs.sample(X_new)
verify_exchangeability(X_new, Xk_new, tolerance=1e-3)
def test_haplotypes_fastphase():
"""
Test whether haplotype knockoffs with HMM fitted by fastPHASE are accurate
"""
p = 10
K = 3
M = 2
n = 1000
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n)
_, Xfp_file = tempfile.mkstemp()
fp.writeXtoInp(X, Xfp_file, phased=True)
fastphase = "fastphase" # Name of fastPhase executable
_, out_path = tempfile.mkstemp()
fp.runFastPhase(Xfp_file,
out_path,
fastphase=fastphase,
phased=True,
K=5,
numit=25)
r_file = out_path + "_rhat.txt"
alpha_file = out_path + "_alphahat.txt"
theta_file = out_path + "_thetahat.txt"
char_file = out_path + "_origchars"
hmm = fp.loadHMM(r_file, alpha_file, theta_file, char_file, phased=True)
knockoffs = knockoffHaplotypes(hmm["r"],
hmm["alpha"],
hmm["theta"],
seed=123)
Xk = knockoffs.sample(X)
verify_exchangeability(X, Xk, tolerance=1e-1)
def test_haplotypes_hmm():
"""
Test whether specialized haplotype knockoff algorithm agrees with special case
"""
p = 10
K = 5
M = 2
n_train = 1000
n_test = 100000
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n_train)
_, Xfp_file = tempfile.mkstemp()
fp.writeXtoInp(X, Xfp_file, phased=True)
fastphase = "fastphase" # Name of fastPhase executable
_, out_path = tempfile.mkstemp()
fp.runFastPhase(Xfp_file,
out_path,
fastphase=fastphase,
phased=True,
K=5,
numit=25)
r_file = out_path + "_rhat.txt"
alpha_file = out_path + "_alphahat.txt"
theta_file = out_path + "_thetahat.txt"
char_file = out_path + "_origchars"
groups = np.repeat(np.arange(p), 3)[:p]
hmm_compact = fp.loadHMM(r_file, alpha_file, theta_file, char_file)
hmm = fp.loadHMM(r_file,
alpha_file,
theta_file,
char_file,
compact=False,
phased=True)
knockoffs = knockoffHMM(hmm["pInit"],
hmm["Q"],
hmm["pEmit"],
groups=groups,
seed=123)
knockoffs_hap = knockoffHaplotypes(hmm_compact["r"], hmm_compact["alpha"], hmm_compact["theta"], \
groups=groups, seed=123)
hmm_hat = fp.loadHMM(r_file,
alpha_file,
theta_file,
char_file,
compact=False,
phased=True)
Xk = knockoffs.sample(X)
Xk_compact = knockoffs_hap.sample(X)
assert np.array_equal(
Xk, Xk_compact), "Knockoffs with trivial groups do not match"
def test_HMM():
"""
Test whether the HMM knockoff generation is correct
"""
p = 10
K = 4
M = 5
n = 100000
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n)
knockoffs = knockoffHMM(pInit, Q, pEmit, seed=123)
Xk = knockoffs.sample(X)
verify_exchangeability(X, Xk)
def test_HMM_groups():
"""
Test whether the HMM knockoff generation is correct
"""
p = 10
K = 4
M = 5
n = 100000
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n)
groups = np.repeat(np.arange(p), 3)[:p]
knockoffs = knockoffHMM(pInit, Q, pEmit, groups=groups, seed=123)
Xk = knockoffs.sample(X)
verify_exchangeability(X, Xk, groups=groups)
def __init__(self,
num_samples,
num_dim,
num_hidden_states,
num_emission_states=3,
**sampler_x_args):
self.n_samples = num_samples
self.dim = num_dim
self.n_hidden_states = num_hidden_states
self.n_emission_states = num_emission_states
self.parameters = sample_parameters(self.dim, self.n_hidden_states,
self.n_emission_states)
self.modelX = models.HMM(self.parameters['pInit'],
self.parameters['Q'],
self.parameters['pEmit'])
self.sample()
def test_HMM_basic():
"""
Test whether the HMM knockoff generation function does not crash
"""
p = 50
K = 4
M = 5
n = 100
pInit, Q, pEmit = generate_HMM(p, K, M)
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n)
knockoffs = knockoffHMM(pInit, Q, pEmit, seed=123)
Xk = knockoffs.sample(X)
groups = np.arange(p)
knockoffs_g = knockoffHMM(pInit, Q, pEmit, groups=groups, seed=123)
Xk_g = knockoffs_g.sample(X)
assert np.array_equal(Xk,
Xk_g), "Knockoffs with trivial groups do not match"
assert np.isfinite(Xk).all(), "Knockoffs are not finite"
pEmit = np.zeros((p,M,K))
gamma = np.random.uniform(low=0, high=10, size=p)
for j in range(p-1):
Q[j,:,:] = np.resize(np.random.uniform(size=K*K),(K,K))
Q[j,:,:] += np.diag([gamma[j]]*K)
Q[j,:,:] /= np.sum(Q[j,:,:],1)[:,None]
for j in range(p):
pEmit[j,:,:] = np.resize(np.random.uniform(size=M*K),(M,K))
pEmit[j,:,:] += np.diag([gamma[j]]*K)
pEmit[j,:,:] /= np.sum(pEmit[j,:,:],0)
pInit = np.zeros((K,))
pInit[0] = 1
# Sample X
n=10000
modelX = models.HMM(pInit, Q, pEmit)
X = modelX.sample(n)
# Generate the knockoffs
knockoffs = knockoffHMM(pInit, Q, pEmit)
Xk = knockoffs.sample(X)
# Plot paths
util.plotPaths(X,Xk)
# Compare original variables and knockoffs
util.compare_marginals(X,Xk)
util.compare_cons_corr(X,Xk)
util.compare_cross_corr(X,Xk)
util.compare_cross_corr(X,Xk,dist=0)
from SNPknock.fastphase import loadHMM
from SNPknock import models
from SNPknock import knockoffHMM, knockoffHaplotypes, knockoffGenotypes
import util, pdb
# Load HMM
r_file = "data/haplotypes_rhat.txt"
alpha_file = "data/haplotypes_alphahat.txt"
theta_file = "data/haplotypes_thetahat.txt"
char_file = "data/haplotypes_origchars"
hmm = loadHMM(r_file, alpha_file, theta_file, char_file, compact=True)
hmm_full = loadHMM(r_file, alpha_file, theta_file, char_file, compact=False)
# Sample X
n = 10
modelX = models.HMM(hmm_full['pInit'], hmm_full['Q'], hmm_full['pEmit'])
X = modelX.sample(n)
# Generate the knockoffs
#knockoffs = knockoffHMM(hmm_full['pInit'], hmm_full['Q'], hmm_full['pEmit'])
#Xk = knockoffs.sample(X)
#print("Generated knockoffs")
# Generate the knockoffs (genotypes)
knockoffs_gen = knockoffGenotypes(hmm['r'], hmm['alpha'], hmm['theta'])
Xk = knockoffs_gen.sample(X)
print("Generated knockoffs (genotypes)")
# Generate the knockoffs (haplotypes)
H = X
H[X == 2] = 1
