def precompute_pca(self):
"""
compute pcs
"""
logging.info("computing PCA on train set")
t0 = time.time()
if not os.path.isfile(self.eigen_fn) or self.force_recompute:
G = self.snp_reader.read(order='C').standardize().val
G.flags.writeable = False
chr1_idx, chr2_idx, rest_idx = split_data_helper.split_chr1_chr2_rest(self.snp_reader.pos)
G_train = G.take(rest_idx, axis=1)
from sklearn.decomposition import PCA
pca = PCA()
pcs = pca.fit_transform(G_train)
logging.info("saving eigendecomp to file %s" % self.eigen_fn)
eig_dec = {"pcs": pcs}
save(self.eigen_fn, eig_dec)
logging.info("time taken for pc computation: " + str(time.time()-t0))
else:
logging.info("pc file already exists: %s" % (self.eigen_fn))
def precompute_pca(self):
"""
compute pcs
"""
logging.info("computing PCA on train set")
t0 = time.time()
if not os.path.isfile(self.eigen_fn) or self.force_recompute:
G = self.snp_reader.read(order='C').standardize().val
G.flags.writeable = False
chr1_idx, chr2_idx, rest_idx = split_data_helper.split_chr1_chr2_rest(
self.snp_reader.pos)
G_train = G.take(rest_idx, axis=1)
from sklearn.decomposition import PCA
pca = PCA()
pcs = pca.fit_transform(G_train)
logging.info("saving eigendecomp to file %s" % self.eigen_fn)
eig_dec = {"pcs": pcs}
save(self.eigen_fn, eig_dec)
logging.info("time taken for pc computation: " +
str(time.time() - t0))
else:
logging.info("pc file already exists: %s" % (self.eigen_fn))
def compute_core(input_tuple):
"""
Leave-two-chromosome-out evaluation scheme:
Chr1: no causals, used for T1-error evaluation
Chr2: has causals, not conditioned on, used for power evaluation
Rest: has causals, conditioned on
T1 Pow [ cond ]
===== ===== ===== .... =====
x x x x xx
"""
methods, snp_fn, eigen_fn, num_causal, num_pcs, seed, sim_id = input_tuple
# partially load bed file
from pysnptools.snpreader import Bed
snp_reader = Bed(snp_fn)
# determine indices for generation and evaluation
##################################################################
chr1_idx, chr2_idx, rest_idx = split_data_helper.split_chr1_chr2_rest(snp_reader.pos)
causal_candidates_idx = np.concatenate((chr2_idx, rest_idx))
# only compute t1-error (condition on all chr with causals on them)
#causal_candidates_idx = rest_idx
test_idx = np.concatenate((chr1_idx, chr2_idx))
if seed is not None:
np.random.seed(int(seed % sys.maxint))
causal_idx = np.random.permutation(causal_candidates_idx)[0:num_causal]
# generate phenotype
###################################################################
genetic_var = 0.5
noise_var = 0.5
y = generate_phenotype(Bed(snp_fn).read(order='C').standardize(), causal_idx, genetic_var, noise_var)
y.flags.writeable = False
############### only alter part until here --> modularize this
# load pcs
###################################################################
logging.info("loading eigendecomp from file %s" % eigen_fn)
eig_dec = load(eigen_fn)
G_pc = eig_dec["pcs"]
G_pc.flags.writeable = False
G_pc_ = G_pc[:,0:num_pcs]
G_pc_norm = DiagKtoN(G_pc_.shape[0]).standardize(G_pc_.copy())
G_pc_norm.flags.writeable = False
# run feature selection
#########################################################
# generate pheno data structure
pheno = {"iid": snp_reader.iid, "vals": y, "header": []}
covar = {"iid": snp_reader.iid, "vals": G_pc_norm, "header": []}
# subset readers
G0 = snp_reader[:,rest_idx]
test_snps = snp_reader[:,test_idx]
result = {}
fs_result = {}
# additional methods can be defined and included in the benchmark
for method_function in methods:
result_, fs_result_ = method_function(test_snps, pheno, G0, covar)
result.update(result_)
fs_result.update(fs_result_)
# save indices
indices = {"causal_idx": causal_idx, "chr1_idx": chr1_idx, "chr2_idx": chr2_idx, "input_tuple": input_tuple, "fs_result": fs_result}
#test_idx
return result, indices
def compute_core(input_tuple):
"""
Leave-two-chromosome-out evaluation scheme:
Chr1: no causals, used for T1-error evaluation
Chr2: has causals, not conditioned on, used for power evaluation
Rest: has causals, conditioned on
T1 Pow [ cond ]
===== ===== ===== .... =====
x x x x xx
"""
methods, snp_fn, eigen_fn, num_causal, num_pcs, seed, sim_id = input_tuple
# partially load bed file
from pysnptools.snpreader import Bed
snp_reader = Bed(snp_fn)
# determine indices for generation and evaluation
##################################################################
chr1_idx, chr2_idx, rest_idx = split_data_helper.split_chr1_chr2_rest(
snp_reader.pos)
causal_candidates_idx = np.concatenate((chr2_idx, rest_idx))
# only compute t1-error (condition on all chr with causals on them)
#causal_candidates_idx = rest_idx
test_idx = np.concatenate((chr1_idx, chr2_idx))
if seed is not None:
np.random.seed(int(seed % sys.maxint))
causal_idx = np.random.permutation(causal_candidates_idx)[0:num_causal]
# generate phenotype
###################################################################
genetic_var = 0.5
noise_var = 0.5
y = generate_phenotype(
Bed(snp_fn).read(order='C').standardize(), causal_idx, genetic_var,
noise_var)
y.flags.writeable = False
############### only alter part until here --> modularize this
# load pcs
###################################################################
logging.info("loading eigendecomp from file %s" % eigen_fn)
eig_dec = load(eigen_fn)
G_pc = eig_dec["pcs"]
G_pc.flags.writeable = False
G_pc_ = G_pc[:, 0:num_pcs]
G_pc_norm = DiagKtoN(G_pc_.shape[0]).standardize(G_pc_.copy())
G_pc_norm.flags.writeable = False
# run feature selection
#########################################################
# generate pheno data structure
pheno = {"iid": snp_reader.iid, "vals": y, "header": []}
covar = {"iid": snp_reader.iid, "vals": G_pc_norm, "header": []}
# subset readers
G0 = snp_reader[:, rest_idx]
test_snps = snp_reader[:, test_idx]
result = {}
fs_result = {}
# additional methods can be defined and included in the benchmark
for method_function in methods:
result_, fs_result_ = method_function(test_snps, pheno, G0, covar)
result.update(result_)
fs_result.update(fs_result_)
# save indices
indices = {
"causal_idx": causal_idx,
"chr1_idx": chr1_idx,
"chr2_idx": chr2_idx,
"input_tuple": input_tuple,
"fs_result": fs_result
}
#test_idx
return result, indices