def dowork(self, i, train_snp_idx, test_snp_idx, result, G, y):
logging.info("{0}, {1}".format(len(train_snp_idx), len(test_snp_idx)))
# intersect selected SNPs with train snps
if not self.selected_snps is None:
# intersect snp names
logging.info("intersecting train snps with selected snps for LOCO")
int_snp_idx = argintersect_left(self.snp_reader.rs[train_snp_idx],
self.selected_snps)
sim_keeper_idx = np.array(train_snp_idx)[int_snp_idx]
else:
sim_keeper_idx = train_snp_idx
# subset data
# fast indexing (needs to be C-order)
assert np.isfortran(G) == False
#G_train = G.take(train_snp_idx, axis=1)
G_sim = G.take(sim_keeper_idx, axis=1)
G_test = G.take(test_snp_idx, axis=1)
t0 = time.time()
if self.num_pcs == 0:
pcs = None
else:
if not self.pc_prefix is None:
out_fn = PrecomputeLocoPcs.create_out_fn(self.pc_prefix, i)
logging.info("loading pc from file: %s" % out_fn)
pcs = load(out_fn)[:, 0:self.num_pcs]
logging.info("..done")
else:
assert False, "please precompute PCs"
logging.info("done after %.4f seconds" % (time.time() - t0))
# only use PCs
if self.pcs_only:
G_sim = None
logging.info("Using PCs only in LocoGWAS")
gwas = FastGwas(G_sim,
G_test,
y,
self.delta,
train_pcs=pcs,
mixing=self.mixing)
gwas.run_gwas()
assert len(gwas.p_values) == len(test_snp_idx)
# wrap up results
return test_snp_idx, gwas.p_values, result
def execute_fs(test_snps, pheno, G0, covar):
"""
run feature selection
"""
result = {}
fs_result = {}
# fs unconditioned
########################
tmp_uuid = str(uuid.uuid4())[0:13]
out_fn = "tmp_pheno_%s.txt" % (tmp_uuid)
out_data = pd.DataFrame({
"id1": G0.iid[:, 0],
"id2": G0.iid[:, 1],
"y": pheno["vals"]
})
out_data.to_csv(out_fn, sep=" ", header=False, index=False)
# write out covariates
items = [
('id1', G0.iid[:, 0]),
('id2', G0.iid[:, 1]),
]
items += [("pc_%i" % i, covar["vals"][:, i])
for i in xrange(covar["vals"].shape[1])]
cov_df = pd.DataFrame.from_items(items)
cov_fn = "tmp_cov_%s.txt" % (tmp_uuid)
cov_df.to_csv(cov_fn, sep=" ", header=False, index=False)
#TODO: fix include_all!!
fsd = create_feature_selection_distributable(G0,
out_fn,
None,
0,
"fs_out",
include_all=False,
cov_fn=cov_fn)
fs_result["result_uncond_all"] = Local().run(fsd)
best_k, best_delta, best_obj, best_snps = fs_result["result_uncond_all"]
fs_idx = argintersect_left(G0.sid, best_snps)
G_fs = G0[:, fs_idx]
result["fs_all"] = single_snp(test_snps, pheno,
G0=G_fs).sort(["Chr", "ChrPos"
])["PValue"].as_matrix()
result["fs_all_cov"] = single_snp(
test_snps, pheno, G0=G_fs,
covar=covar).sort(["Chr", "ChrPos"])["PValue"].as_matrix()
return result, fs_result
def dowork(self, i, train_snp_idx, test_snp_idx, result, G, y):
logging.info("{0}, {1}".format(len(train_snp_idx), len(test_snp_idx)))
# intersect selected SNPs with train snps
if not self.selected_snps is None:
# intersect snp names
logging.info("intersecting train snps with selected snps for LOCO")
int_snp_idx = argintersect_left(self.snp_reader.rs[train_snp_idx], self.selected_snps)
sim_keeper_idx = np.array(train_snp_idx)[int_snp_idx]
else:
sim_keeper_idx = train_snp_idx
# subset data
# fast indexing (needs to be C-order)
assert np.isfortran(G) == False
#G_train = G.take(train_snp_idx, axis=1)
G_sim = G.take(sim_keeper_idx, axis=1)
G_test = G.take(test_snp_idx, axis=1)
t0 = time.time()
if self.num_pcs == 0:
pcs = None
else:
if not self.pc_prefix is None:
out_fn = PrecomputeLocoPcs.create_out_fn(self.pc_prefix, i)
logging.info("loading pc from file: %s" % out_fn)
pcs = load(out_fn)[:,0:self.num_pcs]
logging.info("..done")
else:
assert False, "please precompute PCs"
logging.info("done after %.4f seconds" % (time.time() - t0))
# only use PCs
if self.pcs_only:
G_sim = None
logging.info("Using PCs only in LocoGWAS")
gwas = FastGwas(G_sim, G_test, y, self.delta, train_pcs=pcs, mixing=self.mixing)
gwas.run_gwas()
assert len(gwas.p_values) == len(test_snp_idx)
# wrap up results
return test_snp_idx, gwas.p_values, result
def execute_fs(test_snps, pheno, G0, covar):
"""
run feature selection
"""
result = {}
fs_result = {}
# fs unconditioned
########################
tmp_uuid = str(uuid.uuid4())[0:13]
out_fn = "tmp_pheno_%s.txt" % (tmp_uuid)
out_data = pd.DataFrame({"id1": G0.iid[:,0], "id2": G0.iid[:,1], "y": pheno["vals"]})
out_data.to_csv(out_fn, sep=" ", header=False, index=False)
# write out covariates
items = [
('id1', G0.iid[:,0]),
('id2', G0.iid[:,1]),
]
items += [("pc_%i" % i, covar["vals"][:,i]) for i in xrange(covar["vals"].shape[1])]
cov_df = pd.DataFrame.from_items(items)
cov_fn = "tmp_cov_%s.txt" % (tmp_uuid)
cov_df.to_csv(cov_fn, sep=" ", header=False, index=False)
#TODO: fix include_all!!
fsd = create_feature_selection_distributable(G0, out_fn, None, 0, "fs_out", include_all=False, cov_fn=cov_fn)
fs_result["result_uncond_all"] = Local().run(fsd)
best_k, best_delta, best_obj, best_snps = fs_result["result_uncond_all"]
fs_idx = argintersect_left(G0.sid, best_snps)
G_fs = G0[:,fs_idx]
result["fs_all"] = single_snp(test_snps, pheno, G0=G_fs).sort(["Chr", "ChrPos"])["PValue"].as_matrix()
result["fs_all_cov"] = single_snp(test_snps, pheno, G0=G_fs, covar=covar).sort(["Chr", "ChrPos"])["PValue"].as_matrix()
return result, fs_result
