def _remma_epiDD_eff(y, xmat, zmat, gmat_lst, var_com, bed_file, snp_lst_0=None, var_app=1.0, p_cut=1.0e-5, out_file='epiDD_eff'):
"""
Estimate dominance by dominance epistasis effects by random SNP-BLUP model.
:param y: phenotypic vector
:param xmat: Designed matrix for fixed effect
:param zmat: csr sparse matrix. Designed matrix for random effect.
:param gmat_lst: A list for relationship matrix
:param var_com: Estimated variances
:param bed_file: the prefix for plink binary file
:param snp_lst_0: the first SNP list for the SNP pairs. the min value is 0 and the max value is num_snp-2. The
default value is None, which means list [0, num_snp-1)
:param var_app: the approximate variances for estimated SNP effects.
:param p_cut: put cut value. default value is 1.0e-5.
:param out_file: output file. default value is 'remma_epiDD_eff'.
:return: 0
"""
logging.info("Calculate the phenotypic covariance matrix and inversion")
y = np.array(y).reshape(-1, 1)
n = y.shape[0]
xmat = np.array(xmat).reshape(n, -1)
vmat = np.diag([var_com[-1]] * n)
for val in range(len(gmat_lst)):
vmat += zmat.dot((zmat.dot(gmat_lst[val])).T) * var_com[val]
del gmat_lst
gc.collect()
vmat_inv = np.linalg.inv(vmat)
logging.info("Calculate P matrix")
vxmat = np.dot(vmat_inv, xmat)
xvxmat = np.dot(xmat.T, vxmat)
xvxmat = np.linalg.inv(xvxmat)
pmat = reduce(np.dot, [vxmat, xvxmat, vxmat.T])
pmat = vmat_inv - pmat
pymat = zmat.T.dot(np.dot(pmat, y))
del vmat, vmat_inv, pmat
gc.collect()
num_snp = pd.read_csv(bed_file+'.bim', header=None).shape[0]
num_id = pd.read_csv(bed_file+'.fam', header=None).shape[0]
if snp_lst_0 is None:
snp_lst_0 = range(num_snp - 1)
else:
if max(snp_lst_0) >= num_snp - 1 or min(snp_lst_0) < 0:
logging.error('snp_lst_0 is out of range!')
sys.exit()
logging.info("Convert python variates to C type")
pbed_file = ffi.new("char[]", bed_file.encode('ascii'))
pnum_id = ffi.cast("long long", num_id)
pnum_snp = ffi.cast("long long", num_snp)
snp_lst_0 = np.array(list(snp_lst_0), dtype=np.longlong)
psnp_lst_0 = ffi.cast("long long *", snp_lst_0.ctypes.data)
# psnp_lst_0 = ffi.cast("long long *", ffi.from_buffer(snp_lst_0))
plen_snp_lst_0 = ffi.cast("long long", len(snp_lst_0))
ppymat = ffi.cast("double *", pymat.ctypes.data)
chi_cut = chi2.isf(p_cut, 1)
eff_cut = np.sqrt(chi_cut * var_app)
peff_cut = ffi.cast("double", eff_cut)
temp_file = out_file + '.temp'
pout_file = ffi.new("char[]", temp_file.encode('ascii'))
logging.info('Test')
clock_t0 = time.perf_counter()
cpu_t0 = time.process_time()
lib.remma_epiDD_eff_cpu(pbed_file, pnum_id, pnum_snp, psnp_lst_0, plen_snp_lst_0, ppymat, peff_cut, pout_file)
clock_t1 = time.perf_counter()
cpu_t1 = time.process_time()
logging.info("Running time: Clock time, {:.5f} sec; CPU time, {:.5f} sec.".format(clock_t1 - clock_t0, cpu_t1 - cpu_t0))
logging.info('Add the approximate P values')
with open(temp_file) as fin, open(out_file, 'w') as fout:
head_line = fin.readline()
head_line = head_line.strip()
head_line += ' chi_app p_app\n'
fout.write(head_line)
for line in fin:
arr = line.split()
chi_app = float(arr[-1]) * float(arr[-1]) / var_app
p_app = chi2.sf(chi_app, 1)
fout.write(' '.join(arr + [str(chi_app), str(p_app)]) + '\n')
os.remove(temp_file)
return 0
def remma_epiAA_eff_cpu_c(y,
xmat,
zmat,
gmat_lst,
var_com,
bed_file,
snp_lst_0=None,
eff_cut=-999.0,
out_file='remma_epiAA_eff_cpu_c'):
"""
加加上位检验
:param y: 表型
:param xmat: 固定效应设计矩阵
:param zmat: 随机效应设计矩阵，csr稀疏矩阵
:param gmat_lst: 基因组关系矩阵列表
:param var_com: 方差组分
:param bed_file: plink文件
:param snp_lst_0: 互作对第一个SNP列表，最大值为num_snp-2，最小值为0
:param eff_cut: 依据阈值保留的互作对
:param out_file: 输出文件
:return:
"""
logging.info("计算V矩阵及其逆矩阵")
y = np.array(y).reshape(-1, 1)
n = y.shape[0]
xmat = np.array(xmat).reshape(n, -1)
vmat = np.diag([var_com[-1]] * n)
for val in range(len(gmat_lst)):
vmat += zmat.dot((zmat.dot(gmat_lst[val])).T) * var_com[val]
del gmat_lst
gc.collect()
vmat_inv = np.linalg.inv(vmat)
logging.info("计算P矩阵")
vxmat = np.dot(vmat_inv, xmat)
xvxmat = np.dot(xmat.T, vxmat)
xvxmat = np.linalg.inv(xvxmat)
pmat = reduce(np.dot, [vxmat, xvxmat, vxmat.T])
pmat = vmat_inv - pmat
pymat = zmat.T.dot(np.dot(pmat, y))
del vmat, vmat_inv, pmat
gc.collect()
num_snp = pd.read_csv(bed_file + '.bim', header=None).shape[0]
num_id = pd.read_csv(bed_file + '.fam', header=None).shape[0]
if snp_lst_0 is None:
snp_lst_0 = range(num_snp - 1)
else:
if max(snp_lst_0) >= num_snp - 1 or min(snp_lst_0) < 0:
logging.error('snp_lst_0 is out of range!')
sys.exit()
logging.info("python变量转化到C")
pbed_file = ffi.new("char[]", bed_file.encode('ascii'))
pnum_id = ffi.cast("long long", num_id)
pnum_snp = ffi.cast("long long", num_snp)
snp_lst_0 = np.array(list(snp_lst_0), dtype=np.longlong)
psnp_lst_0 = ffi.cast("long long *", snp_lst_0.ctypes.data)
# psnp_lst_0 = ffi.cast("long long *", ffi.from_buffer(snp_lst_0))
plen_snp_lst_0 = ffi.cast("long long", len(snp_lst_0))
ppymat = ffi.cast("double *", pymat.ctypes.data)
peff_cut = ffi.cast("double", eff_cut)
pout_file = ffi.new("char[]", out_file.encode('ascii'))
logging.info('检验')
clock_t0 = time.perf_counter()
cpu_t0 = time.process_time()
lib.remma_epiAA_eff_cpu(pbed_file, pnum_id, pnum_snp, psnp_lst_0,
plen_snp_lst_0, ppymat, peff_cut, pout_file)
clock_t1 = time.perf_counter()
cpu_t1 = time.process_time()
logging.info(
"Running time: Clock time, {:.5f} sec; CPU time, {:.5f} sec.".format(
clock_t1 - clock_t0, cpu_t1 - cpu_t0))
return 0
