def generate_and_analyze(seed,
N,
do_shuffle,
just_testing=True,
map_function=None,
cache_folder=None):
#Generate SNPs
snpdata = snp_gen(fst=.1,
dfr=0,
iid_count=N,
sid_count=1000,
chr_count=10,
label_with_pop=True,
seed=seed)
K_causal = snpdata.read_kernel(Unit()).standardize()
#Generate geo-spatial locations and K_loc
distance_between_centers = 2500000
x0 = distance_between_centers * 0.5
x1 = distance_between_centers * 1.5
y0 = distance_between_centers
y1 = distance_between_centers
sd = distance_between_centers / 4.
spatial_iid = snpdata.iid
center_dict = {"0": (x0, y0), "1": (x1, y1)}
centers = np.array(
[center_dict[iid_item[0]] for iid_item in spatial_iid])
np.random.seed(seed)
logging.info("Generating positions for seed {0}".format(seed))
spatial_coor = SnpData(
iid=snpdata.iid,
sid=["x", "y"],
val=centers + np.random.multivariate_normal(
[0, 0], [[1, 0], [0, 1]], size=len(centers)) * sd,
parent_string="'spatial_coor_gen_original'")
alpha = distance_between_centers
spatial_val = spatial_similarity(spatial_coor.val, alpha, power=2)
K_loc = KernelData(iid=snpdata.iid, val=spatial_val).standardize()
#Generate phenotype
iid = K_causal.iid
iid_count = K_causal.iid_count
np.random.seed(seed)
pheno_causal = SnpData(iid=iid,
sid=["causal"],
val=np.random.multivariate_normal(
np.zeros(iid_count),
K_causal.val).reshape(-1, 1),
parent_string="causal")
np.random.seed(seed ^ 998372)
pheno_noise = SnpData(iid=iid,
sid=["noise"],
val=np.random.normal(size=iid_count).reshape(
-1, 1),
parent_string="noise")
np.random.seed(seed ^ 12230302)
pheno_loc_original = SnpData(iid=iid,
sid=["loc_original"],
val=np.random.multivariate_normal(
np.zeros(iid_count),
K_loc.val).reshape(-1, 1),
parent_string="loc_original")
if do_shuffle:
idx = np.arange(iid_count)
np.random.seed(seed)
np.random.shuffle(idx)
pheno_loc = pheno_loc_original.read(
view_ok=True
) #don't need to copy, because the next line will be fresh memory
pheno_loc.val = pheno_loc.val[idx, :]
else:
pheno_loc = pheno_loc_original
pheno = SnpData(iid=iid,
sid=["pheno_all"],
val=pheno_causal.val + pheno_noise.val + pheno_loc.val)
#Analyze data
alpha_list = [
int(v) for v in np.logspace(np.log10(100), np.log10(1e10), 100)
]
dataframe = heritability_spatial_correction(
snpdata,
spatial_coor.val,
spatial_iid,
alpha_list=[alpha] if just_testing else alpha_list,
pheno=pheno,
alpha_power=2,
jackknife_count=0,
permute_plus_count=0,
permute_times_count=0,
just_testing=just_testing,
map_function=map_function,
cache_folder=cache_folder)
logging.info(dataframe)
return dataframe
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
do_plot = False
from pysnptools.util import snp_gen
from pysnptools.standardizer import Unit
seed = 0
N = 5000
#Generate SNPs
snpdata = snp_gen(fst=.1,
dfr=0,
iid_count=N,
sid_count=1000,
chr_count=10,
label_with_pop=True,
seed=seed)
K_causal = snpdata.read_kernel(Unit()).standardize()
if do_plot:
pylab.suptitle("$K_{causal}$")
pylab.imshow(K_causal.val, cmap=pylab.gray(), vmin=0, vmax=1)
pylab.show()
import numpy as np
from pysnptools.snpreader import SnpData
distance_between_centers = 2500000
x0 = distance_between_centers * 0.5