def calculate_ld_tables(input_genotype_file, chrom_i, local_ld_hdf5_file, ld_radius,
min_r2=0.2, maf_thres=0.01, indiv_filter=None,
snp_filter=None, return_void=True, verbose=True):
"""
Calculate the LD tables for the given radius, and store in the given file.
"""
if not os.path.isfile(local_ld_hdf5_file):
h5f = h5py.File(input_genotype_file)
print 'Calculating LD information for chromosome %d w. radius %d' % (chrom_i, ld_radius)
g_dict = kgenome.get_genotype_data(h5f, chrom_i, maf_thres, indiv_filter=indiv_filter,
snp_filter=snp_filter, randomize_sign=False, snps_signs=None)
ld_dict = get_ld_table(g_dict['norm_snps'], ld_radius=ld_radius, min_r2=min_r2, verbose=verbose)
ld_dict['avg_ld_score'] = sp.mean(ld_dict['ld_scores'])
print 'Done calculating the LD table and LD score, writing to file:', local_ld_hdf5_file
oh5f = h5py.File(local_ld_hdf5_file, 'w')
hu.dict_to_hdf5(ld_dict, oh5f)
oh5f.close()
print 'LD information is now stored.'
else:
print 'Loading LD information from file: %s' % local_ld_hdf5_file
oh5f = h5py.File(local_ld_hdf5_file, 'r')
ld_dict = hu.hdf5_to_dict(oh5f)
oh5f.close()
if not return_void:
return ld_dict
def get_kinship_pca_dict(input_genotype_file, kinship_pca_file, maf_thres, snp_filter_frac, chrom_ok_snp_dict=None):
if os.path.isfile(kinship_pca_file):
print ':Loading Kinship and PCA information from %s' % kinship_pca_file
k_h5f = h5py.File(kinship_pca_file)
kinship_pca_dict = hu.hdf5_to_dict(k_h5f)
else:
kinship_pca_dict = calc_kinship(input_file=input_genotype_file , out_file=kinship_pca_file,
maf_thres=maf_thres, figure_dir=None, snp_filter_frac=snp_filter_frac,
chrom_ok_snp_dict=chrom_ok_snp_dict)
return kinship_pca_dict
def ld_prune_1k_genotypes(in_hdf5_file, out_hdf5_file, local_ld_file_prefix, ld_radius, max_r2=0.2, maf_thres=0.01, chrom_ok_snp_dict=None):
# Open input and output file
ih5f = h5py.File(in_hdf5_file)
oh5f = h5py.File(out_hdf5_file)
for chrom_i in range(1, 23):
print 'Working on Chromosome %d' % chrom_i
chrom_str = 'chr%d' % chrom_i
g_dict = get_genotype_data(ih5f, chrom_i, maf_thres=maf_thres, randomize_sign=False, snps_signs=None,
return_raw_snps=True, return_snps_info=True, return_normalized_snps=False,
chrom_ok_snp_dict=chrom_ok_snp_dict)
snps = g_dict['snps']
snp_means = g_dict['snp_means']
snp_stds = g_dict['snp_stds']
snp_ids = g_dict['snp_ids']
positions = g_dict['positions']
nts = g_dict['nts']
local_ld_hdf5_file = '%s_chrom%d_ldradius%d.hdf5' % (local_ld_file_prefix, chrom_i, ld_radius)
print 'Loading LD information from file: %s' % local_ld_hdf5_file
ldh5f = h5py.File(local_ld_hdf5_file, 'r')
ld_dict = hu.hdf5_to_dict(ldh5f)
ldh5f.close()
ld_snp_filter = ld.ld_pruning(ld_dict, max_r2=max_r2, verbose=True)
print ld_snp_filter
assert ld_dict['num_snps'] == len(snps)
assert ld_dict['num_snps'] == len(ld_snp_filter)
# Pruning SNPs in LD
snps = snps[ld_snp_filter]
snp_means = snp_means[ld_snp_filter]
snp_stds = snp_stds[ld_snp_filter]
snp_ids = snp_ids[ld_snp_filter]
positions = positions[ld_snp_filter]
nts = nts[ld_snp_filter]
print 'Out of %d SNPs %d were retained' % (ld_dict['num_snps'], len(snps))
cg = oh5f.create_group(chrom_str)
cg.create_dataset('snps', data=sp.array(snps, dtype='int8'))
cg.create_dataset('snp_means', data=snp_means)
cg.create_dataset('snp_stds', data=snp_stds)
cg.create_dataset('snp_ids', data=snp_ids)
cg.create_dataset('positions', data=positions)
cg.create_dataset('nts', data=nts)
indiv_ids = ih5f['indiv_ids'][...]
oh5f.create_dataset('indiv_ids', data=indiv_ids)
ih5f.close()
oh5f.close()
def get_kinship_pca_dict(input_genotype_file,
kinship_pca_file,
maf_thres,
snp_filter_frac,
chrom_ok_snp_dict=None):
if os.path.isfile(kinship_pca_file):
print ':Loading Kinship and PCA information from %s' % kinship_pca_file
k_h5f = h5py.File(kinship_pca_file)
kinship_pca_dict = hu.hdf5_to_dict(k_h5f)
else:
kinship_pca_dict = calc_kinship(input_file=input_genotype_file,
out_file=kinship_pca_file,
maf_thres=maf_thres,
figure_dir=None,
snp_filter_frac=snp_filter_frac,
chrom_ok_snp_dict=chrom_ok_snp_dict)
return kinship_pca_dict
def calculate_ld_tables(input_genotype_file,
chrom_i,
local_ld_hdf5_file,
ld_radius,
min_r2=0.2,
maf_thres=0.01,
indiv_filter=None,
snp_filter=None,
return_void=True,
verbose=True):
"""
Calculate the LD tables for the given radius, and store in the given file.
"""
if not os.path.isfile(local_ld_hdf5_file):
h5f = h5py.File(input_genotype_file)
print 'Calculating LD information for chromosome %d w. radius %d' % (
chrom_i, ld_radius)
g_dict = kgenome.get_genotype_data(h5f,
chrom_i,
maf_thres,
indiv_filter=indiv_filter,
snp_filter=snp_filter,
randomize_sign=False,
snps_signs=None)
ld_dict = get_ld_table(g_dict['norm_snps'],
ld_radius=ld_radius,
min_r2=min_r2,
verbose=verbose)
ld_dict['avg_ld_score'] = sp.mean(ld_dict['ld_scores'])
print 'Done calculating the LD table and LD score, writing to file:', local_ld_hdf5_file
oh5f = h5py.File(local_ld_hdf5_file, 'w')
hu.dict_to_hdf5(ld_dict, oh5f)
oh5f.close()
print 'LD information is now stored.'
else:
print 'Loading LD information from file: %s' % local_ld_hdf5_file
oh5f = h5py.File(local_ld_hdf5_file, 'r')
ld_dict = hu.hdf5_to_dict(oh5f)
oh5f.close()
if not return_void:
return ld_dict
def ld_prune_1k_genotypes(in_hdf5_file,
out_hdf5_file,
local_ld_file_prefix,
ld_radius,
max_r2=0.2,
maf_thres=0.01,
chrom_ok_snp_dict=None):
# Open input and output file
ih5f = h5py.File(in_hdf5_file)
oh5f = h5py.File(out_hdf5_file)
for chrom_i in range(1, 23):
print 'Working on Chromosome %d' % chrom_i
chrom_str = 'chr%d' % chrom_i
g_dict = get_genotype_data(ih5f,
chrom_i,
maf_thres=maf_thres,
randomize_sign=False,
snps_signs=None,
return_raw_snps=True,
return_snps_info=True,
return_normalized_snps=False,
chrom_ok_snp_dict=chrom_ok_snp_dict)
snps = g_dict['snps']
snp_means = g_dict['snp_means']
snp_stds = g_dict['snp_stds']
snp_ids = g_dict['snp_ids']
positions = g_dict['positions']
nts = g_dict['nts']
local_ld_hdf5_file = '%s_chrom%d_ldradius%d.hdf5' % (
local_ld_file_prefix, chrom_i, ld_radius)
print 'Loading LD information from file: %s' % local_ld_hdf5_file
ldh5f = h5py.File(local_ld_hdf5_file, 'r')
ld_dict = hu.hdf5_to_dict(ldh5f)
ldh5f.close()
ld_snp_filter = ld.ld_pruning(ld_dict, max_r2=max_r2, verbose=True)
print ld_snp_filter
assert ld_dict['num_snps'] == len(snps)
assert ld_dict['num_snps'] == len(ld_snp_filter)
# Pruning SNPs in LD
snps = snps[ld_snp_filter]
snp_means = snp_means[ld_snp_filter]
snp_stds = snp_stds[ld_snp_filter]
snp_ids = snp_ids[ld_snp_filter]
positions = positions[ld_snp_filter]
nts = nts[ld_snp_filter]
print 'Out of %d SNPs %d were retained' % (ld_dict['num_snps'],
len(snps))
cg = oh5f.create_group(chrom_str)
cg.create_dataset('snps', data=sp.array(snps, dtype='int8'))
cg.create_dataset('snp_means', data=snp_means)
cg.create_dataset('snp_stds', data=snp_stds)
cg.create_dataset('snp_ids', data=snp_ids)
cg.create_dataset('positions', data=positions)
cg.create_dataset('nts', data=nts)
indiv_ids = ih5f['indiv_ids'][...]
oh5f.create_dataset('indiv_ids', data=indiv_ids)
ih5f.close()
oh5f.close()
