def get_herit_dict(df,
eff_type,
n,
h2,
use_gw_h2=False,
ld_dict=None,
summary_dict=None,
debug=False):
if eff_type != 'BLUP':
ld_scores_dict = ld_dict['ld_scores_dict']
cord_data_g = df['cord_data']
#Calculating genome-wide heritability using LD score regression, and partition heritability by chromsomes
return ld.get_chromosome_herits(cord_data_g,
ld_scores_dict,
n,
h2=h2,
use_gw_h2=use_gw_h2,
summary_dict=summary_dict,
debug=debug)
else:
raise NotImplementedError
def test_get_chromosome_herits(self):
p_dict = make_p_dict(
'--debug',
'inf',
'--cf=%s/test_data/goldens/golden.coord.hdf5' % TEST_DIR,
'--ldr=100',
'--ldf=' + self.tmp_file_prefix,
'--N=10000',
'--out=' + self.tmp_file_prefix,
)
summary_dict = {}
ld_dict = ld.get_ld_dict_using_p_dict(p_dict, summary_dict)
coord_file = os.path.join(TEST_DIR,
'test_data/goldens/golden.coord.hdf5')
df = h5py.File(coord_file, 'r')
herit_dict = ld.get_chromosome_herits(df['cord_data'],
ld_dict['ld_scores_dict'],
n=p_dict['N'],
h2=None)
print(herit_dict)
self.assertAlmostEqual(herit_dict['chrom_1'], 0.0741219)
self.assertAlmostEqual(herit_dict['gw_h2_ld_score_est'], 0.0741219)
def ldpred_genomewide(data_file=None,
ld_radius=None,
ld_dict=None,
out_file_prefix=None,
summary_dict=None,
ps=None,
n=None,
h2=None,
num_iter=None,
verbose=False,
zero_jump_prob=0.05,
burn_in=5):
"""
Calculate LDpred for a genome
"""
df = h5py.File(data_file, 'r')
has_phenotypes = False
if 'y' in df:
'Validation phenotypes found.'
y = df['y'][...] # Phenotype
num_individs = len(y)
risk_scores_pval_derived = sp.zeros(num_individs)
has_phenotypes = True
ld_scores_dict = ld_dict['ld_scores_dict']
chrom_ld_dict = ld_dict['chrom_ld_dict']
chrom_ref_ld_mats = ld_dict['chrom_ref_ld_mats']
print('Applying LDpred with LD radius: %d' % ld_radius)
results_dict = {}
cord_data_g = df['cord_data']
#Calculating genome-wide heritability using LD score regression, and partition heritability by chromsomes
herit_dict = ld.get_chromosome_herits(cord_data_g,
ld_scores_dict,
n,
h2=h2,
debug=verbose,
summary_dict=summary_dict)
LDpred_inf_chrom_dict = {}
print('Calculating LDpred-inf weights')
for chrom_str in util.chromosomes_list:
if chrom_str in cord_data_g:
print('Calculating SNP weights for Chromosome %s' %
((chrom_str.split('_'))[1]))
g = cord_data_g[chrom_str]
# Filter monomorphic SNPs
snp_stds = g['snp_stds_ref'][...]
snp_stds = snp_stds.flatten()
ok_snps_filter = snp_stds > 0
pval_derived_betas = g['betas'][...]
pval_derived_betas = pval_derived_betas[ok_snps_filter]
h2_chrom = herit_dict[chrom_str]
start_betas = LDpred_inf.ldpred_inf(
pval_derived_betas,
genotypes=None,
reference_ld_mats=chrom_ref_ld_mats[chrom_str],
h2=h2_chrom,
n=n,
ld_window_size=2 * ld_radius,
verbose=False)
LDpred_inf_chrom_dict[chrom_str] = start_betas
convergence_report = {}
for p in ps:
convergence_report[p] = False
print('Starting LDpred gibbs with f=%0.4f' % p)
p_str = '%0.4f' % p
results_dict[p_str] = {}
if out_file_prefix:
# Preparing output files
raw_effect_sizes = []
ldpred_effect_sizes = []
ldpred_inf_effect_sizes = []
out_sids = []
chromosomes = []
out_positions = []
out_nts = []
chrom_i = 0
num_chrom = len(util.chromosomes_list)
for chrom_str in util.chromosomes_list:
chrom_i += 1
if chrom_str in cord_data_g:
g = cord_data_g[chrom_str]
if verbose and has_phenotypes:
if 'raw_snps_val' in g:
raw_snps = g['raw_snps_val'][...]
else:
raw_snps = g['raw_snps_ref'][...]
# Filter monomorphic SNPs
snp_stds = g['snp_stds_ref'][...]
snp_stds = snp_stds.flatten()
pval_derived_betas = g['betas'][...]
positions = g['positions'][...]
sids = (g['sids'][...]).astype(util.sids_u_dtype)
log_odds = g['log_odds'][...]
nts = (g['nts'][...]).astype(util.nts_u_dtype)
ok_snps_filter = snp_stds > 0
if not sp.all(ok_snps_filter):
snp_stds = snp_stds[ok_snps_filter]
pval_derived_betas = pval_derived_betas[ok_snps_filter]
positions = positions[ok_snps_filter]
sids = sids[ok_snps_filter]
log_odds = log_odds[ok_snps_filter]
nts = nts[ok_snps_filter]
if verbose and has_phenotypes:
raw_snps = raw_snps[ok_snps_filter]
if out_file_prefix:
chromosomes.extend([chrom_str] * len(pval_derived_betas))
out_positions.extend(positions)
out_sids.extend(sids)
raw_effect_sizes.extend(log_odds)
out_nts.extend(nts)
h2_chrom = herit_dict[chrom_str]
if 'chrom_ld_boundaries' in ld_dict:
ld_boundaries = ld_dict['chrom_ld_boundaries'][chrom_str]
res_dict = ldpred_gibbs(
pval_derived_betas,
h2=h2_chrom,
n=n,
p=p,
ld_radius=ld_radius,
verbose=verbose,
num_iter=num_iter,
burn_in=burn_in,
ld_dict=chrom_ld_dict[chrom_str],
start_betas=LDpred_inf_chrom_dict[chrom_str],
ld_boundaries=ld_boundaries,
zero_jump_prob=zero_jump_prob)
else:
res_dict = ldpred_gibbs(
pval_derived_betas,
h2=h2_chrom,
n=n,
p=p,
ld_radius=ld_radius,
verbose=verbose,
num_iter=num_iter,
burn_in=burn_in,
ld_dict=chrom_ld_dict[chrom_str],
start_betas=LDpred_inf_chrom_dict[chrom_str],
zero_jump_prob=zero_jump_prob)
updated_betas = res_dict['betas']
updated_inf_betas = res_dict['inf_betas']
sum_sqr_effects = sp.sum(updated_betas**2)
if sum_sqr_effects > herit_dict['gw_h2_ld_score_est']:
print(
'Sum of squared updated effects estimates seems too large: %0.4f'
% sum_sqr_effects)
print(
'This suggests that the Gibbs sampler did not convergence.'
)
convergence_report[p] = True
if verbose:
print('Calculating SNP weights for Chromosome %s' %
((chrom_str.split('_'))[1]))
else:
sys.stdout.write('\b\b\b\b\b\b\b%0.2f%%' %
(100.0 *
(min(1,
float(chrom_i + 1) / num_chrom))))
sys.stdout.flush()
updated_betas = updated_betas / (snp_stds.flatten())
updated_inf_betas = updated_inf_betas / (snp_stds.flatten())
ldpred_effect_sizes.extend(updated_betas)
ldpred_inf_effect_sizes.extend(updated_inf_betas)
if verbose and has_phenotypes:
prs = sp.dot(updated_betas, raw_snps)
risk_scores_pval_derived += prs
corr = sp.corrcoef(y, prs)[0, 1]
r2 = corr**2
print(
'The R2 prediction accuracy of PRS using %s was: %0.4f'
% (chrom_str, r2))
if verbose and has_phenotypes:
num_indivs = len(y)
results_dict[p_str]['y'] = y
results_dict[p_str]['risk_scores_pd'] = risk_scores_pval_derived
print('Prediction accuracy was assessed using %d individuals.' %
(num_indivs))
corr = sp.corrcoef(y, risk_scores_pval_derived)[0, 1]
r2 = corr**2
results_dict[p_str]['r2_pd'] = r2
print(
'The R2 prediction accuracy (observed scale) for the whole genome was: %0.4f (%0.6f)'
% (r2, ((1 - r2)**2) / num_indivs))
if corr < 0:
risk_scores_pval_derived = -1 * risk_scores_pval_derived
auc = util.calc_auc(y, risk_scores_pval_derived)
print('AUC for the whole genome was: %0.4f' % auc)
# Now calibration
denominator = sp.dot(risk_scores_pval_derived.T,
risk_scores_pval_derived)
y_norm = (y - sp.mean(y)) / sp.std(y)
numerator = sp.dot(risk_scores_pval_derived.T, y_norm)
regression_slope = (numerator / denominator) # [0][0]
print(
'The slope for predictions with P-value derived effects is: %0.4f'
% regression_slope)
results_dict[p_str]['slope_pd'] = regression_slope
weights_out_file = '%s_LDpred_p%0.4e.txt' % (out_file_prefix, p)
with open(weights_out_file, 'w') as f:
f.write(
'chrom pos sid nt1 nt2 raw_beta ldpred_beta\n'
)
for chrom, pos, sid, nt, raw_beta, ldpred_beta in zip(
chromosomes, out_positions, out_sids, out_nts,
raw_effect_sizes, ldpred_effect_sizes):
nt1, nt2 = nt[0], nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n' %
(chrom, pos, sid, nt1, nt2, raw_beta, ldpred_beta))
weights_out_file = '%s_LDpred-inf.txt' % (out_file_prefix)
with open(weights_out_file, 'w') as f:
f.write(
'chrom pos sid nt1 nt2 raw_beta ldpred_inf_beta \n'
)
for chrom, pos, sid, nt, raw_beta, ldpred_inf_beta in zip(
chromosomes, out_positions, out_sids, out_nts,
raw_effect_sizes, ldpred_inf_effect_sizes):
nt1, nt2 = nt[0], nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n' %
(chrom, pos, sid, nt1, nt2, raw_beta, ldpred_inf_beta))
summary_dict[2.0] = {
'name': 'Gibbs sampler fractions used',
'value': str(ps)
}
['Yes' if convergence_report[p] else 'No' for p in ps]
summary_dict[2.1] = {
'name': 'Convergence issues (for each fraction)',
'value': str(['Yes' if convergence_report[p] else 'No' for p in ps])
}
def ldpred_inf_genomewide(data_file=None, ld_radius = None, ld_dict=None, out_file_prefix=None,
n=None, h2=None, verbose=False):
"""
Calculate LDpred for a genome
"""
df = h5py.File(data_file,'r')
has_phenotypes=False
if 'y' in df:
'Validation phenotypes found.'
y = df['y'][...] # Phenotype
num_individs = len(y)
risk_scores_pval_derived = sp.zeros(num_individs)
has_phenotypes=True
ld_scores_dict = ld_dict['ld_scores_dict']
chrom_ref_ld_mats = ld_dict['chrom_ref_ld_mats']
print('Applying LDpred-inf with LD radius: %d' % ld_radius)
results_dict = {}
cord_data_g = df['cord_data']
#Calculating genome-wide heritability using LD score regression, and partition heritability by chromsomes
herit_dict = ld.get_chromosome_herits(cord_data_g, ld_scores_dict, n, h2=h2)
if out_file_prefix:
#Preparing output files
raw_effect_sizes = []
ldpred_effect_sizes = []
sids = []
chromosomes = []
positions = []
nts = []
for chrom_str in util.chromosomes_list:
if chrom_str in cord_data_g:
g = cord_data_g[chrom_str]
if has_phenotypes:
if 'raw_snps_val' in g:
raw_snps = g['raw_snps_val'][...]
else:
raw_snps = g['raw_snps_ref'][...]
snp_stds = g['snp_stds_ref'][...]
pval_derived_betas = g['betas'][...]
if out_file_prefix:
chromosomes.extend([chrom_str]*len(pval_derived_betas))
positions.extend(g['positions'][...])
sids_arr = (g['sids'][...]).astype(util.sids_u_dtype)
sids.extend(sids_arr)
raw_effect_sizes.extend(g['log_odds'][...])
nts_arr = (g['nts'][...]).astype(util.nts_u_dtype)
nts.extend(nts_arr)
h2_chrom = herit_dict[chrom_str]
updated_betas = ldpred_inf(pval_derived_betas, genotypes=None, reference_ld_mats=chrom_ref_ld_mats[chrom_str],
h2=h2_chrom, n=n, ld_window_size=2*ld_radius, verbose=False)
print('Calculating scores for Chromosome %s'%((chrom_str.split('_'))[1]))
updated_betas = updated_betas / (snp_stds.flatten())
ldpred_effect_sizes.extend(updated_betas)
if has_phenotypes:
prs = sp.dot(updated_betas, raw_snps)
risk_scores_pval_derived += prs
corr = sp.corrcoef(y, prs)[0, 1]
r2 = corr ** 2
print('The R2 prediction accuracy of PRS using %s was: %0.4f' %(chrom_str, r2))
if has_phenotypes:
num_indivs = len(y)
results_dict['y']=y
results_dict['risk_scores_pd']=risk_scores_pval_derived
print('Prediction accuracy was assessed using %d individuals.'%(num_indivs))
corr = sp.corrcoef(y, risk_scores_pval_derived)[0, 1]
r2 = corr ** 2
results_dict['r2_pd']=r2
print('The R2 prediction accuracy (observed scale) for the whole genome was: %0.4f (%0.6f)' % (r2, ((1-r2)**2)/num_indivs))
if corr<0:
risk_scores_pval_derived = -1* risk_scores_pval_derived
auc = util.calc_auc(y,risk_scores_pval_derived)
print('AUC for the whole genome was: %0.4f'%auc)
#Now calibration
denominator = sp.dot(risk_scores_pval_derived.T, risk_scores_pval_derived)
y_norm = (y-sp.mean(y))/sp.std(y)
numerator = sp.dot(risk_scores_pval_derived.T, y_norm)
regression_slope = (numerator / denominator)
print('The slope for predictions with P-value derived effects is: %0.4f'%regression_slope)
results_dict['slope_pd']=regression_slope
weights_out_file = '%s.txt'%(out_file_prefix)
with open(weights_out_file,'w') as f:
f.write('chrom pos sid nt1 nt2 raw_beta ldpred_inf_beta\n')
for chrom, pos, sid, nt, raw_beta, ldpred_beta in zip(chromosomes, positions, sids, nts, raw_effect_sizes, ldpred_effect_sizes):
nt1,nt2 = nt[0],nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n'%(chrom, pos, sid, nt1, nt2, raw_beta, ldpred_beta))
def ldpred_genomewide(data_file=None, ld_radius=None, ld_dict=None, out_file_prefix=None,
summary_dict=None, ps=None,
n=None, h2=None, num_iter=None,
verbose=False, zero_jump_prob=0.05, burn_in=5):
"""
Calculate LDpred for a genome
"""
df = h5py.File(data_file, 'r')
has_phenotypes = False
if 'y' in df:
'Validation phenotypes found.'
y = df['y'][...] # Phenotype
num_individs = len(y)
risk_scores_pval_derived = sp.zeros(num_individs)
has_phenotypes = True
ld_scores_dict = ld_dict['ld_scores_dict']
chrom_ld_dict = ld_dict['chrom_ld_dict']
chrom_ref_ld_mats = ld_dict['chrom_ref_ld_mats']
print('Applying LDpred with LD radius: %d' % ld_radius)
results_dict = {}
cord_data_g = df['cord_data']
#Calculating genome-wide heritability using LD score regression, and partition heritability by chromsomes
herit_dict = ld.get_chromosome_herits(cord_data_g, ld_scores_dict, n, h2=h2, debug=verbose,summary_dict=summary_dict)
LDpred_inf_chrom_dict = {}
print('Calculating LDpred-inf weights')
for chrom_str in util.chromosomes_list:
if chrom_str in cord_data_g:
print('Calculating SNP weights for Chromosome %s' % ((chrom_str.split('_'))[1]))
g = cord_data_g[chrom_str]
# Filter monomorphic SNPs
snp_stds = g['snp_stds_ref'][...]
snp_stds = snp_stds.flatten()
ok_snps_filter = snp_stds > 0
pval_derived_betas = g['betas'][...]
pval_derived_betas = pval_derived_betas[ok_snps_filter]
h2_chrom = herit_dict[chrom_str]
start_betas = LDpred_inf.ldpred_inf(pval_derived_betas, genotypes=None, reference_ld_mats=chrom_ref_ld_mats[chrom_str],
h2=h2_chrom, n=n, ld_window_size=2 * ld_radius, verbose=False)
LDpred_inf_chrom_dict[chrom_str] = start_betas
convergence_report = {}
for p in ps:
convergence_report[p] = False
print('Starting LDpred gibbs with f=%0.4f' % p)
p_str = '%0.4f' % p
results_dict[p_str] = {}
if out_file_prefix:
# Preparing output files
raw_effect_sizes = []
ldpred_effect_sizes = []
ldpred_inf_effect_sizes = []
out_sids = []
chromosomes = []
out_positions = []
out_nts = []
chrom_i = 0
num_chrom = len(util.chromosomes_list)
for chrom_str in util.chromosomes_list:
chrom_i+=1
if chrom_str in cord_data_g:
g = cord_data_g[chrom_str]
if verbose and has_phenotypes:
if 'raw_snps_val' in g:
raw_snps = g['raw_snps_val'][...]
else:
raw_snps = g['raw_snps_ref'][...]
# Filter monomorphic SNPs
snp_stds = g['snp_stds_ref'][...]
snp_stds = snp_stds.flatten()
pval_derived_betas = g['betas'][...]
positions = g['positions'][...]
sids = (g['sids'][...]).astype(util.sids_u_dtype)
log_odds = g['log_odds'][...]
nts = (g['nts'][...]).astype(util.nts_u_dtype)
ok_snps_filter = snp_stds > 0
if not sp.all(ok_snps_filter):
snp_stds = snp_stds[ok_snps_filter]
pval_derived_betas = pval_derived_betas[ok_snps_filter]
positions = positions[ok_snps_filter]
sids = sids[ok_snps_filter]
log_odds = log_odds[ok_snps_filter]
nts = nts[ok_snps_filter]
if verbose and has_phenotypes:
raw_snps = raw_snps[ok_snps_filter]
if out_file_prefix:
chromosomes.extend([chrom_str] * len(pval_derived_betas))
out_positions.extend(positions)
out_sids.extend(sids)
raw_effect_sizes.extend(log_odds)
out_nts.extend(nts)
h2_chrom = herit_dict[chrom_str]
if 'chrom_ld_boundaries' in ld_dict:
ld_boundaries = ld_dict['chrom_ld_boundaries'][chrom_str]
res_dict = ldpred_gibbs(pval_derived_betas, h2=h2_chrom, n=n, p=p, ld_radius=ld_radius,
verbose=verbose, num_iter=num_iter, burn_in=burn_in, ld_dict=chrom_ld_dict[chrom_str],
start_betas=LDpred_inf_chrom_dict[chrom_str], ld_boundaries=ld_boundaries,
zero_jump_prob=zero_jump_prob,
print_progress=False)
else:
res_dict = ldpred_gibbs(pval_derived_betas, h2=h2_chrom, n=n, p=p, ld_radius=ld_radius,
verbose=verbose, num_iter=num_iter, burn_in=burn_in, ld_dict=chrom_ld_dict[chrom_str],
start_betas=LDpred_inf_chrom_dict[chrom_str], zero_jump_prob=zero_jump_prob,
print_progress=False)
updated_betas = res_dict['betas']
updated_inf_betas = res_dict['inf_betas']
sum_sqr_effects = sp.sum(updated_betas ** 2)
if sum_sqr_effects > herit_dict['gw_h2_ld_score_est']:
print('Sum of squared updated effects estimates seems too large: %0.4f'% sum_sqr_effects)
print('This suggests that the Gibbs sampler did not convergence.')
convergence_report[p] = True
if verbose:
print('Calculating SNP weights for Chromosome %s' % ((chrom_str.split('_'))[1]))
else:
sys.stdout.write('\b\b\b\b\b\b\b%0.2f%%' % (100.0 * (min(1, float(chrom_i + 1) / num_chrom))))
sys.stdout.flush()
updated_betas = updated_betas / (snp_stds.flatten())
updated_inf_betas = updated_inf_betas / (snp_stds.flatten())
ldpred_effect_sizes.extend(updated_betas)
ldpred_inf_effect_sizes.extend(updated_inf_betas)
if verbose and has_phenotypes:
prs = sp.dot(updated_betas, raw_snps)
risk_scores_pval_derived += prs
corr = sp.corrcoef(y, prs)[0, 1]
r2 = corr ** 2
print('The R2 prediction accuracy of PRS using %s was: %0.4f' % (chrom_str, r2))
if not verbose:
sys.stdout.write('\b\b\b\b\b\b\b%0.2f%%\n' % (100.0))
sys.stdout.flush()
if verbose and has_phenotypes:
num_indivs = len(y)
results_dict[p_str]['y'] = y
results_dict[p_str]['risk_scores_pd'] = risk_scores_pval_derived
print('Prediction accuracy was assessed using %d individuals.' % (num_indivs))
corr = sp.corrcoef(y, risk_scores_pval_derived)[0, 1]
r2 = corr ** 2
results_dict[p_str]['r2_pd'] = r2
print('The R2 prediction accuracy (observed scale) for the whole genome was: %0.4f (%0.6f)' % (r2, ((1 - r2) ** 2) / num_indivs))
if corr < 0:
risk_scores_pval_derived = -1 * risk_scores_pval_derived
auc = util.calc_auc(y, risk_scores_pval_derived)
print('AUC for the whole genome was: %0.4f' % auc)
# Now calibration
denominator = sp.dot(risk_scores_pval_derived.T, risk_scores_pval_derived)
y_norm = (y - sp.mean(y)) / sp.std(y)
numerator = sp.dot(risk_scores_pval_derived.T, y_norm)
regression_slope = (numerator / denominator) # [0][0]
print('The slope for predictions with P-value derived effects is: %0.4f' % regression_slope)
results_dict[p_str]['slope_pd'] = regression_slope
weights_out_file = '%s_LDpred_p%0.4e.txt' % (out_file_prefix, p)
with open(weights_out_file, 'w') as f:
f.write('chrom pos sid nt1 nt2 raw_beta ldpred_beta\n')
for chrom, pos, sid, nt, raw_beta, ldpred_beta in zip(chromosomes, out_positions, out_sids, out_nts, raw_effect_sizes, ldpred_effect_sizes):
nt1, nt2 = nt[0], nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n' % (chrom, pos, sid, nt1, nt2, raw_beta, ldpred_beta))
weights_out_file = '%s_LDpred-inf.txt' % (out_file_prefix)
with open(weights_out_file, 'w') as f:
f.write('chrom pos sid nt1 nt2 raw_beta ldpred_inf_beta \n')
for chrom, pos, sid, nt, raw_beta, ldpred_inf_beta in zip(chromosomes, out_positions, out_sids, out_nts, raw_effect_sizes, ldpred_inf_effect_sizes):
nt1, nt2 = nt[0], nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n' % (chrom, pos, sid, nt1, nt2, raw_beta, ldpred_inf_beta))
summary_dict[2.0]={'name':'Gibbs sampler fractions used','value':str(ps)}
['Yes' if convergence_report[p] else 'No' for p in ps]
summary_dict[2.1]={'name':'Convergence issues (for each fraction)','value':str(['Yes' if convergence_report[p] else 'No' for p in ps])}
def ldpred_inf_genomewide(data_file=None, ld_radius = None, ld_dict=None, out_file_prefix=None,
n=None, h2=None, verbose=False):
"""
Calculate LDpred for a genome
"""
df = h5py.File(data_file,'r')
has_phenotypes=False
if 'y' in df:
'Validation phenotypes found.'
y = df['y'][...] # Phenotype
num_individs = len(y)
risk_scores_pval_derived = sp.zeros(num_individs)
has_phenotypes=True
ld_scores_dict = ld_dict['ld_scores_dict']
chrom_ref_ld_mats = ld_dict['chrom_ref_ld_mats']
print('Applying LDpred-inf with LD radius: %d' % ld_radius)
results_dict = {}
cord_data_g = df['cord_data']
#Calculating genome-wide heritability using LD score regression, and partition heritability by chromsomes
herit_dict = ld.get_chromosome_herits(cord_data_g, ld_scores_dict, n, h2=h2)
if out_file_prefix:
#Preparing output files
raw_effect_sizes = []
ldpred_effect_sizes = []
sids = []
chromosomes = []
positions = []
nts = []
for chrom_str in util.chromosomes_list:
if chrom_str in cord_data_g:
g = cord_data_g[chrom_str]
if has_phenotypes:
if 'raw_snps_val' in g:
raw_snps = g['raw_snps_val'][...]
else:
raw_snps = g['raw_snps_ref'][...]
snp_stds = g['snp_stds_ref'][...]
pval_derived_betas = g['betas'][...]
if out_file_prefix:
chromosomes.extend([chrom_str]*len(pval_derived_betas))
positions.extend(g['positions'][...])
sids_arr = (g['sids'][...]).astype(util.sids_u_dtype)
sids.extend(sids_arr)
raw_effect_sizes.extend(g['log_odds'][...])
nts_arr = (g['nts'][...]).astype(util.nts_u_dtype)
nts.extend(nts_arr)
h2_chrom = herit_dict[chrom_str]
updated_betas = ldpred_inf(pval_derived_betas, genotypes=None, reference_ld_mats=chrom_ref_ld_mats[chrom_str],
h2=h2_chrom, n=n, ld_window_size=2*ld_radius, verbose=False)
print('Calculating scores for Chromosome %s'%((chrom_str.split('_'))[1]))
updated_betas = updated_betas / (snp_stds.flatten())
ldpred_effect_sizes.extend(updated_betas)
if has_phenotypes:
prs = sp.dot(updated_betas, raw_snps)
risk_scores_pval_derived += prs
corr = sp.corrcoef(y, prs)[0, 1]
r2 = corr ** 2
print('The R2 prediction accuracy of PRS using %s was: %0.4f' %(chrom_str, r2))
if has_phenotypes:
num_indivs = len(y)
results_dict['y']=y
results_dict['risk_scores_pd']=risk_scores_pval_derived
print('Prediction accuracy was assessed using %d individuals.'%(num_indivs))
corr = sp.corrcoef(y, risk_scores_pval_derived)[0, 1]
r2 = corr ** 2
results_dict['r2_pd']=r2
print('The R2 prediction accuracy (observed scale) for the whole genome was: %0.4f (%0.6f)' % (r2, ((1-r2)**2)/num_indivs))
if corr<0:
risk_scores_pval_derived = -1* risk_scores_pval_derived
auc = util.calc_auc(y,risk_scores_pval_derived)
print('AUC for the whole genome was: %0.4f'%auc)
#Now calibration
denominator = sp.dot(risk_scores_pval_derived.T, risk_scores_pval_derived)
y_norm = (y-sp.mean(y))/sp.std(y)
numerator = sp.dot(risk_scores_pval_derived.T, y_norm)
regression_slope = (numerator / denominator)
print('The slope for predictions with P-value derived effects is: %0.4f'%regression_slope)
results_dict['slope_pd']=regression_slope
weights_out_file = '%s.txt'%(out_file_prefix)
with open(weights_out_file,'w') as f:
f.write('chrom pos sid nt1 nt2 raw_beta ldpred_inf_beta\n')
for chrom, pos, sid, nt, raw_beta, ldpred_beta in zip(chromosomes, positions, sids, nts, raw_effect_sizes, ldpred_effect_sizes):
nt1,nt2 = nt[0],nt[1]
f.write('%s %d %s %s %s %0.4e %0.4e\n'%(chrom, pos, sid, nt1, nt2, raw_beta, ldpred_beta))
