def _test_():
singleton_snps = genotypes.simulate_k_tons(n=500, m=1000)
doubleton_snps = genotypes.simulate_k_tons(k=2, n=500, m=1000)
common_snps = genotypes.simulate_common_genotypes(500, 1000)
snps = sp.vstack([common_snps, singleton_snps, doubleton_snps])
print snps
snps = snps.T
snps = (snps - sp.mean(snps, 0)) / sp.std(snps, 0)
snps = snps.T
print snps, snps.shape
file_prefix = os.environ['HOME'] + '/tmp/test'
phen_list = phenotypes.simulate_traits_w_snps_to_hdf5(snps, hdf5_file_prefix=file_prefix,
num_traits=30, p=0.1)
singletons_thres = []
doubletons_thres = []
common_thres = []
for i, y in enumerate(phen_list['phenotypes']):
K = kinship.calc_ibd_kinship(snps)
K = kinship.scale_k(K)
lmm = lm.LinearMixedModel(y)
lmm.add_random_effect(K)
r1 = lmm.get_REML()
print 'pseudo_heritability:', r1['pseudo_heritability']
ex_res = lm.emmax(snps, y, K)
plt.figure()
plt.hist(y, 50)
plt.savefig('%s_%d_phen.png' % (file_prefix, i))
plt.clf()
agr.plot_simple_qqplots_pvals('%s_%d' % (file_prefix, i),
[ex_res['ps'][:1000], ex_res['ps'][1000:2000], ex_res['ps'][2000:]],
result_labels=['Common SNPs', 'Singletons', 'Doubletons'],
line_colors=['b', 'r', 'y'],
num_dots=200, max_neg_log_val=3)
# Cholesky permutations..
res = lm.emmax_perm_test(singleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
singletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(doubleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
doubletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(common_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
common_thres.append(res['threshold_05'][0])
#ATT permutations (Implement)
#PC permutations (Implement)
print sp.mean(singletons_thres), sp.std(singletons_thres)
print sp.mean(doubletons_thres), sp.std(doubletons_thres)
print sp.mean(common_thres), sp.std(common_thres)
def _test_scz_():
# Load Schizophrenia data
singleton_snps = genotypes.simulate_k_tons(n=500, m=1000)
doubleton_snps = genotypes.simulate_k_tons(k=2, n=500, m=1000)
common_snps = genotypes.simulate_common_genotypes(500, 1000)
snps = sp.vstack([common_snps, singleton_snps, doubleton_snps])
test_snps = sp.vstack([singleton_snps, doubleton_snps])
print snps
phen_list = phenotypes.simulate_traits(
snps, hdf5_file_prefix='/home/bv25/tmp/test', num_traits=30, p=1.0)
singletons_thres = []
doubletons_thres = []
common_thres = []
for i, y in enumerate(phen_list):
K = kinship.calc_ibd_kinship(snps)
K = kinship.scale_k(K)
lmm = lm.LinearMixedModel(y)
lmm.add_random_effect(K)
r1 = lmm.get_REML()
print 'pseudo_heritability:', r1['pseudo_heritability']
ex_res = lm.emmax(snps, y, K)
plt.figure()
plt.hist(y, 50)
plt.savefig('/home/bv25/tmp/test_%d_phen.png' % i)
plt.clf()
agr.plot_simple_qqplots_pvals('/home/bv25/tmp/test_%d' % i, [
ex_res['ps'][:1000], ex_res['ps'][1000:2000], ex_res['ps'][2000:]
],
result_labels=[
'Common SNPs', 'Singletons',
'Doubletons'
],
line_colors=['b', 'r', 'y'],
num_dots=200,
max_neg_log_val=3)
# Now permutations..
res = lm.emmax_perm_test(singleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
singletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(doubleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
doubletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(common_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
common_thres.append(res['threshold_05'][0])
print sp.mean(singletons_thres), sp.std(singletons_thres)
print sp.mean(doubletons_thres), sp.std(doubletons_thres)
print sp.mean(common_thres), sp.std(common_thres)
def _test_scz_():
# Load Schizophrenia data
singleton_snps = genotypes.simulate_k_tons(n=500, m=1000)
doubleton_snps = genotypes.simulate_k_tons(k=2, n=500, m=1000)
common_snps = genotypes.simulate_common_genotypes(500, 1000)
snps = sp.vstack([common_snps, singleton_snps, doubleton_snps])
test_snps = sp.vstack([singleton_snps, doubleton_snps])
print snps
phen_list = phenotypes.simulate_traits(snps, hdf5_file_prefix='/home/bv25/tmp/test', num_traits=30, p=1.0)
singletons_thres = []
doubletons_thres = []
common_thres = []
for i, y in enumerate(phen_list):
K = kinship.calc_ibd_kinship(snps)
K = kinship.scale_k(K)
lmm = lm.LinearMixedModel(y)
lmm.add_random_effect(K)
r1 = lmm.get_REML()
print 'pseudo_heritability:', r1['pseudo_heritability']
ex_res = lm.emmax(snps, y, K)
plt.figure()
plt.hist(y, 50)
plt.savefig('/home/bv25/tmp/test_%d_phen.png' % i)
plt.clf()
agr.plot_simple_qqplots_pvals('/home/bv25/tmp/test_%d' % i,
[ex_res['ps'][:1000], ex_res['ps'][1000:2000], ex_res['ps'][2000:]],
result_labels=['Common SNPs', 'Singletons', 'Doubletons'],
line_colors=['b', 'r', 'y'],
num_dots=200, max_neg_log_val=3)
# Now permutations..
res = lm.emmax_perm_test(singleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
singletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(doubleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
doubletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(common_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
common_thres.append(res['threshold_05'][0])
print sp.mean(singletons_thres), sp.std(singletons_thres)
print sp.mean(doubletons_thres), sp.std(doubletons_thres)
print sp.mean(common_thres), sp.std(common_thres)
def perform_cegs_gwas(kinship_type='ibd', phen_type='medians'):
"""
Perform a simple MLM GWAS for the 8 traits
"""
import hdf5_data
import kinship
import linear_models as lm
import time
import scipy as sp
from matplotlib import pyplot as plt
import analyze_gwas_results as agr
phen_dict = hdf5_data.parse_cegs_drosophila_phenotypes()
phenotypes = ['Protein', 'Sugar', 'Triglyceride', 'weight']
envs = ['mated', 'virgin']
for phenotype in phenotypes:
for env in envs:
print phenotype, env
s1 = time.time()
d = hdf5_data.coordinate_cegs_genotype_phenotype(
phen_dict, phenotype, env)
print 'Calculating kinship'
if kinship_type == 'ibs':
K = kinship.calc_ibs_kinship(d['snps'])
elif kinship_type == 'ibd':
K = kinship.calc_ibd_kinship(d['snps'])
else:
raise NotImplemented
if phen_type == 'means':
lmm = lm.LinearMixedModel(d['Y_means'])
elif phen_type == 'medians':
lmm = lm.LinearMixedModel(d['Y_medians'])
else:
raise NotImplementedError
lmm.add_random_effect(K)
print "Running EMMAX"
res = lmm.emmax_f_test(d['snps'], emma_num=1000)
print 'Mean p-value:', sp.mean(res['ps'])
secs = time.time() - s1
if secs > 60:
mins = int(secs) / 60
secs = secs - mins * 60
print 'Took %d mins and %f seconds.' % (mins, secs)
else:
print 'Took %f seconds.' % (secs)
#Now generating QQ-plots
label_str = '%s_%s_%s_%s' % (kinship_type, phenotype, env,
phen_type)
agr.plot_simple_qqplots_pvals(
'/Users/bjarnivilhjalmsson/data/tmp/cegs_qq_%s' % (label_str),
[res['ps']],
result_labels=[label_str],
line_colors=['green'],
num_dots=1000,
title=None,
max_neg_log_val=6)
# Perform multiple loci mixed model GWAS
chromosomes = d['positions'][:, 0]
positions = sp.array(d['positions'][:, 1], 'int32')
x_positions = []
y_log_pvals = []
colors = []
x_shift = 0
for i, chrom in enumerate(sp.unique(chromosomes)):
if chrom in ['2L', '2LHet', '3L', '3LHet', '4', 'X', 'XHet']:
colors.append('c')
else: # chrom in ['2R', '2RHet', '3R', '3RHet', 'U', 'Uextra']
#Toss U and Hets
colors.append('m')
chrom_filter = sp.in1d(chromosomes, chrom)
positions_slice = positions[chrom_filter]
x_positions.append(positions_slice + x_shift)
x_shift += positions_slice.max()
log_ps_slice = -sp.log10(res['ps'][chrom_filter])
y_log_pvals.append(log_ps_slice)
m = len(positions)
log_bonf = -sp.log10(1 / (20.0 * m))
print m, log_bonf
# Plot manhattan plots?
plt.figure(figsize=(12, 4))
plt.axes([0.03, 0.1, 0.95, 0.8])
for i, chrom in enumerate(sp.unique(chromosomes)):
plt.plot(x_positions[i],
y_log_pvals[i],
c=colors[i],
ls='',
marker='.')
xmin, xmax = plt.xlim()
plt.hlines(log_bonf,
xmin,
xmax,
colors='k',
linestyles='--',
alpha=0.5)
plt.title('%s, %s' % (phenotype, env))
plt.savefig(
'/Users/bjarnivilhjalmsson/data/tmp/cegs_gwas_%s_%s_%s_%s.png'
% (kinship_type, phenotype, env, phen_type))
def perform_cegs_gwas(kinship_type='ibd', phen_type='medians'):
"""
Perform a simple MLM GWAS for the 8 traits
"""
import hdf5_data
import kinship
import linear_models as lm
import time
import scipy as sp
from matplotlib import pyplot as plt
import analyze_gwas_results as agr
phen_dict = hdf5_data.parse_cegs_drosophila_phenotypes()
phenotypes = ['Protein', 'Sugar', 'Triglyceride', 'weight']
envs = ['mated', 'virgin']
for phenotype in phenotypes:
for env in envs:
print phenotype, env
s1 = time.time()
d = hdf5_data.coordinate_cegs_genotype_phenotype(
phen_dict, phenotype, env)
print 'Calculating kinship'
if kinship_type == 'ibs':
K = kinship.calc_ibs_kinship(d['snps'])
elif kinship_type == 'ibd':
K = kinship.calc_ibd_kinship(d['snps'])
else:
raise NotImplementedError
if phen_type == 'means':
lmm = lm.LinearMixedModel(d['Y_means'])
elif phen_type == 'medians':
lmm = lm.LinearMixedModel(d['Y_medians'])
else:
raise NotImplementedError
lmm.add_random_effect(K)
print "Running EMMAX"
res = lmm.emmax_f_test(d['snps'], emma_num=1000)
print 'Mean p-value:', sp.mean(res['ps'])
secs = time.time() - s1
if secs > 60:
mins = int(secs) / 60
secs = secs - mins * 60
print 'Took %d mins and %f seconds.' % (mins, secs)
else:
print 'Took %f seconds.' % (secs)
# Now generating QQ-plots
label_str = '%s_%s_%s_%s' % (
kinship_type, phenotype, env, phen_type)
agr.plot_simple_qqplots_pvals('/Users/bjarnivilhjalmsson/data/tmp/cegs_qq_%s' % (label_str),
[res['ps']], result_labels=[
label_str], line_colors=['green'],
num_dots=1000, title=None, max_neg_log_val=6)
# Perform multiple loci mixed model GWAS
chromosomes = d['positions'][:, 0]
positions = sp.array(d['positions'][:, 1], 'int32')
x_positions = []
y_log_pvals = []
colors = []
x_shift = 0
for i, chrom in enumerate(sp.unique(chromosomes)):
if chrom in ['2L', '2LHet', '3L', '3LHet', '4', 'X', 'XHet']:
colors.append('c')
else: # chrom in ['2R', '2RHet', '3R', '3RHet', 'U', 'Uextra']
# Toss U and Hets
colors.append('m')
chrom_filter = sp.in1d(chromosomes, chrom)
positions_slice = positions[chrom_filter]
x_positions.append(positions_slice + x_shift)
x_shift += positions_slice.max()
log_ps_slice = -sp.log10(res['ps'][chrom_filter])
y_log_pvals.append(log_ps_slice)
m = len(positions)
log_bonf = -sp.log10(1 / (20.0 * m))
print m, log_bonf
# Plot manhattan plots?
plt.figure(figsize=(12, 4))
plt.axes([0.03, 0.1, 0.95, 0.8])
for i, chrom in enumerate(sp.unique(chromosomes)):
plt.plot(x_positions[i], y_log_pvals[i],
c=colors[i], ls='', marker='.')
xmin, xmax = plt.xlim()
plt.hlines(log_bonf, xmin, xmax, colors='k',
linestyles='--', alpha=0.5)
plt.title('%s, %s' % (phenotype, env))
plt.savefig('/Users/bjarnivilhjalmsson/data/tmp/cegs_gwas_%s_%s_%s_%s.png' %
(kinship_type, phenotype, env, phen_type))
def _test_():
singleton_snps = genotypes.simulate_k_tons(n=500, m=1000)
doubleton_snps = genotypes.simulate_k_tons(k=2, n=500, m=1000)
common_snps = genotypes.simulate_common_genotypes(500, 1000)
snps = sp.vstack([common_snps, singleton_snps, doubleton_snps])
print snps
snps = snps.T
snps = (snps - sp.mean(snps, 0)) / sp.std(snps, 0)
snps = snps.T
print snps, snps.shape
file_prefix = os.environ['HOME'] + '/tmp/test'
phen_list = phenotypes.simulate_traits_w_snps_to_hdf5(
snps, hdf5_file_prefix=file_prefix, num_traits=30, p=0.1)
singletons_thres = []
doubletons_thres = []
common_thres = []
for i, y in enumerate(phen_list['phenotypes']):
K = kinship.calc_ibd_kinship(snps)
K = kinship.scale_k(K)
lmm = lm.LinearMixedModel(y)
lmm.add_random_effect(K)
r1 = lmm.get_REML()
print 'pseudo_heritability:', r1['pseudo_heritability']
ex_res = lm.emmax(snps, y, K)
plt.figure()
plt.hist(y, 50)
plt.savefig('%s_%d_phen.png' % (file_prefix, i))
plt.clf()
agr.plot_simple_qqplots_pvals('%s_%d' % (file_prefix, i), [
ex_res['ps'][:1000], ex_res['ps'][1000:2000], ex_res['ps'][2000:]
],
result_labels=[
'Common SNPs', 'Singletons',
'Doubletons'
],
line_colors=['b', 'r', 'y'],
num_dots=200,
max_neg_log_val=3)
# Cholesky permutations..
res = lm.emmax_perm_test(singleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
singletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(doubleton_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
doubletons_thres.append(res['threshold_05'][0])
res = lm.emmax_perm_test(common_snps, y, K, num_perm=1000)
print 1.0 / (20 * 1000.0), res['threshold_05']
common_thres.append(res['threshold_05'][0])
#ATT permutations (Implement)
#PC permutations (Implement)
print sp.mean(singletons_thres), sp.std(singletons_thres)
print sp.mean(doubletons_thres), sp.std(doubletons_thres)
print sp.mean(common_thres), sp.std(common_thres)
