def multiple_loci_mixed_model_gwas(phenotype_id=5, pvalue_file_prefix='mlmm_results',
result_files_prefix='mlmm_manhattan', max_num_steps=10, snp_priors=None):
"""
Perform multiple loci mixed model GWAS for flowering time (phenotype_id=5 in the phenotype file)
in plants grown under 10C conditions.
"""
import linear_models as lm
import kinship
# Load genotypes
sd = load_a_thaliana_genotypes()
# Load phenotypes
phend = load_a_thaliana_phenotypes()
# Coordinate phenotype of interest and genotypes. This filters the genotypes and
# phenotypes, leaving only accessions (individuals) which overlap between both,
# and SNPs that are polymorphic in the resulting subset.
sd.coordinate_w_phenotype_data(phend, phenotype_id)
# Calculate kinship (IBS)
K = kinship.calc_ibs_kinship(sd.get_snps())
# Perform multiple loci mixed model GWAS
mlmm_results = lm.mlmm(phend.get_values(phenotype_id), K, sd=sd,
num_steps=max_num_steps, file_prefix=result_files_prefix,
save_pvals=True, pval_file_prefix=result_files_prefix, snp_priors=snp_priors)
def multiple_loci_mixed_model_gwas(phenotype_id=5,
pvalue_file_prefix='mlmm_results',
result_files_prefix='mlmm_manhattan',
max_num_steps=10,
snp_priors=None):
"""
Perform multiple loci mixed model GWAS for flowering time (phenotype_id=5 in the phenotype file)
in plants grown under 10C conditions.
"""
import linear_models as lm
import kinship
# Load genotypes
sd = load_a_thaliana_genotypes()
# Load phenotypes
phend = load_a_thaliana_phenotypes()
# Coordinate phenotype of interest and genotypes. This filters the genotypes and
# phenotypes, leaving only accessions (individuals) which overlap between both,
# and SNPs that are polymorphic in the resulting subset.
sd.coordinate_w_phenotype_data(phend, phenotype_id)
# Calculate kinship (IBS)
K = kinship.calc_ibs_kinship(sd.get_snps())
# Perform multiple loci mixed model GWAS
mlmm_results = lm.mlmm(phend.get_values(phenotype_id),
K,
sd=sd,
num_steps=max_num_steps,
file_prefix=result_files_prefix,
save_pvals=True,
pval_file_prefix=result_files_prefix,
snp_priors=snp_priors)
def get_ibs_kinship_matrix(self, debug_filter=1, snp_dtype='int8', dtype='single',chunk_size=None):
"""
Calculate the IBS kinship matrix.
(un-scaled)
Currently it works only for binary kinship matrices.
"""
log.debug('Starting kinship calculation')
return kinship.calc_ibs_kinship(self,chunk_size=chunk_size)
def get_ibs_kinship_matrix(self, debug_filter=1, snp_dtype='int8', dtype='single',chunk_size=None):
"""
Calculate the IBS kinship matrix.
(un-scaled)
Currently it works only for binary kinship matrices.
"""
log.debug('Starting kinship calculation')
return kinship.calc_ibs_kinship(self,chunk_size=chunk_size)
def mixed_model_gwas(phenotype_id=5,
pvalue_file='mm_results.pvals',
manhattan_plot_file='mm_manhattan.png',
qq_plot_file_prefix='mm_qq'):
"""
Perform mixed model (EMMAX) GWAS for flowering time (phenotype_id=5 in the phenotype file)
in plants grown under 10C conditions.
"""
import linear_models as lm
import kinship
import gwaResults as gr
# Load genotypes
sd = load_a_thaliana_genotypes()
# Load phenotypes
phend = load_a_thaliana_phenotypes()
# Coordinate phenotype of interest and genotypes. This filters the genotypes and
# phenotypes, leaving only accessions (individuals) which overlap between both,
# and SNPs that are polymorphic in the resulting subset.
sd.coordinate_w_phenotype_data(phend, phenotype_id)
# Calculate kinship (IBS)
K = kinship.calc_ibs_kinship(sd.get_snps())
# Perform mixed model GWAS
mm_results = lm.emmax(sd.get_snps(), phend.get_values(phenotype_id), K)
# Construct a results object
res = gr.Result(scores=mm_results['ps'], snps_data=sd)
# Save p-values to file
res.write_to_file(pvalue_file)
# Plot Manhattan plot
res.plot_manhattan(png_file=manhattan_plot_file,
percentile=90,
plot_bonferroni=True,
neg_log_transform=True)
# Plot a QQ-plot
res.plot_qq(qq_plot_file_prefix)
def lotus_mixed_model_gwas(phenotype_id=4, phen_file = '/home/bjarni/LotusGenome/cks/Lotus31012019/20181113_136LjAccessionData.csv',
gt_file = '/home/bjarni/LotusGenome/cks/Lotus31012019/all_chromosomes_binary.csv',
pvalue_file='mm_results.pvals', manhattan_plot_file='mm_manhattan.png', qq_plot_file_prefix='mm_qq'):
"""
Perform mixed model (EMMAX) GWAS for Lotus data
"""
import linear_models as lm
import kinship
import gwaResults as gr
import dataParsers as dp
# Load genotypes
sd = dp.parse_snp_data(gt_file)
# Load phenotypes
import phenotypeData as pd
phend = pd.parse_phenotype_file(phen_file, with_db_ids=False)
# Coordinate phenotype of interest and genotypes. This filters the genotypes and
# phenotypes, leaving only accessions (individuals) which overlap between both,
# and SNPs that are polymorphic in the resulting subset.
sd.coordinate_w_phenotype_data(phend, phenotype_id)
# Calculate kinship (IBS)
K = kinship.calc_ibs_kinship(sd.get_snps())
# Perform mixed model GWAS
mm_results = lm.emmax(sd.get_snps(), phend.get_values(phenotype_id), K)
# Construct a results object
res = gr.Result(scores=mm_results['ps'], snps_data=sd)
# Save p-values to file
res.write_to_file(pvalue_file)
# Plot Manhattan plot
res.plot_manhattan(png_file=manhattan_plot_file, percentile=90, plot_bonferroni=True,
neg_log_transform=True)
# Plot a QQ-plot
res.plot_qq(qq_plot_file_prefix)
def mixed_model_gwas(phenotype_id=5, pvalue_file='mm_results.pvals',
manhattan_plot_file='mm_manhattan.png',
qq_plot_file_prefix='mm_qq'):
"""
Perform mixed model (EMMAX) GWAS for flowering time (phenotype_id=5 in the phenotype file)
in plants grown under 10C conditions.
"""
import linear_models as lm
import kinship
import gwaResults as gr
# Load genotypes
sd = load_a_thaliana_genotypes()
# Load phenotypes
phend = load_a_thaliana_phenotypes()
# Coordinate phenotype of interest and genotypes. This filters the genotypes and
# phenotypes, leaving only accessions (individuals) which overlap between both,
# and SNPs that are polymorphic in the resulting subset.
sd.coordinate_w_phenotype_data(phend, phenotype_id)
# Calculate kinship (IBS)
K = kinship.calc_ibs_kinship(sd.get_snps())
# Perform mixed model GWAS
mm_results = lm.emmax(sd.get_snps(), phend.get_values(phenotype_id), K)
# Construct a results object
res = gr.Result(scores=mm_results['ps'], snps_data=sd)
# Save p-values to file
res.write_to_file(pvalue_file)
# Plot Manhattan plot
res.plot_manhattan(png_file=manhattan_plot_file, percentile=90, plot_bonferroni=True,
neg_log_transform=True)
# Plot a QQ-plot
res.plot_qq(qq_plot_file_prefix)
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))