def single_validation(fraction=None, test_index=None):
'''Run a single validation experiment with fraction% of deleted test genotypes. Returns a validation
Experiment object.'''
p = im.hutt('hutt.npz')
e = im.v.Experiment(p, fraction=fraction, test_index=test_index)
phaser = im.phase_main.main_phaser(print_times=True)
e.run(phaser)
(_, stats) = im.plots.plot_experiment_stats(e)
print stats[np.argsort(-stats[:, 2] / stats[:, 1]), :]
return e
def single_validation(fraction=None, test_index=None):
'''Run a single validation experiment with fraction% of deleted test genotypes. Returns a validation
Experiment object.'''
p = im.hutt('hutt.npz')
e = im.v.Experiment(p, fraction=fraction, test_index=test_index)
phaser = im.phase_main.main_phaser(print_times=True)
e.run(phaser)
(_, stats) = im.plots.plot_experiment_stats(e)
print stats[np.argsort(-stats[:, 2] / stats[:, 1]), :]
return e
def plot_two_families():
'''Test ancestor imputation and child POO alignment for two families on chromosome 22.'''
# Parameters
chrom = 22
plot = False # True
save_plot = False # True
debug = False # True
# Read data
p = im.hutt('hutt.phased.npz')
q = p.pedigree.quasi_founders
# aligned = set(p.haplotype.aligned_samples)
t = frozenset([frozenset(im.gt.genotyped_children(p, p.pedigree.find_family_by_child(i, genotyped=False))) for i in q])
num_sibs = map(len, t)
print 'Distribution of QF family sizes', util.occur_dict(num_sibs)
# plot_hist_num_sibs(num_sibs)
# ibd = im.index.segment_index.SegmentIndex(os.environ['OBER_OUT'] + '/index_segments')
if plot: P.figure(1)
s = set([x for x in t if 1049 in x][0]) - set([1049])
pa, _ = analyze_family(p, s, max_colors=4, title='Haplotype Coloring: Quasi-Founder Sibs, All, Chrom. %d' % (chrom,), plot=plot, debug=debug)
if save_plot: P.savefig(os.environ['OBER'] + '/doc/poo/qf_family/hap_colors_poo.png')
if plot: P.figure(2)
s2 = set([x for x in t if 1049 in x][0])
analyze_family(p, s2, max_colors=4, title='Haplotype Coloring: Quasi-Founder Sibs, POOC Chrom. %d' % (chrom,), plot=plot, debug=debug)
if save_plot: P.savefig(os.environ['OBER'] + '/doc/poo/qf_family/hap_colors_all.png')
if plot: P.figure(3)
f = p.find_family(10, 1414) # 4 children, genotyped parents
s3 = f.children
analyze_family(p, s3, max_colors=4, title='Haplotype Coloring: Non-Founder Sibs Chrom. %d' % (chrom,), plot=plot, debug=debug)
if save_plot: P.savefig(os.environ['OBER'] + '/doc/poo/nf_family/hap_colors.png')
if plot: P.show()
print im.color.hap_color.best_hap_alignment_to_colors(pa)
print 'Regions', pa.num_regions
print 'Parental haplotype coverage %', parent_coverage_fraction(pa, p)
print 'Children coverage by parental haplotypes', pa.color_sequence_coverage(np.arange(4))
decide whether to genotype them with a dense or sparse
Illumina chip.
Created on July 15, 2013
@author: Oren Livne <*****@*****.**>
============================================================
'''
import impute as im, os, numpy as np, matplotlib.pyplot as P
# Load data
ped = im.hutt_pedigree()
path = os.environ['OBER_OUT'] + '/kids'
chrom = 22
prefix = path + '/cytosnp/chr%d/cytosnp.imputed' % (chrom, )
illumina = im.io.read_npz(prefix + '.phased.npz')
affy = im.hutt('hutt.phased.npz')
# Large family - with lots of sibs of one of the new Hutt kids
#parents = 246, 389
parents = 288, 465
f = ped.find_family(parents[0], parents[1])
# Compare Illumina, Affy IBD sharing pictures
P.figure(1)
im.plots.plot_family_comparison(affy, f, 1, xaxis='bp')
P.savefig(os.environ['OBER'] + '/doc/kids/family_%d_%d_affy.png' % parents)
P.figure(2)
im.plots.plot_family_comparison(illumina, f, 1, xaxis='bp')
P.savefig(os.environ['OBER'] + '/doc/kids/family_%d_%d_illumina.png' % parents)
#!/usr/bin/env python
'''
============================================================
Test GERMLINE IBD on 507's ungenotyped family.
Created on September 15, 2012
@author: Oren Livne <*****@*****.**>
============================================================
'''
import impute as im
import numpy as np
p = im.hutt('hutt.stage3.npz')
q = im.hutt('hutt.stage3.npz')
phaser = im.phase_distant.family_sib_comparison_phaser()
i = 507
phaser.run(q, im.PhaseParam(single_member=i, debug=True))
print np.where(p.haplotype.data[:, i, :] != q.haplotype.data[:, i, :])
def hutt_ibd_segments(hutt_file, i, ai, j, bj, **kwargs):
'''IBD segments using a phasing npz file relative to the chr22 directory.'''
return problem_ibd_segments(im.hutt(hutt_file), i, ai, j, bj, **kwargs)
print 'Parental haplotype coverage %', parent_coverage_fraction(pa, p)
print 'Children coverage by parental haplotypes', pa.color_sequence_coverage(np.arange(4))
####################################################################################
if __name__ == '__main__':
'''
--------------------------------------------------
Main program
--------------------------------------------------
'''
# parent_coverage = Counter()
# for chrom in CHROMOSOMES[-1:]:
# print 'Chromosome', chrom
# p = im.io.read_npz('%s/phasing/chr%d/hutt.phased.npz' % (os.environ['OBER_OUT'], chrom))
# # plot_two_families()
# parent_coverage_chrom = qf_families_parent_coverage(p)
# parent_coverage += parent_coverage_chrom
# print parent_coverage_chrom
# parents = set(x[0] for x in parent_coverage.iterkeys())
# a = [(b, (parent_coverage[(b, 0)] + parent_coverage[(b, 1)]) / (2.*sum(ChromDao.TOTAL_BP_TYPED[-1:]))) for b in set(x[0] for x in parent_coverage.iterkeys())]
# print a
p = im.hutt('hutt.phased.npz')
# pa, segments = analyze_family(p, np.setdiff1d(im.gt.genotyped_children(p, f), [1069]))#, debug=True)
# f = p.find_family_by_child(998, genotyped=False)
# pa, segments = analyze_family(p, im.gt.genotyped_children(p, f))
f = p.find_family_by_child(640, genotyped=False)
pa, segments = analyze_family(p, im.gt.genotyped_children(p, f))
#!/usr/bin/env python
"""
============================================================
Imputation test - chromosome 22.
Created on February 4, 2013
@author: Oren Livne <*****@*****.**>
============================================================
"""
import impute as im, numpy as np, os
OBER = os.environ["OBER"]
p = im.hutt("hutt.phased.npz")
ibd = im.smart_segment_set.SmartSegmentSet.load(p.pedigree.num_genotyped, OBER + "/out/segments.out")
t = im.imputation.ImputationSet.from_file(p.pedigree, OBER + "/data/impute/rare/rare.npz") # @UndefinedVariable
snps = np.where(t.snp["chrom"] == 22)[0] # SNP list out of all SNPs in t to impute
im.imputation.iibd.impute(p.haplotype, ibd, t, snp=snps, debug=False)
Plot the recombination rate lambda=lambda(f) where f is
the inbreeding coefficient. Per discussion with Mark Abney
on IBD HMM for haplotypes.
Created on January 23, 2013
@author: Oren Livne <*****@*****.**>
============================================================
'''
import matplotlib.pyplot as P, impute as im, os
lam = im.hap_lambda.lambda_vs_f()
F, L, S = im.hap_lambda.lambda_mean(lam)
out_dir = os.environ['OBER'] + '/doc/ibd'
# Bin lambda, f and calculate mean and stddev of each bin so that we can see trends
P.close(1)
P.figure(1)
im.hap_lambda.plot_lambda_vs_f(lam)
# P.title('Recombination Rate vs. Inbreeding in the Hutterities')
P.show()
P.savefig(out_dir + '/lambda_vs_f.eps')
# Plot lambda std dev vs. mean lambda in family children
P.close(2)
problem = im.hutt('hutt.npz')
P.figure(2)
im.hap_lambda.plot_lambda_std(problem)
P.show()
P.savefig(out_dir + '/lambda_child.eps')
if __name__ == '__main__':
'''
--------------------------------------------------
Main program
--------------------------------------------------
'''
out_dir = os.environ['OBER'] + '/doc/imputation/validation/ibd-optimization'
# Data format: [region start snp, region stop snp, # IBD pairs in 1415x1415 IBD set]
# Data obtained manually with commands like
#i=50; j=3168; cat segments.out | awk -v i=$i -vj=$j '($1 <= i) && (j <= $2)' | wc -l
# (or into file and then wc -l)
pairs = [((50, 3168), 1428), ((550, 2650), 7554), ((1050, 2150), 34630), ((1300, 1900), 62017), ((1425, 1775), 94152)]
p = im.hutt('hutt.npz')
cm = p.info.snp['dist_cm']
chrom = p.info.snp['chrom'][0]
l = [cm[x[0][1]] - cm[x[0][0]] for x in pairs]
num_pairs = [x[1] for x in pairs]
P.figure(1)
P.clf()
P.semilogy(l, num_pairs, 'bo-')
P.grid(True)
P.title('Chromosome %d' % (chrom,))
P.xlabel('Region Length [cM]')
P.ylabel('# IBD Pairs')
P.show()
P.savefig('%s/num_ibd_pairs.chr%d.png' % (out_dir, chrom,))
#!/usr/bin/env python
'''
============================================================
Test GERMLINE IBD on 507's ungenotyped family.
Created on September 15, 2012
@author: Oren Livne <*****@*****.**>
============================================================
'''
import impute as im
import numpy as np
p = im.hutt('hutt.stage3.npz')
q = im.hutt('hutt.stage3.npz')
phaser = im.phase_distant.family_sib_comparison_phaser()
i = 507
phaser.run(q, im.PhaseParam(single_member=i, debug=True))
print np.where(p.haplotype.data[:,i,:] != q.haplotype.data[:,i,:])
'''
============================================================
Plot phasing % after the different phasing stages.
Created on August 16, 2012
@author: Oren Livne <*****@*****.**>
============================================================
'''
import impute as im, matplotlib.pyplot as P, numpy as np, os
from numpy.core.function_base import linspace
P.figure(1)
P.clf()
P.hold(True)
p = im.hutt('hutt.phased.npz')
d5 = im.plots.plot_fill_fraction(p, color='b', label='Stage 5')
p = im.hutt('hutt.stage6.npz')
d = im.plots.plot_fill_fraction(p, color='r', label='Stage 6')
zoom = 0.96
ticks = 10
min_y = 0.95 * min(d[:, 1][0], d5[:, 1][0])
max_x = np.where(d[:, 1] > zoom)[0][0]
P.xlim([0, max_x + 1])
P.ylim([min_y, 1.0])
yticks = linspace(min_y, 1.0, ticks)
P.yticks(yticks, ['%.3f' % (t,) for t in yticks])
P.title('Hutterites Phasing Coverage, Chromosome 22')
#!/usr/bin/env python
'''
============================================================
Find Lung function study ID sublist of the entire Hutterites
problem set ID list. Output indices into the latter.
Created on Feb 18, 2013
@author: Oren Livne <*****@*****.**>
============================================================
'''
import sys, os, numpy as np, impute as im
#from optparse import OptionParser
####################################################################################
if __name__ == '__main__':
'''
--------------------------------------------------
Main program
--------------------------------------------------
'''
d = os.environ['OBER_DATA'] + '/lung'
s = im.io_pedigree.read(d + '/hutt-lung.pdg.tfam',
genotyped_id_file=d + '/hutt-lung-samples.txt')
p = im.hutt('hutt.stage5.npz')
i = np.array([
i in s.sample_id[0:s.num_genotyped]
for i in p.pedigree.sample_id[0:p.pedigree.num_genotyped]
])
np.savetxt(sys.stdout, np.where(i)[0], fmt='%d')
def hutt_ibd_segments(hutt_file, i, ai, j, bj, **kwargs):
'''IBD segments using a phasing npz file relative to the chr22 directory.'''
return problem_ibd_segments(im.hutt(hutt_file), i, ai, j, bj, **kwargs)
