def test_phase_trivial_cases(self):
'''Check phasing trivial cases in trios. The trio data is (0,1=parents, 2=child). The
solution is kept in the trio test file as the fictitious individual 3.'''
g = self.problem.genotype
itu.assert_size_equals(self.problem.genotype, 19, 3)
assert_equal(self.problem.error.shape, (19, 3), 'Incorrect error array size')
trio = (0, 1, 2)
solution = self.solution.genotype.data
h = self.problem.haplotype
assert_problem_stats(self.problem, 6 * g.num_snps, 0, 0)
self.phaser.run(self.problem)
for snp in self.problem.snp_range:
expected_parent_genotype = solution[snp, trio[0:CHILD], :]
#expected_child_genotype = solution[snp,trio[CHILD],:]
expected_child_haplotype = solution[snp, trio[CHILD], :]
parent_genotype = g.data[snp, trio[0:CHILD], :]
#child_genotype = g.data[snp,trio[CHILD]]
child_haplotype = h.data[snp, trio[CHILD]]
'''
print 'SNP', snp
print 'Data', g.data[snp,trio,:]
print 'Imputed parent', parent_genotype
print 'Child hap', child_haplotype
print 'Solution hap', solution[snp,trio,:]
'''
assert_equal(child_haplotype, expected_child_haplotype, 'Wrong child haplotype by trivial phaser at snp %d' % (snp,))
assert_equal(parent_genotype, expected_parent_genotype, 'Wrong parent genotype imputation by trivial phaser at snp %d' % (snp,))
#assert_equal(np.sort(child_genotype), np.sort(expected_child_genotype), 'Wrong child genotype imputation by trivial phaser at snp %d' % (snp,))
assert_problem_stats(self.problem, 6 * g.num_snps, 66, 6, error_rate=0.1)
def test_phase_trivial_cases(self):
'''Check phasing trivial cases in trios. The trio data is (0,1=parents, 2=child). The
solution is kept in the trio test file as the fictitious individual 3.'''
g = self.problem.genotype
itu.assert_size_equals(self.problem.genotype, 1, 2)
duo = (0, 1)
solution = self.solution.genotype.data
h = self.problem.haplotype
assert_problem_stats(self.problem, 4 * g.num_snps, 0, 0)
self.phaser.run(self.problem)
for snp in self.problem.snp_range:
expected_parent_genotype = solution[snp, duo[0], :]
#expected_child_genotype = solution[snp,trio[CHILD],:]
expected_child_haplotype = solution[snp, duo[1], :]
parent_genotype = g.data[snp, duo[0], :]
#child_genotype = g.data[snp,trio[CHILD]]
child_haplotype = h.data[snp, duo[1]]
'''
print 'SNP', snp
print 'Data', g.data[snp,trio,:]
print 'Imputed parent', parent_genotype
print 'Child hap', child_haplotype
print 'Solution hap', solution[snp,trio,:]
'''
assert_equal(child_haplotype, expected_child_haplotype, 'Wrong child haplotype by trivial phaser at snp %d' % (snp,))
assert_equal(parent_genotype, expected_parent_genotype, 'Wrong parent genotype imputation by trivial phaser at snp %d' % (snp,))
#assert_equal(np.sort(child_genotype), np.sort(expected_child_genotype), 'Wrong child genotype imputation by trivial phaser at snp %d' % (snp,))
assert_problem_stats(self.problem, 4 * g.num_snps, 4, 0)
def test_phase_family(self):
'''Check phasing trivial cases in all genotyped trios.'''
problem = io.read_plink(pedigree=itu.HUTT_PED, prefix=itu.GENOTYPE_SAMPLE, haplotype=None)
itu.assert_size_equals(problem.genotype, 8, 1415)
assert_equal(len(problem.trios()), 869, 'Unexpected # of genotyped trios')
self.phaser.run(problem, PhaseParam(debug=False))
itu.assert_problem_stats(problem, 22640, 20225, 144)
def test_phase_trivial_cases_all_trios(self):
'''Check phasing trivial cases in all genotyped trios.'''
itu.assert_size_equals(self.problem.genotype, 8, 1415)
assert_equal(len(self.problem.trios()), 869,
'Unexpected # of genotyped trios')
self.phaser.run(self.problem)
itu.assert_problem_stats(self.problem, 22640, 18567, 10)
def test_child_comparison_one_parent(self):
'''Test applying child comparison to a nuclear family with many genotyped kids but only
one genotyped parent.'''
problem = io.read_npz(itu.FAMILY945_ONE_PARENT_STAGE2)
itu.assert_size_equals(problem.genotype, 3218, 8)
itu.assert_problem_stats(problem, 51488, 44150, 96)
phaser = family_child_comparison_phaser(debug=False)
phaser.run(problem)
itu.assert_problem_stats(problem, 51488, 47343, 101)
def test_child_comparison_one_parent(self):
'''Test applying child comparison to a nuclear family with many genotyped kids but only
one genotyped parent.'''
problem = io.read_npz(itu.FAMILY945_ONE_PARENT_STAGE2)
itu.assert_size_equals(problem.genotype, 3218, 8)
itu.assert_problem_stats(problem, 51488, 44150, 96)
phaser = family_child_comparison_phaser(debug=False)
phaser.run(problem)
itu.assert_problem_stats(problem, 51488, 47343, 101)
def test_phase_trivial_cases_all_trios(self):
'''Check phasing trivial cases in all genotyped trios.'''
itu.assert_size_equals(self.problem.genotype, 8, 1415)
assert_equal(len(self.problem.trios()), 869, 'Unexpected # of genotyped trios')
self.phaser.run(self.problem)
itu.assert_problem_stats(self.problem, 22640, 18567, 10)
#---------------------------------------------
# Private Methods
#---------------------------------------------
def test_family_12(self):
'''Test comparing sibs with non-genotyped parents (stage 4).'''
problem = io.read_npz(itu.FAMILY12_STAGE2)
itu.assert_size_equals(problem.genotype, 3218, 7)
itu.assert_problem_stats(problem, 45052, 42162, 237)
assert_equal(len(list(problem.families(genotyped=False))), 1, 'Incorrect number of families')
phaser = family_sib_comparison_phaser()
phaser.run(problem, PhaseParam(single_member=1))
itu.assert_problem_stats(problem, 45052, 42162, 237)
def test_family_963(self):
'''Test comparing sibs with non-genotyped parents (stage 4). This was a problematic family.'''
problem = io.read_npz(itu.FAMILY963_STAGE4)
itu.assert_size_equals(problem.genotype, 3218, 3)
itu.assert_problem_stats(problem, 19308, 19286, 23)
assert_equal(len(list(problem.families(genotyped=False))), 1, 'Incorrect number of families')
phaser = family_sib_comparison_phaser()
phaser.run(problem)
itu.assert_problem_stats(problem, 19308, 19286, 23)
def test_family_12(self):
'''Test comparing sibs with non-genotyped parents (stage 4).'''
problem = io.read_npz(itu.FAMILY12_STAGE2)
itu.assert_size_equals(problem.genotype, 3218, 7)
itu.assert_problem_stats(problem, 45052, 42162, 237)
assert_equal(len(list(problem.families(genotyped=False))), 1,
'Incorrect number of families')
phaser = family_sib_comparison_phaser()
phaser.run(problem, PhaseParam(single_member=1))
itu.assert_problem_stats(problem, 45052, 42162, 237)
def test_family_963(self):
'''Test comparing sibs with non-genotyped parents (stage 4). This was a problematic family.'''
problem = io.read_npz(itu.FAMILY963_STAGE4)
itu.assert_size_equals(problem.genotype, 3218, 3)
itu.assert_problem_stats(problem, 19308, 19286, 23)
assert_equal(len(list(problem.families(genotyped=False))), 1,
'Incorrect number of families')
phaser = family_sib_comparison_phaser()
phaser.run(problem)
itu.assert_problem_stats(problem, 19308, 19286, 23)
def test_family_2003_need_poo_alignment(self):
'''Test comparing sibs with non-genotyped parents (stage 4). This case highlights
the need to align POO-phases, i.e., swap founder haps to correctly patch families at individual
ID 28412 (our original index 386; in this problem, index 10).'''
problem = io.read_npz(itu.FAMILY2003_STAGE3)
itu.assert_size_equals(problem.genotype, 3218, 9)
itu.assert_problem_stats(problem, 57924, 43339, 85)
assert_equal(len(list(problem.families(genotyped=False))), 1, 'Incorrect number of families')
#f = problem.families(genotyped=False)[0]
#print f.member_list
#print problem.pedigree.sample_id
phaser = family_sib_comparison_phaser()
phaser.run(problem)
itu.assert_problem_stats(problem, 57924, 57515, 85)
def test_family_2003_need_poo_alignment(self):
'''Test comparing sibs with non-genotyped parents (stage 4). This case highlights
the need to align POO-phases, i.e., swap founder haps to correctly patch families at individual
ID 28412 (our original index 386; in this problem, index 10).'''
problem = io.read_npz(itu.FAMILY2003_STAGE3)
itu.assert_size_equals(problem.genotype, 3218, 9)
itu.assert_problem_stats(problem, 57924, 43339, 85)
assert_equal(len(list(problem.families(genotyped=False))), 1,
'Incorrect number of families')
#f = problem.families(genotyped=False)[0]
#print f.member_list
#print problem.pedigree.sample_id
phaser = family_sib_comparison_phaser()
phaser.run(problem)
itu.assert_problem_stats(problem, 57924, 57515, 85)
def test_outer_duo(self):
'''Test applying child comparison to a nuclear family with many genotyped kids but only
one genotyped parent. Seems to be fine for now: too many errors are flagged, but we are not
going to split hair.'''
p = self.problem
# h = p.haplotype
# (f, m) = (self.family.father, self.family.mother)
snp = p.info.snp_by_name('rs5746679')
assert_equal(snp, [3], 'Wrong SNP index')
itu.assert_size_equals(p.genotype, 3218, 7)
itu.assert_problem_stats(p, 45052, 40086, 4)
# print 'genotypes'
# print p.genotype.data[snp, :, :]
# print 'haplotypes'
# print p.haplotype.data[snp, :, :]
phaser = family_phaser()
phaser.run(p)
itu.assert_problem_stats(p, 45052, 45023, 25)
def test_phase_and_get_stats(self):
'''Test gathering phasing statistics in a Stats object.'''
nuclear_family_phaser().run(self.problem)
g_orig = self.problem.genotype.data.copy()
stats = v.Stats(g_orig, self.problem.haplotype, self.problem.num_errors)
itu.assert_problem_stats(self.problem, 167336, 137693, 102)
# Check stats fields
partially_filled_genotype = np.where(recode.recode_single_genotype(self.problem.genotype.data) < 0)
assert_equal(len(partially_filled_genotype[0]), 279, 'Unexpected # of partially-filled genotypes')
assert_equal(stats.imputed.total, 185, 'Unexpected # of fully-imputed genotypes')
assert_almost_equal(stats.imputed.fraction, 0.00221, decimal=5, err_msg='Unexpected fraction of fully-imputed genotypes')
assert_equal(stats.imputed_partial.total, 45, 'Unexpected # of partially-imputed genotypes')
# Check that printouts don't crash us
stats.pprint(open(os.devnull, 'wb'))
# Check that stats is pickable and unpicklable
out_name = util.temp_filename(suffix='.npz')
out = open(out_name, 'wb')
np.savez(out, stats=np.array([stats]))
out.close()
loaded = np.load(out_name)
assert_equal(loaded['stats'][0].imputed_partial.total, stats.imputed_partial.total, 'Pickling & unpickling a Stats object failed')
