def testRegionBoundaryWithExclusions(self):
DataParser.ind_exclusions = ["1:1", "2:2", "3:3"]
genotypes = [[0, 1, 0, 0, 1, 0, 0, 1, 0], [0, 0, 1, 1, 1, 0, 0, 0, 1],
[1, 0, 0, 0, 2, 1, 1, 0, 0], [1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 0, 0, 1, 2, 0, 1, 0, 0], [0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 1, 0, 0, 0]]
BoundaryCheck.chrom = 2
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = get_lines(self.tped_filename, split=True)
index = 4
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes[index], list(genodata.genotypes))
index += 1
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
self.assertEqual(7, index)
def testTPedNoParentsPheno(self):
f = open(self.tfam_filename, "w")
f.write("""1 1 1
2 2 1
3 3 2
4 4 2
5 5 1
6 6 1
7 7 1
8 8 1
9 9 2
10 10 2
11 11 1
12 12 1""")
f.close()
DataParser.has_parents = False
DataParser.has_pheno = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.tped_filename).readlines()]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedNegativePosLocalChromMissSNP(self):
BoundaryCheck.chrom = 1
DataParser.boundary.LoadExclusions(snps=["rs0004"])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = get_lines(self.misssnp_tped_filename, split=True)
index = 2
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(3, index)
def testRegionBoundaryWithExclusions(self):
DataParser.ind_exclusions = ["1:1", "2:2", "3:3"]
genotypes = [
[0, 1, 0, 0, 1, 0, 0, 1, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 1],
[1, 0, 0, 0, 2, 1, 1, 0, 0],
[1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 0, 0, 1, 2, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 1, 0, 0, 0]
]
BoundaryCheck.chrom = 2
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.tped_filename).readlines()]
index = 4
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTpedAnalysis(self):
# We'll start with the correct phenotype with the genotypes, so we'll use
# a boundary to restrict us to only use the first SNP
BoundaryCheck.chrom = 1
DataParser.boundary = BoundaryCheck()
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertAlmostEqual(0.0034756155, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.1134684009, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337649965541, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.0007779211, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(-0.0033479839, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0492050029324, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.9457525716, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.57778118, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[1].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[1].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[1].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[2].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[2].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[2].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[2].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[2].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[2].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[2].beta_pvalues[3], places=6)
def testTpedBounded(self):
BoundaryCheck.chrom = 1
DataParser.boundary = BoundaryCheck(bp=[2000,3000])
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertEqual(1, results[0].chr)
self.assertEqual(2000, results[0].pos)
self.assertAlmostEqual(0.57778118, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[0].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[1].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[1].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[1].beta_pvalues[3], places=6)
def testMissingWithExclusions(self):
DataParser.ind_exclusions = ["2:2", "3:3"]
genotypes_w_missing = [[0, -1, -1, -1, -1, -1, -1, -1, -1, 1],
[1, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 1, 1, 0, 0, 0]]
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = libgwas.get_lines(self.miss_tped_filename, split=True)
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index],
list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTPedNoFamIDSex(self):
f = open(self.tfam_filename, "w")
f.write("""1 0 0 0.1
2 0 0 0.4
3 0 0 1.0
4 0 0 0.5
5 0 0 0.9
6 0 0 1.0
7 0 0 0.1
8 0 0 0.4
9 0 0 1.0
10 0 0 0.5
11 0 0 0.9
12 0 0 1.0""")
f.close()
DataParser.has_fid = False
DataParser.has_sex = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.tped_filename).readlines()]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTPedLiability(self):
f = open(self.tfam_filename, "w")
f.write("""1 1 0 0 1 0.1 1
2 2 0 0 1 0.4 1
3 3 0 0 2 1.0 1
4 4 0 0 2 0.5 1
5 5 0 0 1 0.9 1
6 6 0 0 1 1.0 1
7 7 0 0 1 0.1 1
8 8 0 0 1 0.4 1
9 9 0 0 2 1.0 1
10 10 0 0 2 0.5 1
11 11 0 0 1 0.9 1
12 12 0 0 1 1.0 1""")
f.close()
DataParser.has_liability = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.tped_filename).readlines()]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedWithMissingMxIndExclusionsToo(self):
pc = PhenoCovar()
DataParser.ind_exclusions = ["2:2", "3:3"]
DataParser.ind_miss_tol = 0.5 # We should only lose 1
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.miss_tped_filename).readlines()]
genotypes_w_missing = [
[0, -1, -1, -1, -1, -1, -1, -1, -1, 1],
[1, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 1, 1, 0, 0, 0]
]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedWithMissingComplete(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = get_lines(self.miss_tped_filename, split=True)
self.assertEqual(7, ped_parser.locus_count)
genotypes_w_missing = [[0, 1], [1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, 1, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, 2, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 0, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0]]
index = 0
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(7, index)
def testTpedAnalysis(self):
# We'll start with the correct phenotype with the genotypes, so we'll use
# a boundary to restrict us to only use the first SNP
BoundaryCheck.chrom = 1
DataParser.boundary = BoundaryCheck()
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertAlmostEqual(0.0034756155, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.1134684009, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337649965541, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.0007779211, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(-0.0033479839, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0492050029324, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.9457525716, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.57778118, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[1].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[1].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[1].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[2].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[2].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[2].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[2].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[2].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[2].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[2].beta_pvalues[3], places=6)
def testTpedBounded(self):
BoundaryCheck.chrom = 1
DataParser.boundary = BoundaryCheck(bp=[2000,3000])
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertEqual(1, results[0].chr)
self.assertEqual(2000, results[0].pos)
self.assertAlmostEqual(0.57778118, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[0].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[1].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[1].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[1].beta_pvalues[3], places=6)
def test_tped_standardization2(self):
DataParser.has_sex = True
DataParser.has_pheno = True
PhenoCovar.sex_as_covariate = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
nonmissing = numpy.empty(pc.phenotype_data[0].shape, dtype=numpy.bool)
nonmissing[:] = True
libgwas.standardizer.set_standardizer(
libgwas.standardizer.NoStandardization)
raw_pheno = [
0.1, 0.4, 1.0, 0.5, 0.9, 1.0, 0.1, 0.4, 1.0, 0.5, 0.9, 1.0
]
raw_cov = [1, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 1]
for pheno in pc:
(y, c,
total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(raw_pheno)):
self.assertAlmostEqual(raw_pheno[i], y[i])
self.assertAlmostEqual(raw_cov[i], c[0][i])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pc.do_standardize_variables = True
libgwas.standardizer.set_standardizer(Standardizer)
std_pheno = [
-1.61601695, -0.73455316, 1.02837442, -0.4407319, 0.73455316,
1.02837442, -1.61601695, -0.73455316, 1.02837442, -0.4407319,
0.73455316, 1.02837442
]
std_cov = [
-0.70710678, -0.70710678, 1.41421356, 1.41421356, -0.70710678,
-0.70710678, -0.70710678, -0.70710678, 1.41421356, 1.41421356,
-0.70710678, -0.70710678
]
for pheno in pc:
(y, c,
total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(std_pheno)):
self.assertAlmostEqual(std_pheno[i], y[i])
self.assertAlmostEqual(std_cov[i], c[0][i])
def test_tped_standardization_w_dbl_missing(self):
PhenoCovar.sex_as_covariate = True
DataParser.ind_exclusions = ["11:11", "12:12"]
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
nonmissing = numpy.empty(pc.phenotype_data[0].shape, dtype=numpy.bool)
nonmissing[:] = True
nonmissing[0] = False
nonmissing[1] = False
libgwas.standardizer.set_standardizer(
libgwas.standardizer.NoStandardization)
raw_pheno = [1.0, 0.5, 0.9, 1.0, 0.1, 0.4, 1.0, 0.5]
raw_cov = [2, 2, 1, 1, 1, 1, 2, 2]
for pheno in pc:
(y, c,
total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(raw_pheno)):
self.assertAlmostEqual(raw_pheno[i], y[i])
self.assertAlmostEqual(raw_cov[i], c[0][i])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pc.do_standardize_variables = True
libgwas.standardizer.set_standardizer(Standardizer)
std_pheno = [
1.19915853, -0.26322992, 0.90668084, 1.19915853, -1.43314068,
-0.55570761, 1.19915853, -0.26322992
]
std_cov = [
1.22474487, 1.22474487, -0.81649658, -0.81649658, -0.81649658,
-0.81649658, 1.22474487, 1.22474487
]
test_var = [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
for pheno in pc:
(y, c,
total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(std_pheno)):
self.assertAlmostEqual(std_pheno[i], y[i])
self.assertAlmostEqual(std_cov[i], c[0][i])
def testAllelesIteration(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
index = 0
for snp in ped_parser:
self.assertEqual(self.tped1_alleles[index][1], snp.minor_allele)
self.assertEqual(self.tped1_alleles[index][0], snp.major_allele)
index += 1
self.assertEqual(7, index)
def testPedNegativePositions(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.misssnp_tped_filename).readlines()]
index = 2
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedNegativePositions(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = libgwas.get_lines(self.misssnp_tped_filename, split=True)
index = 2
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedWithMissingComplete(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.miss_tped_filename).readlines()]
self.assertEqual(7, ped_parser.locus_count)
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes_w_missing[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedComplete(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
self.assertEqual(12, ped_parser.ind_count)
mapdata = libgwas.get_lines(self.tped_filename, split=True)
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def test_tped_standardization_w_dbl_missing(self):
PhenoCovar.sex_as_covariate = True
DataParser.ind_exclusions = ["11:11", "12:12"]
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
nonmissing = numpy.empty(pc.phenotype_data[0].shape, dtype=numpy.bool)
nonmissing[:] = True
nonmissing[0] = False
nonmissing[1] = False
libgwas.standardizer.set_standardizer(libgwas.standardizer.NoStandardization)
raw_pheno = [1.0, 0.5, 0.9, 1.0, 0.1, 0.4, 1.0, 0.5]
raw_cov = [2, 2, 1, 1, 1, 1, 2, 2]
for pheno in pc:
(y, c, total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(raw_pheno)):
self.assertAlmostEqual(raw_pheno[i], y[i])
self.assertAlmostEqual(raw_cov[i], c[0][i])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pc.do_standardize_variables = True
libgwas.standardizer.set_standardizer(Standardizer)
std_pheno = [ 1.19915853, -0.26322992, 0.90668084,
1.19915853, -1.43314068, -0.55570761, 1.19915853, -0.26322992]
std_cov = [ 1.22474487, 1.22474487, -0.81649658,
-0.81649658, -0.81649658, -0.81649658, 1.22474487, 1.22474487]
test_var = [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
for pheno in pc:
(y, c, total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(std_pheno)):
self.assertAlmostEqual(std_pheno[i], y[i])
self.assertAlmostEqual(std_cov[i], c[0][i])
def testPedNegativePosLocalChromMissSNP(self):
BoundaryCheck.chrom = 1
DataParser.boundary.LoadExclusions(snps=["rs0004"])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.misssnp_tped_filename).readlines()]
index = 2
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(3, index)
def testTPedPhenoMissingPC(self):
PhenoCovar.sex_as_covariate = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_missing,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
self.assertEqual(12, len(pc.covariate_data[0]))
self.assertEqual(12, len(pc.phenotype_data[0]))
self.assertEqual(1, len(pc.phenotype_names))
mapdata = get_lines(self.tped_filename, split=True)
self.genotypes = [[1, 0, 0, 1, 0, 0, 1, 0, 0, 1],
[1, 0, 0, 0, 1, 1, 1, 0, 0, 0],
[2, 1, 1, 0, 0, 0, 2, 1, 1, 0],
[1, 2, 1, 1, 0, 0, 1, 2, 1, 1],
[2, 0, 1, 0, 0, 1, 2, 0, 1, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0, 0],
[1, 1, 0, 0, 0, 0, 1, 1, 0, 0]]
pheno_values = [0.4, 1.0, 0.5, 0.9, 1.0, 0.1, 0.4, 1.0, 0.5, 0.9]
index = 0
self.assertEqual(7, ped_parser.locus_count)
for snp in ped_parser:
for y in pc:
(pheno, covars,
nonmissing) = y.get_variables(snp.missing_genotypes)
self.assertAlmostEqual(pheno_values, list(pheno), places=4)
try:
genodata = snp.get_genotype_data(nonmissing)
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(7, index)
def testTPedNoFamID(self):
with open(self.tfam_filename, "w") as f:
f.write("""1 0 0 1 0.1
2 0 0 1 0.4
3 0 0 2 1.0
4 0 0 2 0.5
5 0 0 1 0.9
6 0 0 1 1.0
7 0 0 1 0.1
8 0 0 1 0.4
9 0 0 2 1.0
10 0 0 2 0.5
11 0 0 1 0.9
12 0 0 1 1.0""")
DataParser.has_fid = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = get_lines(self.tped_filename, split=True)
index = 0
for snp in ped_parser:
for y in pc:
(pheno, covars,
non_missing) = y.get_variables(snp.missing_genotypes)
try:
genodata = snp.get_genotype_data(non_missing)
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(7, index)
def testPedNegativePosLocalChromMissSNP(self):
BoundaryCheck.chrom = 1
DataParser.boundary.LoadExclusions(snps=["rs0004"])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = libgwas.get_lines(self.misssnp_tped_filename, split=True)
index = 2
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(3, index)
def testTPedNoParentsPheno(self):
with open(self.tfam_filename, "w") as f:
f.write("""1 1 1
2 2 1
3 3 2
4 4 2
5 5 1
6 6 1
7 7 1
8 8 1
9 9 2
10 10 2
11 11 1
12 12 1""")
DataParser.has_parents = False
DataParser.has_pheno = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = get_lines(self.tped_filename, split=True)
index = 0
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(7, index)
def testPedNegativePositionsLocalChrom(self):
BoundaryCheck.chrom = 1
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.misssnp_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [
x.strip().split()
for x in open(self.misssnp_tped_filename).readlines()
]
index = 2
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(4, index)
def test_tped_standardization2(self):
DataParser.has_sex = True
DataParser.has_pheno = True
PhenoCovar.sex_as_covariate = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
nonmissing = numpy.empty(pc.phenotype_data[0].shape, dtype=numpy.bool)
nonmissing[:] = True
libgwas.standardizer.set_standardizer(libgwas.standardizer.NoStandardization)
raw_pheno = [0.1, 0.4, 1.0, 0.5, 0.9, 1.0, 0.1, 0.4, 1.0, 0.5, 0.9, 1.0]
raw_cov = [1, 1, 2, 2, 1, 1, 1, 1, 2, 2, 1, 1]
for pheno in pc:
(y, c, total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(raw_pheno)):
self.assertAlmostEqual(raw_pheno[i], y[i])
self.assertAlmostEqual(raw_cov[i], c[0][i])
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pc.do_standardize_variables = True
libgwas.standardizer.set_standardizer(Standardizer)
std_pheno = [-1.61601695, -0.73455316, 1.02837442, -0.4407319 , 0.73455316, 1.02837442,
-1.61601695, -0.73455316, 1.02837442, -0.4407319 , 0.73455316, 1.02837442]
std_cov = [-0.70710678, -0.70710678, 1.41421356, 1.41421356, -0.70710678, -0.70710678,
-0.70710678, -0.70710678, 1.41421356, 1.41421356, -0.70710678, -0.70710678]
for pheno in pc:
(y, c, total_nonmissing) = pheno.get_variables(numpy.invert(nonmissing))
for i in range(0, len(std_pheno)):
self.assertAlmostEqual(std_pheno[i], y[i])
self.assertAlmostEqual(std_cov[i], c[0][i])
def testPedSnpBoundaryTPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0001-rs0003"])
BoundaryCheck.chrom = 1
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = libgwas.get_lines(self.tped_filename, split=True)
index = 0
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertAlmostEqual(self.hetero_freq_tped[index],
snp.hetero_freq,
places=4)
index += 1
self.assertEqual(3, ped_parser.locus_count)
index = 0
for snp in ped_parser:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(3, index)
def testPedSnpBoundary2TPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0005-rs0006"])
BoundaryCheck.chrom = 2
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = [x.split() for x in open(self.tped_filename).readlines()]
index = 4
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertAlmostEqual(self.hetero_freq_tped[index],
snp.hetero_freq,
places=4)
index += 1
self.assertEqual(2, ped_parser.locus_count)
index = 4
for snp in ped_parser:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(6, index)
def testPedSnpBoundary2TPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0005-rs0006"])
BoundaryCheck.chrom = 2
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = [x.split() for x in open(self.tped_filename).readlines()]
index = 4
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertAlmostEqual(self.hetero_freq_tped[index], snp.hetero_freq, places=4)
index += 1
self.assertEqual(2, ped_parser.locus_count)
index = 4
for snp in ped_parser:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(6, index)
def testPedRegionBoundaryWithExclusionsTPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0005-rs0007"])
DataParser.boundary.LoadExclusions(snps=["rs0007"])
BoundaryCheck.chrom = 2
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = [x.split() for x in open(self.tped_filename).readlines()]
index = 4
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
index += 1
index = 4
for snp in ped_parser:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(6, index)
def testPedRegionBoundaryWithExclusionsTPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0005-rs0007"])
DataParser.boundary.LoadExclusions(snps=["rs0007"])
BoundaryCheck.chrom = 2
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = [x.split() for x in open(self.tped_filename).readlines()]
index = 4
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
index += 1
index = 4
for snp in ped_parser:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(6, index)
def testTPedLiability(self):
with open(self.tfam_filename, "w") as f:
f.write("""1 1 0 0 1 0.1 1
2 2 0 0 1 0.4 1
3 3 0 0 2 1.0 1
4 4 0 0 2 0.5 1
5 5 0 0 1 0.9 1
6 6 0 0 1 1.0 1
7 7 0 0 1 0.1 1
8 8 0 0 1 0.4 1
9 9 0 0 2 1.0 1
10 10 0 0 2 0.5 1
11 11 0 0 1 0.9 1
12 12 0 0 1 1.0 1""")
DataParser.has_liability = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = get_lines(self.tped_filename, split=True)
index = 0
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(7, index)
def testPedRegionBoundaryWithExclusionsTPed(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
DataParser.boundary = SnpBoundaryCheck(snps=["rs0005-rs0007"])
DataParser.boundary.LoadExclusions(snps=["rs0007"])
BoundaryCheck.chrom = 2
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
pedigree = get_lines(self.tped_filename, split=True)
index = 4
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
index += 1
index = 4
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(pedigree[index][0]), snp.chr)
self.assertEqual(int(pedigree[index][3]), snp.pos)
self.assertEqual(pedigree[index][1], snp.rsid)
self.assertEqual(self.genotypes[index],
list(genodata.genotypes))
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(6, index)
def testTPedPhenoComplete(self):
PhenoCovar.sex_as_covariate = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
self.assertEqual(12, len(pc.covariate_data[0]))
self.assertEqual(12, len(pc.phenotype_data[0]))
self.assertEqual(1, len(pc.phenotype_names))
mapdata = libgwas.get_lines(self.tped_filename, split=True)
index = 0
self.assertEqual(7, ped_parser.locus_count)
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTPedPhenoComplete(self):
PhenoCovar.sex_as_covariate = True
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
self.assertEqual(12, len(pc.covariate_data[0]))
self.assertEqual(12, len(pc.phenotype_data[0]))
self.assertEqual(1, len(pc.phenotype_names))
mapdata = [x.strip().split() for x in open(self.tped_filename).readlines()]
index = 0
self.assertEqual(7, ped_parser.locus_count)
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testRegionBoundaryWithExclusions(self):
DataParser.ind_exclusions = ["1:1", "2:2", "3:3"]
genotypes = [[0, 1, 0, 0, 1, 0, 0, 1, 0], [0, 0, 1, 1, 1, 0, 0, 0, 1],
[1, 0, 0, 0, 2, 1, 1, 0, 0], [1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 0, 0, 1, 2, 0, 1, 0, 0], [0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 1, 0, 0, 0]]
BoundaryCheck.chrom = 2
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = libgwas.get_lines(self.tped_filename, split=True)
index = 4
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedWithMissingComplete(self):
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [
x.strip().split()
for x in open(self.miss_tped_filename).readlines()
]
self.assertEqual(7, ped_parser.locus_count)
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes_w_missing[index],
list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testPedWithMissingMxSnpComplete(self):
pc = PhenoCovar()
DataParser.snp_miss_tol = 0.5 # We should only lose 1
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = libgwas.get_lines(self.miss_tped_filename, split=True)
genotypes_w_missing = [[0, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0],
[1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, -1, 1, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, -1, 2, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, -1, 0, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, -1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, -1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0]]
hetero_freq_tped = [
0.3636, 0.5, 0.3636, 0.4545, 0.3636, 0.2727, 0.2727
]
self.assertEqual(7, ped_parser.locus_count)
index = 0
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
index += 1
self.assertEqual(7, index)
index = 0
missing = 0
valid = 0
for snp in ped_parser:
for y in pc:
(pheno, covars,
nonmissing) = y.get_variables(snp.missing_genotypes)
try:
genodata = snp.get_genotype_data(nonmissing)
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index],
list(snp.genotype_data))
self.assertAlmostEqual(hetero_freq_tped[index],
genodata.hetero_freq,
places=4)
valid += 1
except TooMuchMissing as e:
missing += 1
except InvalidFrequency as e:
pass
index += 1
self.assertEqual(1, missing)
self.assertEqual(6, valid)
self.assertEqual(7, index)
def testTPedNoParentsPheno(self):
f = open(self.tfam_filename, "w")
f.write("""1 1 1
2 2 1
3 3 2
4 4 2
5 5 1
6 6 1
7 7 1
8 8 1
9 9 2
10 10 2
11 11 1
12 12 1""")
f.close()
DataParser.has_parents = False
DataParser.has_pheno = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [
x.strip().split() for x in open(self.tped_filename).readlines()
]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTPedNoFamIDSex(self):
f = open(self.tfam_filename, "w")
f.write("""1 0 0 0.1
2 0 0 0.4
3 0 0 1.0
4 0 0 0.5
5 0 0 0.9
6 0 0 1.0
7 0 0 0.1
8 0 0 0.4
9 0 0 1.0
10 0 0 0.5
11 0 0 0.9
12 0 0 1.0""")
f.close()
DataParser.has_fid = False
DataParser.has_sex = False
pc = PhenoCovar()
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [
x.strip().split() for x in open(self.tped_filename).readlines()
]
index = 0
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(self.genotypes[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
def testTpedSnpBounded(self):
BoundaryCheck.chrom = 1
DataParser.boundary = SnpBoundaryCheck(snps=["rs1000-rs3000"])
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertEqual(1, results[0].chr)
self.assertEqual(1000, results[0].pos)
self.assertAlmostEqual(0.0034756155, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.1134684009, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337649965541, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.0007779211, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(-0.0033479839, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0492050029324, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.9457525716, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.57778118, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[1].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[1].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[1].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[2].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[2].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[2].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[2].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[2].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[2].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[2].beta_pvalues[3], places=6)
def testTpedSnpBounded(self):
BoundaryCheck.chrom = 1
DataParser.boundary = SnpBoundaryCheck(snps=["rs1000-rs3000"])
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertEqual(1, results[0].chr)
self.assertEqual(1000, results[0].pos)
self.assertAlmostEqual(0.0034756155, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.1134684009, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337649965541, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.0007779211, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(-0.0033479839, results[0].betas[3], places=6)
self.assertAlmostEqual(0.0492050029324, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.9457525716, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.57778118, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.02798537, results[1].betas[1], places=6)
self.assertAlmostEqual(0.033790691857, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.40755865, results[1].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.03275892, results[1].betas[3], places=6)
self.assertAlmostEqual(0.0475661, results[1].beta_stderr[3], places=6)
self.assertAlmostEqual(0.49101013, results[1].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.44661276, results[2].p_mvtest, places=6)
self.assertAlmostEqual(0.01663975, results[2].betas[1], places=6)
self.assertAlmostEqual(0.03443300, results[2].beta_stderr[1], places=6)
self.assertAlmostEqual(0.62891811, results[2].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.05712017, results[2].betas[3], places=6)
self.assertAlmostEqual(0.04783608, results[2].beta_stderr[3], places=6)
self.assertAlmostEqual(0.232446188, results[2].beta_pvalues[3], places=6)
def testTPedAnalysisCov(self):
PhenoCovar.sex_as_covariate = True
DataParser.boundary = BoundaryCheck()
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
#pheno.standardize_variables()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertAlmostEqual(0.00342380, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.11362883, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337610, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.00076356, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.01911090, results[0].betas[3], places=6)
self.assertAlmostEqual(0.10143178, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.8505542, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.584950593047, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.0276543736525, results[1].betas[1], places=6)
self.assertAlmostEqual(0.03383588, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.413751829881, results[1].beta_pvalues[1], places=6)
def testPedWithMissingMxIndExclusionsToo(self):
pc = PhenoCovar()
DataParser.ind_exclusions = ["2:2", "3:3"]
DataParser.ind_miss_tol = 0.5 # We should only lose 1
ped_parser = TransposedPedigreeParser(self.tfam_filename,
self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = get_lines(self.miss_tped_filename, split=True)
genotypes_w_missing = [[0, 1], [1, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 0, 1, 1, 0, 0, 0]]
index = 0
non_missing = self.non_missing
non_missing[1] = False
non_missing[2] = False
for snp in ped_parser:
snp_filter = numpy.ones(snp.missing_genotypes.shape[0]) == 1
try:
genodata = snp.get_genotype_data(snp_filter)
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index],
list(genodata.genotypes))
index += 1
except TooMuchMissing as e:
pass
except InvalidFrequency as e:
pass
self.assertEqual(7, index)
def testTPedAnalysisCov(self):
PhenoCovar.sex_as_covariate = True
DataParser.boundary = BoundaryCheck()
pheno = PhenoCovar()
dataset = TransposedPedigreeParser(self.tfam_filename, self.tped_filename)
dataset.load_tfam(pheno)
dataset.load_genotypes()
#pheno.standardize_variables()
results = [x for x in mv_esteq.RunAnalysis(dataset, pheno)]
self.assertAlmostEqual(0.00342380, results[0].p_mvtest, places=6)
self.assertAlmostEqual(0.11362883, results[0].betas[1], places=6)
self.assertAlmostEqual(0.0337610, results[0].beta_stderr[1], places=6)
self.assertAlmostEqual(0.00076356, results[0].beta_pvalues[1], places=6)
self.assertAlmostEqual(0.01911090, results[0].betas[3], places=6)
self.assertAlmostEqual(0.10143178, results[0].beta_stderr[3], places=6)
self.assertAlmostEqual(0.8505542, results[0].beta_pvalues[3], places=6)
self.assertAlmostEqual(0.584950593047, results[1].p_mvtest, places=6)
self.assertAlmostEqual(0.0276543736525, results[1].betas[1], places=6)
self.assertAlmostEqual(0.03383588, results[1].beta_stderr[1], places=6)
self.assertAlmostEqual(0.413751829881, results[1].beta_pvalues[1], places=6)
def testPedWithMissingMxSnpComplete(self):
pc = PhenoCovar()
DataParser.snp_miss_tol = 0.5 # We should only lose 1
ped_parser = TransposedPedigreeParser(self.tfam_filename, self.miss_tped_filename)
ped_parser.load_tfam(pc)
ped_parser.load_genotypes()
mapdata = [x.strip().split() for x in open(self.miss_tped_filename).readlines()]
genotypes_w_missing = [
[0, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0],
[1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1],
[0, -1, 1, 1, 0, 0, 0, 2, 1, 1, 0, 0],
[0, -1, 2, 1, 1, 0, 0, 1, 2, 1, 1, 0],
[1, -1, 0, 1, 0, 0, 1, 2, 0, 1, 0, 0],
[1, -1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, -1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0]
]
hetero_freq_tped = [0.3636, 0.5, 0.3636, 0.4545, 0.3636, 0.2727, 0.2727]
self.assertEqual(6, ped_parser.locus_count)
index = 1
loci = ped_parser.get_loci()
for snp in loci:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertAlmostEqual(hetero_freq_tped[index], snp.hetero_freq, places=4)
index += 1
index = 1
for snp in ped_parser:
self.assertEqual(int(mapdata[index][0]), snp.chr)
self.assertEqual(int(mapdata[index][3]), snp.pos)
self.assertEqual(mapdata[index][1], snp.rsid)
self.assertEqual(genotypes_w_missing[index], list(snp.genotype_data))
index += 1
self.assertEqual(7, index)
