def test_export_gen_exprs(self):
gen = hl.import_gen(resource('example.gen'),
sample_file=resource('example.sample'),
contig_recoding={
"01": "1"
},
reference_genome='GRCh37',
min_partitions=3).add_col_index().add_row_index()
out1 = new_temp_file()
hl.export_gen(gen,
out1,
id1=hl.str(gen.col_idx),
id2=hl.str(gen.col_idx),
missing=0.5,
varid=hl.str(gen.row_idx),
rsid=hl.str(gen.row_idx),
gp=[0.0, 1.0, 0.0])
in1 = (hl.import_gen(out1 + '.gen',
sample_file=out1 + '.sample',
min_partitions=3).add_col_index().add_row_index())
self.assertTrue(
in1.aggregate_entries(hl.agg.fraction(
in1.GP == [0.0, 1.0, 0.0])) == 1.0)
self.assertTrue(
in1.aggregate_rows(
hl.agg.fraction((in1.varid == hl.str(in1.row_idx))
& (in1.rsid == hl.str(in1.row_idx)))) == 1.0)
self.assertTrue(
in1.aggregate_cols(hl.agg.fraction(
(in1.s == hl.str(in1.col_idx)))))
def test_export_gen(self):
gen = hl.import_gen(resource('example.gen'),
sample_file=resource('example.sample'),
contig_recoding={"01": "1"},
reference_genome='GRCh37',
min_partitions=3)
file = '/tmp/test_export_gen'
hl.export_gen(gen, file)
gen2 = hl.import_gen(file + '.gen',
sample_file=file + '.sample',
reference_genome='GRCh37',
min_partitions=3)
self.assertTrue(gen._same(gen2, tolerance=3E-4, absolute=True))
def generate_random_gen():
mt = hl.utils.range_matrix_table(30, 10)
mt = (mt.annotate_rows(locus=hl.locus('20', mt.row_idx + 1),
alleles=['A', 'G']).key_rows_by('locus', 'alleles'))
mt = (mt.annotate_cols(s=hl.str(mt.col_idx)).key_cols_by('s'))
# using totally random values leads rounding differences where
# identical GEN values get rounded differently, leading to
# differences in the GT call between import_{gen, bgen}
mt = mt.annotate_entries(a=hl.int32(hl.rand_unif(0.0, 255.0)))
mt = mt.annotate_entries(b=hl.int32(hl.rand_unif(0.0, 255.0 - mt.a)))
mt = mt.transmute_entries(GP=hl.array([mt.a, mt.b, 255.0 - mt.a - mt.b]) /
255.0)
# 20% missing
mt = mt.filter_entries(hl.rand_bool(0.8))
hl.export_gen(mt, 'random', precision=4)
def generate_random_gen():
mt = hl.utils.range_matrix_table(30, 10)
mt = (mt.annotate_rows(locus = hl.locus('20', mt.row_idx + 1),
alleles = ['A', 'G'])
.key_rows_by('locus', 'alleles'))
mt = (mt.annotate_cols(s = hl.str(mt.col_idx))
.key_cols_by('s'))
# using totally random values leads rounding differences where
# identical GEN values get rounded differently, leading to
# differences in the GT call between import_{gen, bgen}
mt = mt.annotate_entries(a = hl.int32(hl.rand_unif(0.0, 255.0)))
mt = mt.annotate_entries(b = hl.int32(hl.rand_unif(0.0, 255.0 - mt.a)))
mt = mt.transmute_entries(GP = hl.array([mt.a, mt.b, 255.0 - mt.a - mt.b]) / 255.0)
# 20% missing
mt = mt.filter_entries(hl.rand_bool(0.8))
hl.export_gen(mt, 'random', precision=4)
def test_export_gen_exprs(self):
gen = hl.import_gen(resource('example.gen'),
sample_file=resource('example.sample'),
contig_recoding={"01": "1"},
reference_genome='GRCh37',
min_partitions=3).add_col_index().add_row_index()
out1 = new_temp_file()
hl.export_gen(gen, out1, id1=hl.str(gen.col_idx), id2=hl.str(gen.col_idx), missing=0.5,
varid=hl.str(gen.row_idx), rsid=hl.str(gen.row_idx), gp=[0.0, 1.0, 0.0])
in1 = (hl.import_gen(out1 + '.gen', sample_file=out1 + '.sample', min_partitions=3)
.add_col_index()
.add_row_index())
self.assertTrue(in1.aggregate_entries(hl.agg.fraction(in1.GP == [0.0, 1.0, 0.0])) == 1.0)
self.assertTrue(in1.aggregate_rows(hl.agg.fraction((in1.varid == hl.str(in1.row_idx)) &
(in1.rsid == hl.str(in1.row_idx)))) == 1.0)
self.assertTrue(in1.aggregate_cols(hl.agg.fraction((in1.s == hl.str(in1.col_idx)))))
def test_export_gen(self):
gen = hl.import_gen(resource('example.gen'),
sample_file=resource('example.sample'),
contig_recoding={"01": "1"},
reference_genome='GRCh37',
min_partitions=3)
# permute columns so not in alphabetical order!
import random
indices = list(range(gen.count_cols()))
random.shuffle(indices)
gen = gen.choose_cols(indices)
file = '/tmp/test_export_gen'
hl.export_gen(gen, file)
gen2 = hl.import_gen(file + '.gen',
sample_file=file + '.sample',
reference_genome='GRCh37',
min_partitions=3)
self.assertTrue(gen._same(gen2, tolerance=3E-4, absolute=True))