def test_combiner_works():
_paths = ['gvcfs/HG00096.g.vcf.gz', 'gvcfs/HG00268.g.vcf.gz']
paths = [resource(p) for p in _paths]
parts = [
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 17821257, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 18708366, reference_genome='GRCh38')),
includes_end=True),
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 18708367, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 19776611, reference_genome='GRCh38')),
includes_end=True),
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 19776612, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 21144633, reference_genome='GRCh38')),
includes_end=True)
]
vcfs = hl.import_gvcfs(paths, parts, reference_genome='GRCh38', array_elements_required=False)
entry_to_keep = defined_entry_fields(vcfs[0].filter_rows(hl.is_defined(vcfs[0].info.END)), 100_000) - {'GT', 'PGT', 'PL'}
vcfs = [transform_gvcf(mt.annotate_rows(info=mt.info.annotate(
MQ_DP=hl.missing(hl.tint32),
VarDP=hl.missing(hl.tint32),
QUALapprox=hl.missing(hl.tint32))),
reference_entry_fields_to_keep=entry_to_keep)
for mt in vcfs]
comb = combine_variant_datasets(vcfs)
assert len(parts) == comb.variant_data.n_partitions()
comb.variant_data._force_count_rows()
comb.reference_data._force_count_rows()
def test_vcf_vds_combiner_equivalence():
import hail.experimental.vcf_combiner.vcf_combiner as vcf
import hail.vds.combiner as vds
_paths = ['gvcfs/HG00096.g.vcf.gz', 'gvcfs/HG00268.g.vcf.gz']
paths = [resource(p) for p in _paths]
parts = [
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 17821257, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 18708366, reference_genome='GRCh38')),
includes_end=True),
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 18708367, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 19776611, reference_genome='GRCh38')),
includes_end=True),
hl.Interval(start=hl.Struct(locus=hl.Locus('chr20', 19776612, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus('chr20', 21144633, reference_genome='GRCh38')),
includes_end=True)
]
vcfs = [mt.annotate_rows(info=mt.info.annotate(
MQ_DP=hl.missing(hl.tint32),
VarDP=hl.missing(hl.tint32),
QUALapprox=hl.missing(hl.tint32)))
for mt in hl.import_gvcfs(paths, parts, reference_genome='GRCh38',
array_elements_required=False)]
entry_to_keep = defined_entry_fields(vcfs[0].filter_rows(hl.is_defined(vcfs[0].info.END)), 100_000) - {'GT', 'PGT', 'PL'}
vds = vds.combine_variant_datasets([vds.transform_gvcf(mt, reference_entry_fields_to_keep=entry_to_keep) for mt in vcfs])
smt = vcf.combine_gvcfs([vcf.transform_gvcf(mt) for mt in vcfs])
smt_from_vds = hl.vds.to_merged_sparse_mt(vds).drop('RGQ')
smt = smt.select_entries(*smt_from_vds.entry) # harmonize fields and order
smt = smt.key_rows_by('locus', 'alleles')
assert smt._same(smt_from_vds)
def __init__(self, schema, paths, key, intervals):
assert (key is None) == (intervals is None)
self.schema = schema
self.paths = paths
self.key = key
if intervals is not None:
t = hl.expr.impute_type(intervals)
if not isinstance(t, hl.tarray) and not isinstance(
t.element_type, hl.tinterval):
raise TypeError("'intervals' must be an array of tintervals")
pt = t.element_type.point_type
if isinstance(pt, hl.tstruct):
self._interval_type = t
else:
self._interval_type = hl.tarray(
hl.tinterval(hl.tstruct(__point=pt)))
if intervals is not None and t != self._interval_type:
self.intervals = [
hl.Interval(hl.Struct(__point=i.start),
hl.Struct(__point=i.end), i.includes_start,
i.includes_end) for i in intervals
]
else:
self.intervals = intervals
def generate_5_sample_vds():
paths = [
os.path.join(resource('gvcfs'), '1kg_chr22', path) for path in [
'HG00187.hg38.g.vcf.gz', 'HG00190.hg38.g.vcf.gz',
'HG00308.hg38.g.vcf.gz', 'HG00313.hg38.g.vcf.gz',
'HG00320.hg38.g.vcf.gz'
]
]
parts = [
hl.Interval(start=hl.Struct(
locus=hl.Locus('chr22', 1, reference_genome='GRCh38')),
end=hl.Struct(locus=hl.Locus(
'chr22',
hl.get_reference('GRCh38').contig_length('chr22') - 1,
reference_genome='GRCh38')),
includes_end=True)
]
vcfs = hl.import_gvcfs(paths,
parts,
reference_genome='GRCh38',
array_elements_required=False)
to_keep = defined_entry_fields(
vcfs[0].filter_rows(hl.is_defined(vcfs[0].info.END)), 100_000)
vds = hl.vds.combiner.combine_variant_datasets(
[hl.vds.combiner.transform_gvcf(mt, to_keep) for mt in vcfs])
vds.variant_data = vds.variant_data._key_rows_by_assert_sorted(
'locus', 'alleles')
vds.write(os.path.join(resource('vds'), '1kg_chr22_5_samples.vds'),
overwrite=True)
def read_with_index_p1000():
rows = 10_000_000
bins = 1_000
width = rows // bins
intervals = [hl.Interval(start=i, end=i + width) for i in range(0, rows, width)]
ht = hl.read_table(resource('table_10M_par_10.ht'), _intervals=intervals)
ht._force_count()
def read_with_index_p1000(path):
rows = 10_000_000
bins = 1_000
width = rows // bins
intervals = [hl.Interval(start=i, end=i + width) for i in range(0, rows, width)]
ht = hl.read_table(path, _intervals=intervals)
ht._force_count()
def default_exome_intervals(reference_genome) -> List[hl.utils.Interval]:
"""create a list of locus intervals suitable for importing and merging exome gvcfs. As exomes
are small. One partition per chromosome works well here.
Parameters
----------
reference_genome: :obj:`str` or :class:`.ReferenceGenome`, optional
Reference genome to use. NOTE: only GRCh37 and GRCh38 references
are supported.
Returns
-------
:obj:`List[Interval]`
"""
if reference_genome.name == 'GRCh37':
contigs = [f'{i}' for i in range(1, 23)] + ['X', 'Y', 'MT']
elif reference_genome.name == 'GRCh38':
contigs = [f'chr{i}' for i in range(1, 23)] + ['chrX', 'chrY', 'chrM']
else:
raise ValueError(
f"Invalid reference genome '{reference_genome.name}', only 'GRCh37' and 'GRCh38' are supported"
)
return [
hl.Interval(start=hl.Locus(contig=contig,
position=1,
reference_genome=reference_genome),
end=hl.Locus.parse(f'{contig}:END',
reference_genome=reference_genome),
includes_end=True) for contig in contigs
]
def test_order_by_intervals(self):
intervals = {0: hl.Interval(0, 3, includes_start=True, includes_end=False),
1: hl.Interval(0, 4, includes_start=True, includes_end=True),
2: hl.Interval(1, 4, includes_start=True, includes_end=False),
3: hl.Interval(0, 4, includes_start=False, includes_end=False),
4: hl.Interval(0, 4, includes_start=True, includes_end=False)}
ht = hl.utils.range_table(5)
ht = ht.annotate_globals(ilist=intervals)
ht = ht.annotate(interval=ht['ilist'][ht['idx']])
ht = ht.order_by(ht['interval'])
ordered = ht['interval'].collect()
expected = [intervals[i] for i in [0, 4, 1, 3, 2]]
self.assertEqual(ordered, expected)
def __init__(self, name, contigs, lengths, x_contigs=[], y_contigs=[], mt_contigs=[], par=[], _builtin=False):
super(ReferenceGenome, self).__init__()
contigs = wrap_to_list(contigs)
x_contigs = wrap_to_list(x_contigs)
y_contigs = wrap_to_list(y_contigs)
mt_contigs = wrap_to_list(mt_contigs)
self._config = {
'name': name,
'contigs': [{'name': c, 'length': l} for c, l in lengths.items()],
'xContigs': x_contigs,
'yContigs': y_contigs,
'mtContigs': mt_contigs,
'par': [{'start': {'contig': c, 'position': s}, 'end': {'contig': c, 'position': e}} for (c, s, e) in par]
}
self._contigs = contigs
self._lengths = lengths
self._par_tuple = par
self._par = [hl.Interval(hl.Locus(c, s, self), hl.Locus(c, e, self)) for (c, s, e) in par]
self._global_positions = None
ReferenceGenome._references[name] = self
if not _builtin:
Env.backend().add_reference(self._config)
hl.ir.register_reference_genome_functions(name)
self._has_sequence = False
self._liftovers = set()
def test_filter_intervals_compound_partition_key(self):
ds = hl.import_vcf(resource('sample.vcf'), min_partitions=20)
ds = (ds.annotate_rows(variant=hl.struct(locus=ds.locus, alleles=ds.alleles))
.key_rows_by('locus', 'alleles'))
intervals = [hl.Interval(hl.Struct(locus=hl.Locus('20', 10639222), alleles=['A', 'T']),
hl.Struct(locus=hl.Locus('20', 10644700), alleles=['A', 'T']))]
self.assertEqual(hl.filter_intervals(ds, intervals).count_rows(), 3)
def locus_interval(start, end):
return hl.Interval(start=hl.Locus(
contig=contig,
position=start,
reference_genome=reference_genome),
end=hl.Locus(contig=contig,
position=end,
reference_genome=reference_genome),
includes_end=True)
def read(fname: str) -> 'DNDArray':
# read without good partitioning, just to get the globals
a = DNDArray(hl.read_table(fname))
t = hl.read_table(fname, _intervals=[
hl.Interval(hl.Struct(r=i, c=j),
hl.Struct(r=i, c=j + 1))
for i in range(a.n_block_rows)
for j in range(a.n_block_cols)])
return DNDArray(t)
def assert_rg_loaded_correctly(name):
rg = hl.get_reference(name)
self.assertEqual(rg.contigs, ["1", "X", "Y", "MT"])
self.assertEqual(rg.lengths, {"1": 5, "X": 4, "Y": 3, "MT": 2})
self.assertEqual(rg.x_contigs, ["X"])
self.assertEqual(rg.y_contigs, ["Y"])
self.assertEqual(rg.mt_contigs, ["MT"])
self.assertEqual(rg.par, [
hl.Interval(start=hl.Locus("X", 2, name),
end=hl.Locus("X", 4, name))
])
def get_n_even_intervals(n):
ref = hl.default_reference()
genome_size = sum(ref.lengths.values())
partition_size = int(genome_size / n) + 1
return list(
map(
lambda x: hl.Interval(
hl.eval(hl.locus_from_global_position(x * partition_size)),
hl.eval(
hl.locus_from_global_position(
min(x * partition_size + partition_size, genome_size -
1)))), range(n)))
def calculate_new_intervals(ht, n, reference_genome):
"""takes a table, keyed by ['locus', ...] and produces a list of intervals suitable
for repartitioning a combiner matrix table
Parameters
----------
ht : :class:`.Table`
Table / Rows Table to compute new intervals for
n : :obj:`int`
Number of rows each partition should have, (last partition may be smaller)
reference_genome: :obj:`str` or :class:`.ReferenceGenome`, optional
Reference genome to use.
Returns
-------
:obj:`List[Interval]`
"""
assert list(ht.key) == ['locus']
assert ht.locus.dtype == hl.tlocus(reference_genome=reference_genome)
end = hl.Locus(reference_genome.contigs[-1],
reference_genome.lengths[reference_genome.contigs[-1]],
reference_genome=reference_genome)
n_rows = ht.count()
if n_rows == 0:
raise ValueError('empty table!')
ht = ht.select()
ht = ht.annotate(x=hl.scan.count())
ht = ht.annotate(y=ht.x + 1)
ht = ht.filter((ht.x // n != ht.y // n) | (ht.x == (n_rows - 1)))
ht = ht.select()
ht = ht.annotate(start=hl.or_else(
hl.scan._prev_nonnull(
hl.locus_from_global_position(ht.locus.global_position() + 1,
reference_genome=reference_genome)),
hl.locus_from_global_position(0, reference_genome=reference_genome)))
ht = ht.key_by()
ht = ht.select(
interval=hl.interval(start=ht.start, end=ht.locus, includes_end=True))
intervals = ht.aggregate(hl.agg.collect(ht.interval))
last_st = hl.eval(
hl.locus_from_global_position(
hl.literal(intervals[-1].end).global_position() + 1,
reference_genome=reference_genome))
interval = hl.Interval(start=last_st, end=end, includes_end=True)
intervals.append(interval)
return intervals
def test_gvcfs(spark, tmp_path):
# GVCF MatrixTables are not keyed by locus and alleles, just by locus
input_vcf = 'test-data/tabix-test-vcf/combined.chr20_18210071_18210093.g.vcf.gz'
partitions = [
hl.Interval(hl.Locus("chr20", 1, reference_genome='GRCh38'),
hl.Locus("chr20", 20000000, reference_genome='GRCh38'),
includes_end=True)
]
hail_df = functions.from_matrix_table(
hl.import_gvcfs([input_vcf],
partitions,
force_bgz=True,
reference_genome='GRCh38')[0])
_assert_lossless_adapter(spark, tmp_path, hail_df, input_vcf, 'vcf',
'bigvcf')
def values(self):
values = [(hl.tbool, True), (hl.tint32, 0), (hl.tint64, 0),
(hl.tfloat32, 0.5), (hl.tfloat64, 0.5), (hl.tstr, "foo"),
(hl.tstruct(x=hl.tint32), hl.Struct(x=0)),
(hl.tarray(hl.tint32), [0, 1, 4]),
(hl.tset(hl.tint32), {0, 1, 4}),
(hl.tdict(hl.tstr, hl.tint32), {
"a": 0,
"b": 1,
"c": 4
}), (hl.tinterval(hl.tint32), hl.Interval(0, 1, True,
False)),
(hl.tlocus(hl.default_reference()), hl.Locus("1", 1)),
(hl.tcall, hl.Call([0, 1]))]
return values
def __init__(self, path, intervals, filter_intervals):
if intervals is not None:
t = hl.expr.impute_type(intervals)
if not isinstance(t, hl.tarray) and not isinstance(t.element_type, hl.tinterval):
raise TypeError("'intervals' must be an array of tintervals")
pt = t.element_type.point_type
if isinstance(pt, hl.tstruct):
self._interval_type = t
else:
self._interval_type = hl.tarray(hl.tinterval(hl.tstruct(__point=pt)))
self.path = path
self.filter_intervals = filter_intervals
if intervals is not None and t != self._interval_type:
self.intervals = [hl.Interval(hl.Struct(__point=i.start),
hl.Struct(__point=i.end),
i.includes_start,
i.includes_end) for i in intervals]
else:
self.intervals = intervals
def union_intervals(intervals: List[hl.Interval], is_sorted: bool = False):
"""
Generate a list with the union of all intervals in the input list by merging overlapping intervals.
:param intervals: Intervals to merge
:param is_sorted: If set, assumes intervals are already sorted, otherwise will sort.
:return: List of merged intervals
"""
sorted_intervals = intervals if is_sorted else sort_intervals(intervals)
merged_intervals = sorted_intervals[:1]
for interval in sorted_intervals[1:]:
if merged_intervals[-1].start.contig == interval.start.contig:
if merged_intervals[-1].end.position < interval.end.position:
if interval.start.position <= merged_intervals[-1].end.position:
merged_intervals[-1] = hl.Interval(
merged_intervals[-1].start, interval.end)
else:
merged_intervals.append(interval)
else:
merged_intervals.append(interval)
return merged_intervals
def read_with_index_p50k():
intervals = [hl.Interval(start=i, end=i + 200) for i in range(0, 10_000_000, 200)]
ht = hl.read_table(resource('table_10M_par_10.ht'), _intervals=intervals)
ht._force_count()
def from_matrix_table(
mt: MatrixTable,
entrc_field: str,
*,
n_partitions: Optional[int] = None,
block_size: Optional[int] = None
) -> 'DNDArray':
if n_partitions is None:
n_partitions = mt.n_partitions()
if block_size is None:
block_size = DNDArray.default_block_size
if n_partitions == 0:
assert mt.count_cols() == 0
assert mt.count_rows() == 0
t = range_table(0, 0)
t = t.annotate(r=0, c=0, block=nd.array([]).reshape((0, 0)))
t = t.select_globals(
r_field='r',
c_field='c',
n_rows=0,
n_cols=0,
n_block_rows=0,
n_block_cols=0,
block_size=0)
return DNDArray(t)
assert 'r' not in mt.row
assert 'c' not in mt.row
assert 'block' not in mt.row
n_rows, n_cols = mt.count()
n_block_rows = (n_rows + block_size - 1) // block_size
n_block_cols = (n_cols + block_size - 1) // block_size
entries, cols, row_index, col_blocks = (Env.get_uid() for _ in range(4))
mt = (mt
.select_globals()
.select_rows()
.select_cols()
.add_row_index(row_index)
.localize_entries(entries, cols))
# FIXME: remove when ndarray support structs
mt = mt.annotate(**{entries: mt[entries][entrc_field]})
mt = mt.annotate(
**{col_blocks: hl.range(n_block_cols).map(
lambda c: hl.struct(
c=c,
entries=mt[entries][(c * block_size):((c + 1) * block_size)]))}
)
mt = mt.explode(col_blocks)
mt = mt.select(row_index, **mt[col_blocks])
mt = mt.annotate(r=hl.int(mt[row_index] // block_size))
mt = mt.key_by(mt.r, mt.c)
mt = mt.group_by(mt.r, mt.c).aggregate(
entries=hl.sorted(
hl.agg.collect(hl.struct(row_index=mt[row_index], entries=mt.entries)),
key=lambda x: x.row_index
).map(lambda x: x.entries))
mt = mt.select(block=hl.nd.array(mt.entries))
mt = mt.select_globals(
r_field='r',
c_field='c',
n_rows=n_rows,
n_cols=n_cols,
n_block_rows=n_block_rows,
n_block_cols=n_block_cols,
block_size=block_size)
fname = new_temp_file()
mt = mt.key_by(mt.r, mt.c)
mt.write(fname, _codec_spec=DNDArray.fast_codec_spec)
t = hl.read_table(fname, _intervals=[
hl.Interval(hl.Struct(r=i, c=j),
hl.Struct(r=i, c=j + 1))
for i in range(n_block_rows)
for j in range(n_block_cols)])
return DNDArray(t)
def from_matrix_table(
mt: MatrixTable,
entry_field: str,
*,
n_partitions: Optional[int] = None,
block_size: Optional[int] = None,
sort_columns: bool = False
) -> 'DNDArray':
if n_partitions is None:
n_partitions = mt.n_partitions()
if block_size is None:
block_size = DNDArray.default_block_size
if n_partitions == 0:
assert mt.count_cols() == 0
assert mt.count_rows() == 0
t = range_table(0, 0)
t = t.annotate(r=0, c=0, block=nd.array([]).reshape((0, 0)))
t = t.select_globals(
n_rows=0,
n_cols=0,
n_block_rows=0,
n_block_cols=0,
block_size=0)
return DNDArray(t)
assert 'r' not in mt.row
assert 'c' not in mt.row
assert 'block' not in mt.row
n_rows, n_cols = mt.count()
n_block_rows = (n_rows + block_size - 1) // block_size
n_block_cols = (n_cols + block_size - 1) // block_size
entries, cols, row_index, col_blocks = (Env.get_uid() for _ in range(4))
if sort_columns:
col_index = Env.get_uid()
col_order = mt.add_col_index(col_index)
col_order = col_order.key_cols_by().cols()
col_order = col_order.select(key=col_order.row.select(*mt.col_key),
index=col_order[col_index])
col_order = col_order.collect(_localize=False)
col_order = hl.sorted(col_order, key=lambda x: x.key)
col_order = col_order['index'].collect()[0]
mt = mt.choose_cols(col_order)
else:
col_keys = mt.col_key.collect(_localize=False)
out_of_order = hl.range(hl.len(col_keys) - 1).map(
lambda i: col_keys[i] > col_keys[i + 1])
out_of_order = out_of_order.collect()[0]
if any(out_of_order):
raise ValueError(
'from_matrix_table: columns are not in sorted order. You may request a '
'sort with sort_columns=True.')
mt = (mt
.select_globals()
.select_rows()
.select_cols()
.add_row_index(row_index)
.localize_entries(entries, cols))
# FIXME: remove when ndarray support structs
mt = mt.annotate(**{entries: mt[entries][entry_field]})
mt = mt.annotate(
**{col_blocks: hl.range(n_block_cols).map(
lambda c: hl.struct(
c=c,
entries=mt[entries][(c * block_size):((c + 1) * block_size)]))}
)
mt = mt.explode(col_blocks)
mt = mt.select(row_index, **mt[col_blocks])
mt = mt.annotate(r=hl.int(mt[row_index] // block_size))
mt = mt.key_by(mt.r, mt.c)
mt = mt.group_by(mt.r, mt.c).aggregate(
entries=hl.sorted(
hl.agg.collect(hl.struct(row_index=mt[row_index], entries=mt.entries)),
key=lambda x: x.row_index
).map(lambda x: x.entries))
mt = mt.select(block=hl.nd.array(mt.entries))
mt = mt.select_globals(
n_rows=n_rows,
n_cols=n_cols,
n_block_rows=n_block_rows,
n_block_cols=n_block_cols,
block_size=block_size)
fname = new_temp_file()
mt = mt.key_by(mt.r, mt.c)
mt.write(fname, _codec_spec=DNDArray.fast_codec_spec)
t = hl.read_table(fname, _intervals=[
hl.Interval(hl.Struct(r=i, c=j),
hl.Struct(r=i, c=j + 1))
for i in range(n_block_rows)
for j in range(n_block_cols)])
return DNDArray(t)
def generate_datasets(doctest_namespace, output_dir):
doctest_namespace['hl'] = hl
files = ["sample.vds", "sample.qc.vds", "sample.filtered.vds"]
for f in files:
if os.path.isdir(f):
shutil.rmtree(f)
ds = hl.import_vcf('data/sample.vcf.bgz')
ds = ds.sample_rows(0.03)
ds = ds.annotate_rows(use_as_marker=hl.rand_bool(0.5),
panel_maf=0.1,
anno1=5,
anno2=0,
consequence="LOF",
gene="A",
score=5.0)
ds = ds.annotate_rows(a_index=1)
ds = hl.sample_qc(hl.variant_qc(ds))
ds = ds.annotate_cols(is_case=True,
pheno=hl.struct(is_case=hl.rand_bool(0.5),
is_female=hl.rand_bool(0.5),
age=hl.rand_norm(65, 10),
height=hl.rand_norm(70, 10),
blood_pressure=hl.rand_norm(120, 20),
cohort_name="cohort1"),
cov=hl.struct(PC1=hl.rand_norm(0, 1)),
cov1=hl.rand_norm(0, 1),
cov2=hl.rand_norm(0, 1),
cohort="SIGMA")
ds = ds.annotate_globals(
global_field_1=5,
global_field_2=10,
pli={
'SCN1A': 0.999,
'SONIC': 0.014
},
populations=['AFR', 'EAS', 'EUR', 'SAS', 'AMR', 'HIS'])
ds = ds.annotate_rows(gene=['TTN'])
ds = ds.annotate_cols(cohorts=['1kg'], pop='EAS')
ds = ds.checkpoint(f'{output_dir.name}/example.vds', overwrite=True)
doctest_namespace['ds'] = ds
doctest_namespace['dataset'] = ds
doctest_namespace['dataset2'] = ds.annotate_globals(global_field=5)
doctest_namespace['dataset_to_union_1'] = ds
doctest_namespace['dataset_to_union_2'] = ds
v_metadata = ds.rows().annotate_globals(global_field=5).annotate(
consequence='SYN')
doctest_namespace['v_metadata'] = v_metadata
s_metadata = ds.cols().annotate(pop='AMR', is_case=False, sex='F')
doctest_namespace['s_metadata'] = s_metadata
doctest_namespace['cols_to_keep'] = s_metadata
doctest_namespace['cols_to_remove'] = s_metadata
doctest_namespace['rows_to_keep'] = v_metadata
doctest_namespace['rows_to_remove'] = v_metadata
# Table
table1 = hl.import_table('data/kt_example1.tsv', impute=True, key='ID')
table1 = table1.annotate_globals(global_field_1=5, global_field_2=10)
doctest_namespace['table1'] = table1
doctest_namespace['other_table'] = table1
table2 = hl.import_table('data/kt_example2.tsv', impute=True, key='ID')
doctest_namespace['table2'] = table2
table4 = hl.import_table('data/kt_example4.tsv',
impute=True,
types={
'B': hl.tstruct(B0=hl.tbool, B1=hl.tstr),
'D': hl.tstruct(cat=hl.tint32, dog=hl.tint32),
'E': hl.tstruct(A=hl.tint32, B=hl.tint32)
})
doctest_namespace['table4'] = table4
people_table = hl.import_table('data/explode_example.tsv',
delimiter='\\s+',
types={
'Age': hl.tint32,
'Children': hl.tarray(hl.tstr)
},
key='Name')
doctest_namespace['people_table'] = people_table
# TDT
doctest_namespace['tdt_dataset'] = hl.import_vcf('data/tdt_tiny.vcf')
ds2 = hl.variant_qc(ds)
doctest_namespace['ds2'] = ds2.select_rows(AF=ds2.variant_qc.AF)
# Expressions
doctest_namespace['names'] = hl.literal(['Alice', 'Bob', 'Charlie'])
doctest_namespace['a1'] = hl.literal([0, 1, 2, 3, 4, 5])
doctest_namespace['a2'] = hl.literal([1, -1, 1, -1, 1, -1])
doctest_namespace['t'] = hl.literal(True)
doctest_namespace['f'] = hl.literal(False)
doctest_namespace['na'] = hl.null(hl.tbool)
doctest_namespace['call'] = hl.call(0, 1, phased=False)
doctest_namespace['a'] = hl.literal([1, 2, 3, 4, 5])
doctest_namespace['d'] = hl.literal({
'Alice': 43,
'Bob': 33,
'Charles': 44
})
doctest_namespace['interval'] = hl.interval(3, 11)
doctest_namespace['locus_interval'] = hl.parse_locus_interval(
"1:53242-90543")
doctest_namespace['locus'] = hl.locus('1', 1034245)
doctest_namespace['x'] = hl.literal(3)
doctest_namespace['y'] = hl.literal(4.5)
doctest_namespace['s1'] = hl.literal({1, 2, 3})
doctest_namespace['s2'] = hl.literal({1, 3, 5})
doctest_namespace['s3'] = hl.literal({'Alice', 'Bob', 'Charlie'})
doctest_namespace['struct'] = hl.struct(a=5, b='Foo')
doctest_namespace['tup'] = hl.literal(("a", 1, [1, 2, 3]))
doctest_namespace['s'] = hl.literal('The quick brown fox')
doctest_namespace['interval2'] = hl.Interval(3, 6)
doctest_namespace['nd'] = hl._ndarray([[1, 2], [3, 4]])
# Overview
doctest_namespace['ht'] = hl.import_table("data/kt_example1.tsv",
impute=True)
doctest_namespace['mt'] = ds
gnomad_data = ds.rows()
doctest_namespace['gnomad_data'] = gnomad_data.select(gnomad_data.info.AF)
# BGEN
bgen = hl.import_bgen('data/example.8bits.bgen',
entry_fields=['GT', 'GP', 'dosage'])
doctest_namespace['variants_table'] = bgen.rows()
burden_ds = hl.import_vcf('data/example_burden.vcf')
burden_kt = hl.import_table('data/example_burden.tsv',
key='Sample',
impute=True)
burden_ds = burden_ds.annotate_cols(burden=burden_kt[burden_ds.s])
burden_ds = burden_ds.annotate_rows(
weight=hl.float64(burden_ds.locus.position))
burden_ds = hl.variant_qc(burden_ds)
genekt = hl.import_locus_intervals('data/gene.interval_list')
burden_ds = burden_ds.annotate_rows(gene=genekt[burden_ds.locus])
burden_ds = burden_ds.checkpoint(f'{output_dir.name}/example_burden.vds',
overwrite=True)
doctest_namespace['burden_ds'] = burden_ds
print("finished setting up doctest...")
def generate_datasets(doctest_namespace):
doctest_namespace['hl'] = hl
doctest_namespace['np'] = np
ds = hl.import_vcf('data/sample.vcf.bgz')
ds = ds.sample_rows(0.03)
ds = ds.annotate_rows(use_as_marker=hl.rand_bool(0.5),
panel_maf=0.1,
anno1=5,
anno2=0,
consequence="LOF",
gene="A",
score=5.0)
ds = ds.annotate_rows(a_index=1)
ds = hl.sample_qc(hl.variant_qc(ds))
ds = ds.annotate_cols(is_case=True,
pheno=hl.struct(is_case=hl.rand_bool(0.5),
is_female=hl.rand_bool(0.5),
age=hl.rand_norm(65, 10),
height=hl.rand_norm(70, 10),
blood_pressure=hl.rand_norm(120, 20),
cohort_name="cohort1"),
cov=hl.struct(PC1=hl.rand_norm(0, 1)),
cov1=hl.rand_norm(0, 1),
cov2=hl.rand_norm(0, 1),
cohort="SIGMA")
ds = ds.annotate_globals(
global_field_1=5,
global_field_2=10,
pli={
'SCN1A': 0.999,
'SONIC': 0.014
},
populations=['AFR', 'EAS', 'EUR', 'SAS', 'AMR', 'HIS'])
ds = ds.annotate_rows(gene=['TTN'])
ds = ds.annotate_cols(cohorts=['1kg'], pop='EAS')
ds = ds.checkpoint(f'output/example.mt', overwrite=True)
doctest_namespace['ds'] = ds
doctest_namespace['dataset'] = ds
doctest_namespace['dataset2'] = ds.annotate_globals(global_field=5)
doctest_namespace['dataset_to_union_1'] = ds
doctest_namespace['dataset_to_union_2'] = ds
v_metadata = ds.rows().annotate_globals(global_field=5).annotate(
consequence='SYN')
doctest_namespace['v_metadata'] = v_metadata
s_metadata = ds.cols().annotate(pop='AMR', is_case=False, sex='F')
doctest_namespace['s_metadata'] = s_metadata
doctest_namespace['cols_to_keep'] = s_metadata
doctest_namespace['cols_to_remove'] = s_metadata
doctest_namespace['rows_to_keep'] = v_metadata
doctest_namespace['rows_to_remove'] = v_metadata
small_mt = hl.balding_nichols_model(3, 4, 4)
doctest_namespace['small_mt'] = small_mt.checkpoint('output/small.mt',
overwrite=True)
# Table
table1 = hl.import_table('data/kt_example1.tsv', impute=True, key='ID')
table1 = table1.annotate_globals(global_field_1=5, global_field_2=10)
doctest_namespace['table1'] = table1
doctest_namespace['other_table'] = table1
table2 = hl.import_table('data/kt_example2.tsv', impute=True, key='ID')
doctest_namespace['table2'] = table2
table4 = hl.import_table('data/kt_example4.tsv',
impute=True,
types={
'B': hl.tstruct(B0=hl.tbool, B1=hl.tstr),
'D': hl.tstruct(cat=hl.tint32, dog=hl.tint32),
'E': hl.tstruct(A=hl.tint32, B=hl.tint32)
})
doctest_namespace['table4'] = table4
people_table = hl.import_table('data/explode_example.tsv',
delimiter='\\s+',
types={
'Age': hl.tint32,
'Children': hl.tarray(hl.tstr)
},
key='Name')
doctest_namespace['people_table'] = people_table
# TDT
doctest_namespace['tdt_dataset'] = hl.import_vcf('data/tdt_tiny.vcf')
ds2 = hl.variant_qc(ds)
doctest_namespace['ds2'] = ds2.select_rows(AF=ds2.variant_qc.AF)
# Expressions
doctest_namespace['names'] = hl.literal(['Alice', 'Bob', 'Charlie'])
doctest_namespace['a1'] = hl.literal([0, 1, 2, 3, 4, 5])
doctest_namespace['a2'] = hl.literal([1, -1, 1, -1, 1, -1])
doctest_namespace['t'] = hl.literal(True)
doctest_namespace['f'] = hl.literal(False)
doctest_namespace['na'] = hl.null(hl.tbool)
doctest_namespace['call'] = hl.call(0, 1, phased=False)
doctest_namespace['a'] = hl.literal([1, 2, 3, 4, 5])
doctest_namespace['d'] = hl.literal({
'Alice': 43,
'Bob': 33,
'Charles': 44
})
doctest_namespace['interval'] = hl.interval(3, 11)
doctest_namespace['locus_interval'] = hl.parse_locus_interval(
"1:53242-90543")
doctest_namespace['locus'] = hl.locus('1', 1034245)
doctest_namespace['x'] = hl.literal(3)
doctest_namespace['y'] = hl.literal(4.5)
doctest_namespace['s1'] = hl.literal({1, 2, 3})
doctest_namespace['s2'] = hl.literal({1, 3, 5})
doctest_namespace['s3'] = hl.literal({'Alice', 'Bob', 'Charlie'})
doctest_namespace['struct'] = hl.struct(a=5, b='Foo')
doctest_namespace['tup'] = hl.literal(("a", 1, [1, 2, 3]))
doctest_namespace['s'] = hl.literal('The quick brown fox')
doctest_namespace['interval2'] = hl.Interval(3, 6)
doctest_namespace['nd'] = hl._nd.array([[1, 2], [3, 4]])
# Overview
doctest_namespace['ht'] = hl.import_table("data/kt_example1.tsv",
impute=True)
doctest_namespace['mt'] = ds
gnomad_data = ds.rows()
doctest_namespace['gnomad_data'] = gnomad_data.select(gnomad_data.info.AF)
# BGEN
bgen = hl.import_bgen('data/example.8bits.bgen',
entry_fields=['GT', 'GP', 'dosage'])
doctest_namespace['variants_table'] = bgen.rows()
burden_ds = hl.import_vcf('data/example_burden.vcf')
burden_kt = hl.import_table('data/example_burden.tsv',
key='Sample',
impute=True)
burden_ds = burden_ds.annotate_cols(burden=burden_kt[burden_ds.s])
burden_ds = burden_ds.annotate_rows(
weight=hl.float64(burden_ds.locus.position))
burden_ds = hl.variant_qc(burden_ds)
genekt = hl.import_locus_intervals('data/gene.interval_list')
burden_ds = burden_ds.annotate_rows(gene=genekt[burden_ds.locus])
burden_ds = burden_ds.checkpoint(f'output/example_burden.vds',
overwrite=True)
doctest_namespace['burden_ds'] = burden_ds
ld_score_one_pheno_sumstats = hl.import_table(
'data/ld_score_regression.one_pheno.sumstats.tsv',
types={
'locus': hl.tlocus('GRCh37'),
'alleles': hl.tarray(hl.tstr),
'chi_squared': hl.tfloat64,
'n': hl.tint32,
'ld_score': hl.tfloat64,
'phenotype': hl.tstr,
'chi_squared_50_irnt': hl.tfloat64,
'n_50_irnt': hl.tint32,
'chi_squared_20160': hl.tfloat64,
'n_20160': hl.tint32
},
key=['locus', 'alleles'])
doctest_namespace[
'ld_score_one_pheno_sumstats'] = ld_score_one_pheno_sumstats
mt = hl.import_matrix_table(
'data/ld_score_regression.all_phenos.sumstats.tsv',
row_fields={
'locus': hl.tstr,
'alleles': hl.tstr,
'ld_score': hl.tfloat64
},
entry_type=hl.tstr)
mt = mt.key_cols_by(phenotype=mt.col_id)
mt = mt.key_rows_by(locus=hl.parse_locus(mt.locus),
alleles=mt.alleles.split(','))
mt = mt.drop('row_id', 'col_id')
mt = mt.annotate_entries(x=mt.x.split(","))
mt = mt.transmute_entries(chi_squared=hl.float64(mt.x[0]),
n=hl.int32(mt.x[1]))
mt = mt.annotate_rows(ld_score=hl.float64(mt.ld_score))
doctest_namespace['ld_score_all_phenos_sumstats'] = mt
print("finished setting up doctest...")
def generate_datasets(doctest_namespace):
doctest_namespace['hl'] = hl
if not os.path.isdir("output/"):
try:
os.mkdir("output/")
except OSError:
pass
files = ["sample.vds", "sample.qc.vds", "sample.filtered.vds"]
for f in files:
if os.path.isdir(f):
shutil.rmtree(f)
ds = hl.read_matrix_table('data/example.vds')
doctest_namespace['ds'] = ds
doctest_namespace['dataset'] = ds
doctest_namespace['dataset2'] = ds.annotate_globals(global_field=5)
doctest_namespace['dataset_to_union_1'] = ds
doctest_namespace['dataset_to_union_2'] = ds
v_metadata = ds.rows().annotate_globals(global_field=5).annotate(
consequence='SYN')
doctest_namespace['v_metadata'] = v_metadata
s_metadata = ds.cols().annotate(pop='AMR', is_case=False, sex='F')
doctest_namespace['s_metadata'] = s_metadata
doctest_namespace['cols_to_keep'] = s_metadata
doctest_namespace['cols_to_remove'] = s_metadata
doctest_namespace['rows_to_keep'] = v_metadata
doctest_namespace['rows_to_remove'] = v_metadata
# Table
table1 = hl.import_table('data/kt_example1.tsv', impute=True, key='ID')
table1 = table1.annotate_globals(global_field_1=5, global_field_2=10)
doctest_namespace['table1'] = table1
doctest_namespace['other_table'] = table1
table2 = hl.import_table('data/kt_example2.tsv', impute=True, key='ID')
doctest_namespace['table2'] = table2
table4 = hl.import_table('data/kt_example4.tsv',
impute=True,
types={
'B': hl.tstruct(B0=hl.tbool, B1=hl.tstr),
'D': hl.tstruct(cat=hl.tint32, dog=hl.tint32),
'E': hl.tstruct(A=hl.tint32, B=hl.tint32)
})
doctest_namespace['table4'] = table4
people_table = hl.import_table('data/explode_example.tsv',
delimiter='\\s+',
types={
'Age': hl.tint32,
'Children': hl.tarray(hl.tstr)
},
key='Name')
doctest_namespace['people_table'] = people_table
# TDT
doctest_namespace['tdt_dataset'] = hl.import_vcf('data/tdt_tiny.vcf')
ds2 = hl.variant_qc(ds)
doctest_namespace['ds2'] = ds2.select_rows(AF=ds2.variant_qc.AF)
# Expressions
doctest_namespace['names'] = hl.literal(['Alice', 'Bob', 'Charlie'])
doctest_namespace['a1'] = hl.literal([0, 1, 2, 3, 4, 5])
doctest_namespace['a2'] = hl.literal([1, -1, 1, -1, 1, -1])
doctest_namespace['t'] = hl.literal(True)
doctest_namespace['f'] = hl.literal(False)
doctest_namespace['na'] = hl.null(hl.tbool)
doctest_namespace['call'] = hl.call(0, 1, phased=False)
doctest_namespace['a'] = hl.literal([1, 2, 3, 4, 5])
doctest_namespace['d'] = hl.literal({
'Alice': 43,
'Bob': 33,
'Charles': 44
})
doctest_namespace['interval'] = hl.interval(3, 11)
doctest_namespace['locus_interval'] = hl.parse_locus_interval(
"1:53242-90543")
doctest_namespace['locus'] = hl.locus('1', 1034245)
doctest_namespace['x'] = hl.literal(3)
doctest_namespace['y'] = hl.literal(4.5)
doctest_namespace['s1'] = hl.literal({1, 2, 3})
doctest_namespace['s2'] = hl.literal({1, 3, 5})
doctest_namespace['s3'] = hl.literal({'Alice', 'Bob', 'Charlie'})
doctest_namespace['struct'] = hl.struct(a=5, b='Foo')
doctest_namespace['tup'] = hl.literal(("a", 1, [1, 2, 3]))
doctest_namespace['s'] = hl.literal('The quick brown fox')
doctest_namespace['interval2'] = hl.Interval(3, 6)
doctest_namespace['nd'] = hl._ndarray([[1, 2], [3, 4]])
# Overview
doctest_namespace['ht'] = hl.import_table("data/kt_example1.tsv",
impute=True)
doctest_namespace['mt'] = ds
gnomad_data = ds.rows()
doctest_namespace['gnomad_data'] = gnomad_data.select(gnomad_data.info.AF)
# BGEN
bgen = hl.import_bgen('data/example.8bits.bgen',
entry_fields=['GT', 'GP', 'dosage'])
doctest_namespace['variants_table'] = bgen.rows()
print("finished setting up doctest...")