def test_liftover_strand(self):
grch37 = hl.get_reference('GRCh37')
grch37.add_liftover(resource('grch37_to_grch38_chr20.over.chain.gz'),
'GRCh38')
self.assertEqual(
hl.eval(
hl.liftover(hl.locus('20', 60001, 'GRCh37'),
'GRCh38',
include_strand=True)),
hl.eval(
hl.struct(result=hl.locus('chr20', 79360, 'GRCh38'),
is_negative_strand=False)))
self.assertEqual(
hl.eval(
hl.liftover(hl.locus_interval('20', 37007582, 37007586, True,
True, 'GRCh37'),
'GRCh38',
include_strand=True)),
hl.eval(
hl.struct(result=hl.locus_interval('chr12', 32563117, 32563121,
True, True, 'GRCh38'),
is_negative_strand=True)))
with self.assertRaises(FatalError):
hl.eval(
hl.liftover(
hl.parse_locus_interval('1:10000-10000',
reference_genome='GRCh37'),
'GRCh38'))
grch37.remove_liftover("GRCh38")
def test_reference_genome_liftover(self):
grch37 = hl.get_reference('GRCh37')
grch38 = hl.get_reference('GRCh38')
self.assertTrue(not grch37.has_liftover('GRCh38') and not grch38.has_liftover('GRCh37'))
grch37.add_liftover(resource('grch37_to_grch38_chr20.over.chain.gz'), 'GRCh38')
grch38.add_liftover(resource('grch38_to_grch37_chr20.over.chain.gz'), 'GRCh37')
assert grch37.has_liftover('GRCh38')
assert grch38.has_liftover('GRCh37')
ds = hl.import_vcf(resource('sample.vcf'))
t = ds.annotate_rows(liftover=hl.liftover(hl.liftover(ds.locus, 'GRCh38'), 'GRCh37')).rows()
assert t.all(t.locus == t.liftover)
null_locus = hl.null(hl.tlocus('GRCh38'))
rows = [
{'l37': hl.locus('20', 1, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 60000, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 60001, 'GRCh37'), 'l38': hl.locus('chr20', 79360, 'GRCh38')},
{'l37': hl.locus('20', 278686, 'GRCh37'), 'l38': hl.locus('chr20', 298045, 'GRCh38')},
{'l37': hl.locus('20', 278687, 'GRCh37'), 'l38': hl.locus('chr20', 298046, 'GRCh38')},
{'l37': hl.locus('20', 278688, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278689, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278690, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278691, 'GRCh37'), 'l38': hl.locus('chr20', 298047, 'GRCh38')},
{'l37': hl.locus('20', 37007586, 'GRCh37'), 'l38': hl.locus('chr12', 32563117, 'GRCh38')},
{'l37': hl.locus('20', 62965520, 'GRCh37'), 'l38': hl.locus('chr20', 64334167, 'GRCh38')},
{'l37': hl.locus('20', 62965521, 'GRCh37'), 'l38': null_locus}
]
schema = hl.tstruct(l37=hl.tlocus(grch37), l38=hl.tlocus(grch38))
t = hl.Table.parallelize(rows, schema)
self.assertTrue(t.all(hl.cond(hl.is_defined(t.l38),
hl.liftover(t.l37, 'GRCh38') == t.l38,
hl.is_missing(hl.liftover(t.l37, 'GRCh38')))))
t = t.filter(hl.is_defined(t.l38))
self.assertTrue(t.count() == 6)
t = t.key_by('l38')
t.count()
self.assertTrue(list(t.key) == ['l38'])
null_locus_interval = hl.null(hl.tinterval(hl.tlocus('GRCh38')))
rows = [
{'i37': hl.locus_interval('20', 1, 60000, True, False, 'GRCh37'), 'i38': null_locus_interval},
{'i37': hl.locus_interval('20', 60001, 82456, True, True, 'GRCh37'),
'i38': hl.locus_interval('chr20', 79360, 101815, True, True, 'GRCh38')}
]
schema = hl.tstruct(i37=hl.tinterval(hl.tlocus(grch37)), i38=hl.tinterval(hl.tlocus(grch38)))
t = hl.Table.parallelize(rows, schema)
self.assertTrue(t.all(hl.liftover(t.i37, 'GRCh38') == t.i38))
grch37.remove_liftover("GRCh38")
grch38.remove_liftover("GRCh37")
def test_reference_genome_liftover(self):
grch37 = hl.get_reference('GRCh37')
grch38 = hl.get_reference('GRCh38')
self.assertTrue(not grch37.has_liftover('GRCh38') and not grch38.has_liftover('GRCh37'))
grch37.add_liftover(resource('grch37_to_grch38_chr20.over.chain.gz'), 'GRCh38')
grch38.add_liftover(resource('grch38_to_grch37_chr20.over.chain.gz'), 'GRCh37')
self.assertTrue(grch37.has_liftover('GRCh38') and grch38.has_liftover('GRCh37'))
ds = hl.import_vcf(resource('sample.vcf'))
t = ds.annotate_rows(liftover=hl.liftover(hl.liftover(ds.locus, 'GRCh38'), 'GRCh37')).rows()
self.assertTrue(t.all(t.locus == t.liftover))
null_locus = hl.null(hl.tlocus('GRCh38'))
rows = [
{'l37': hl.locus('20', 1, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 60000, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 60001, 'GRCh37'), 'l38': hl.locus('chr20', 79360, 'GRCh38')},
{'l37': hl.locus('20', 278686, 'GRCh37'), 'l38': hl.locus('chr20', 298045, 'GRCh38')},
{'l37': hl.locus('20', 278687, 'GRCh37'), 'l38': hl.locus('chr20', 298046, 'GRCh38')},
{'l37': hl.locus('20', 278688, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278689, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278690, 'GRCh37'), 'l38': null_locus},
{'l37': hl.locus('20', 278691, 'GRCh37'), 'l38': hl.locus('chr20', 298047, 'GRCh38')},
{'l37': hl.locus('20', 37007586, 'GRCh37'), 'l38': hl.locus('chr12', 32563117, 'GRCh38')},
{'l37': hl.locus('20', 62965520, 'GRCh37'), 'l38': hl.locus('chr20', 64334167, 'GRCh38')},
{'l37': hl.locus('20', 62965521, 'GRCh37'), 'l38': null_locus}
]
schema = hl.tstruct(l37=hl.tlocus(grch37), l38=hl.tlocus(grch38))
t = hl.Table.parallelize(rows, schema)
self.assertTrue(t.all(hl.cond(hl.is_defined(t.l38),
hl.liftover(t.l37, 'GRCh38') == t.l38,
hl.is_missing(hl.liftover(t.l37, 'GRCh38')))))
t = t.filter(hl.is_defined(t.l38))
self.assertTrue(t.count() == 6)
t = t.key_by('l38')
t.count()
self.assertTrue(list(t.key) == ['l38'])
null_locus_interval = hl.null(hl.tinterval(hl.tlocus('GRCh38')))
rows = [
{'i37': hl.locus_interval('20', 1, 60000, True, False, 'GRCh37'), 'i38': null_locus_interval},
{'i37': hl.locus_interval('20', 60001, 82456, True, True, 'GRCh37'),
'i38': hl.locus_interval('chr20', 79360, 101815, True, True, 'GRCh38')}
]
schema = hl.tstruct(i37=hl.tinterval(hl.tlocus(grch37)), i38=hl.tinterval(hl.tlocus(grch38)))
t = hl.Table.parallelize(rows, schema)
self.assertTrue(t.all(hl.liftover(t.i37, 'GRCh38') == t.i38))
grch37.remove_liftover("GRCh38")
grch38.remove_liftover("GRCh37")
def test_liftover_strand(self):
grch37 = hl.get_reference('GRCh37')
grch37.add_liftover(resource('grch37_to_grch38_chr20.over.chain.gz'), 'GRCh38')
self.assertEqual(hl.eval(hl.liftover(hl.locus('20', 60001, 'GRCh37'), 'GRCh38', include_strand=True)),
hl.eval(hl.struct(result=hl.locus('chr20', 79360, 'GRCh38'), is_negative_strand=False)))
self.assertEqual(hl.eval(hl.liftover(hl.locus_interval('20', 37007582, 37007586, True, True, 'GRCh37'),
'GRCh38', include_strand=True)),
hl.eval(hl.struct(result=hl.locus_interval('chr12', 32563117, 32563121, True, True, 'GRCh38'),
is_negative_strand=True)))
grch37.remove_liftover("GRCh38")
def _import_purcell_5k(path) -> hl.Table:
p5k = hl.import_locus_intervals(path, reference_genome='GRCh37')
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
if not rg37.has_liftover('GRCh38'):
rg37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', rg38)
p5k = p5k.annotate(start=hl.liftover(p5k.interval.start, 'GRCh38'),
end=hl.liftover(p5k.interval.start, 'GRCh38'))
p5k = p5k.filter((p5k.start.contig == 'chr' + p5k.interval.start.contig)
& (p5k.end.contig == 'chr' + p5k.interval.end.contig))
p5k = p5k.key_by()
p5k = p5k.select(locus=p5k.start, locus_b37=p5k.interval.start)
return p5k.key_by('locus')
def _import_purcell_5k(path) -> hl.Table:
p5k = hl.import_locus_intervals(path, reference_genome="GRCh37")
rg37 = hl.get_reference("GRCh37")
rg38 = hl.get_reference("GRCh38")
if not rg37.has_liftover("GRCh38"):
rg37.add_liftover("references/grch37_to_grch38.over.chain.gz", rg38)
p5k = p5k.annotate(
start=hl.liftover(p5k.interval.start, "GRCh38"),
end=hl.liftover(p5k.interval.start, "GRCh38"),
)
p5k = p5k.filter((p5k.start.contig == "chr" + p5k.interval.start.contig)
& (p5k.end.contig == "chr" + p5k.interval.end.contig))
p5k = p5k.key_by()
p5k = p5k.select(locus=p5k.start, locus_b37=p5k.interval.start)
return p5k.key_by("locus")
def get_liftover_v2_qc_mt(data_type: str,
ld_pruned: bool,
release_only: bool = False,
overwrite: bool = False) -> hl.MatrixTable:
"""
Returns MatrixTable for sample QC purposes on build 38: can be exomes, genomes, or joint (joint dataset can also be ld_pruned=True)
Criteria: callrate > 0.99, AF > 0.001, SNPs only, bi-allelics only
Note: sites where the locus changes chromosome are discarded
"""
path = qc_mt_path(data_type, ld_pruned, 'GRCh38')
if not overwrite and hl.hadoop_exists(path):
grch38_qc_mt = hl.read_matrix_table(path)
else:
grch38_qc_mt = hl.read_matrix_table(
qc_mt_path(data_type, ld_pruned=ld_pruned))
get_liftover_genome(grch38_qc_mt)
grch38_qc_mt = grch38_qc_mt.key_rows_by()
grch38_qc_mt = grch38_qc_mt.transmute_rows(locus=hl.liftover(
grch38_qc_mt.locus, 'GRCh38'),
locus37=grch38_qc_mt.locus)
grch38_qc_mt = grch38_qc_mt.filter_rows(
grch38_qc_mt.locus.contig == 'chr' + grch38_qc_mt.locus37.contig)
grch38_qc_mt = grch38_qc_mt.key_rows_by(locus=grch38_qc_mt.locus,
alleles=grch38_qc_mt.alleles)
grch38_qc_mt = grch38_qc_mt.checkpoint(path, overwrite=overwrite)
if release_only:
meta = get_gnomad_meta(data_type)
grch38_qc_mt = grch38_qc_mt.filter_cols(
meta[grch38_qc_mt.col_key].release)
return grch38_qc_mt
def intersect_target_ref(ref_mt_filt,
snp_list,
grch37_or_grch38,
intersect_out,
overwrite: bool = False):
mt = hl.read_matrix_table(ref_mt_filt)
if grch37_or_grch38.lower() == 'grch38':
snp_list = snp_list.key_by(locus=hl.locus(hl.str(snp_list.chr),
hl.int(snp_list.pos),
reference_genome='GRCh38'),
alleles=[snp_list.ref, snp_list.alt])
mt = mt.filter_rows(hl.is_defined(snp_list[mt.row_key]))
elif grch37_or_grch38.lower() == 'grch37':
snp_list = snp_list.key_by(locus=hl.locus(hl.str(snp_list.chr),
hl.int(snp_list.pos),
reference_genome='GRCh37'),
alleles=[snp_list.ref, snp_list.alt])
# liftover snp list to GRCh38, filter to SNPs in mt
rg37, rg38 = load_liftover()
snp_liftover = snp_list.annotate(
new_locus=hl.liftover(snp_list.locus, 'GRCh38'))
snp_liftover = snp_liftover.filter(
hl.is_defined(snp_liftover.new_locus))
snp_liftover = snp_liftover.key_by(locus=snp_liftover.new_locus,
alleles=snp_liftover.alleles)
mt = mt.filter_rows(hl.is_defined(snp_liftover[mt.row_key]))
mt = mt.repartition(5000)
mt = mt.checkpoint(intersect_out,
overwrite=overwrite,
_read_if_exists=not overwrite)
def main(args):
full_vcf = hl.read_matrix_table(args.allreads_prefix + '.mt')
# liftover chains
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', rg38)
chips = hl.hadoop_open(args.chip_loci)
chip_dict = {}
for chip in chips:
chip = chip.strip().split()
chip_pos = hl.import_table(chip[1],
filter='\[Controls\]',
skip_blank_lines=True)
chip_pos = chip_pos.filter(
hl.array(list(map(str, range(1, 23))) + ['X', 'Y']).contains(
chip_pos.chr))
chip_pos = chip_pos.key_by(
locus=hl.locus(chip_pos.chr, hl.int(chip_pos.pos)))
# liftover chip position info
chip_pos = chip_pos.annotate(
new_locus=hl.liftover(chip_pos.locus, 'GRCh38'))
chip_pos = chip_pos.filter(hl.is_defined(chip_pos.new_locus))
chip_pos = chip_pos.key_by(locus=chip_pos.new_locus)
# filter full vcf to sites in genotype data
geno_vcf = full_vcf.filter_rows(hl.is_defined(
chip_pos[full_vcf.locus]))
hl.export_vcf(
geno_vcf,
'gs://neurogap/high_coverage/NeuroGap_30x_' + chip[0] + '.vcf.bgz')
def get_gnomad_ld_pruned_mt(genome_version="GRCh38"):
gnomad_ld_pruned_hg37_path = "gs://gnomad/sample_qc/mt/gnomad.joint.high_callrate_common_biallelic_snps.pruned.mt"
gnomad_ld_pruned_hg38_path = "gs://seqr-bw/ref/GRCh38/gnomad_ld_pruned.mt"
if genome_version == "GRCh37":
return hl.read_matrix_table(gnomad_ld_pruned_hg37_path)
elif genome_version == "GRCh38":
if not file_exists(gnomad_ld_pruned_hg38_path):
grch37 = hl.get_reference('GRCh37')
try:
grch37.add_liftover("gs://hail-common/references/grch37_to_grch38.over.chain.gz", 'GRCh38') # doesn't like when try to add on chain file more than once
except: # in case the lift-over chain file was added previously
pass
gnomad_ld_pruned_mt = hl.read_matrix_table(gnomad_ld_pruned_hg37_path)
gnomad_ld_pruned_mt = gnomad_ld_pruned_mt.annotate_rows(liftover_locus = hl.liftover(gnomad_ld_pruned_mt.locus, 'GRCh38'))
gnomad_ld_pruned_mt = gnomad_ld_pruned_mt.filter_rows(hl.is_defined(gnomad_ld_pruned_mt.liftover_locus))
gnomad_ld_pruned_mt = gnomad_ld_pruned_mt.rename({'locus': 'locus_grch37'}).rename({'liftover_locus': 'locus'})
gnomad_ld_pruned_mt = gnomad_ld_pruned_mt.key_rows_by('locus','alleles')
gnomad_ld_pruned_mt.write(gnomad_ld_pruned_hg38_path)
return hl.read_matrix_table(gnomad_ld_pruned_hg38_path)
else:
raise ValueError(f"Invalid genome version: {genome_version}")
def liftover_to_grch38(input_type: str = None,
dirname: str = None,
basename: str = None):
lifted_over = f'{dirname}{basename}.liftover.grch38.mt'
print('\nLifting over to GRCh38')
mt = read_infile(input_type=input_type, dirname=dirname, basename=basename)
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', rg38)
mt = mt.annotate_rows(new_locus=hl.liftover(mt.locus,
'GRCh38',
include_strand=True),
old_locus=mt.locus)
mt = mt.filter_rows(
hl.is_defined(mt.new_locus) & ~mt.new_locus.is_negative_strand)
mt = mt.key_rows_by(locus=mt.new_locus.result, alleles=mt.alleles)
print(f'\nWriting out data lifted-over to GRCh38 to: {lifted_over}')
mt.write(lifted_over)
return hl.read_matrix_table(lifted_over)
def liftover_expr(
locus: hl.expr.LocusExpression, alleles: hl.expr.ArrayExpression,
destination_ref: hl.ReferenceGenome) -> hl.expr.StructExpression:
lifted_over_locus = hl.liftover(locus,
destination_ref,
include_strand=True)
lifted_over_alleles = alleles.map(lambda a: hl.if_else(
lifted_over_locus.is_negative_strand, hl.reverse_complement(a), a))
return hl.struct(locus=lifted_over_locus.result,
alleles=lifted_over_alleles)
def add_37_coordinates(mt):
"""Annotates the GRCh38 MT with 37 coordinates using hail's built-in liftover
:param mt: MatrixTable from VCF
:return: MatrixTable annotated with GRCh37 coordinates
"""
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg38.add_liftover(
'gs://hail-common/references/grch38_to_grch37.over.chain.gz', rg37)
mt = mt.annotate_rows(rg37_locus=hl.liftover(mt.locus, 'GRCh37'))
return mt
def main():
# Parse args
args = parse_args()
# Prepare liftover
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(args.chainfile, rg38)
# Create my own rg38 with altered names
rg38_custom_contigs = [
contig.replace('chr', '') for contig in rg38.contigs
]
rg38_custom_lens = {}
for contig in rg38.lengths:
rg38_custom_lens[contig.replace('chr', '')] = rg38.lengths[contig]
rg38_custom = hl.ReferenceGenome('rg38_custom', rg38_custom_contigs,
rg38_custom_lens)
# Load plink
mt = hl.import_plink(bed=args.in_plink + '.bed',
bim=args.in_plink + '.bim',
fam=args.in_plink + '.fam',
reference_genome='GRCh37',
min_partitions=args.min_partitions)
# # Re-call to remove phasing (required for plink output)
# mt = mt.annotate_entries(GT=hl.call(mt.GT[0], mt.GT[1], phased=False))
# Liftover
mt = mt.annotate_rows(locus_GRCh38=hl.liftover(mt.locus, 'GRCh38'))
# Strip chr from contig name (causes problems with GCTA)
mt = mt.annotate_rows(
contig_GRCh38=mt.locus_GRCh38.contig.replace('chr', ''))
# Swap GRCh37 locus for GRCh38 (but have to use rg38_custom)
mt = mt.key_rows_by()
mt = mt.annotate_rows(locus=hl.locus(mt.contig_GRCh38,
mt.locus_GRCh38.position,
reference_genome=rg38_custom))
mt = mt.key_rows_by(mt.locus, mt.alleles)
# Remove rows with missing locus (after liftover)
mt = mt.filter_rows(hl.is_defined(mt.locus))
# Write plink format
hl.export_plink(dataset=mt, output=args.out_plink)
return 0
def main(args):
covs = ['0.5', '1', '2', '4', '6']
# liftover gencove data
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', rg38)
for cov in ['1']:
all_vcf = hl.hadoop_open(
'gs://neurogap/high_coverage/gencove/fastq_keep.txt')
header = all_vcf.readline().split()
header_index = dict(zip(header, list(range(len(header)))))
comb = None
if args.merge_vcf:
for line in all_vcf:
# read and merge
line = line.split()
if line[header_index['depth']] == cov and line[
header_index['gencove_qc']] == 'PASS':
vcf = hl.import_vcf(line[header_index['path']],
force_bgz=True,
reference_genome='GRCh37',
min_partitions=100)
if comb is None:
comb = vcf
else:
comb = comb.union_cols(vcf)
# write out mt
#comb = comb.naive_coalesce(5000)
comb.write('gs://neurogap/high_coverage/gencove/merge_' + cov +
'_hg19.mt',
overwrite=args.overwrite)
if args.liftover:
comb = hl.read_matrix_table(
'gs://neurogap/high_coverage/gencove/merge_' + cov +
'_hg19.mt')
comb = comb.annotate_rows(
new_locus=hl.liftover(comb.locus, 'GRCh38'))
comb = comb.filter_rows(hl.is_defined(comb.new_locus))
comb = comb.key_rows_by(locus=comb.new_locus, alleles=comb.alleles)
# write out mt
comb.write('gs://neurogap/high_coverage/gencove/merge_' + cov +
'_grch38.mt',
overwrite=args.overwrite)
def lift_data(
t: Union[hl.MatrixTable, hl.Table],
gnomad: bool,
data_type: str,
path: str,
rg: hl.genetics.ReferenceGenome,
overwrite: bool,
) -> Union[hl.MatrixTable, hl.Table]:
"""
Lifts input Table or MatrixTable from one reference build to another
:param t: Table or MatrixTable
:param gnomad: Whether data is gnomAD data
:param data_type: Data type (exomes or genomes for gnomAD; not used otherwise)
:param path: Path to input Table/MatrixTable (if data is not gnomAD data)
:param rg: Reference genome
:param overwrite: Whether to overwrite data
:return: Table or MatrixTablewith liftover annotations
"""
logger.info("Annotating input with liftover coordinates")
liftover_expr = {
"new_locus": hl.liftover(t.locus, rg, include_strand=True),
"old_locus": t.locus,
}
t = (t.annotate(**liftover_expr)
if isinstance(t, hl.Table) else t.annotate_rows(**liftover_expr))
no_target_expr = hl.agg.count_where(hl.is_missing(t.new_locus))
num_no_target = (t.aggregate(no_target_expr) if isinstance(t, hl.Table)
else t.aggregate_rows(no_target_expr))
logger.info(f"Filtering out {num_no_target} sites that failed to liftover")
keep_expr = hl.is_defined(t.new_locus)
t = t.filter(keep_expr) if isinstance(
t, hl.Table) else t.filter_rows(keep_expr)
row_key_expr = {"locus": t.new_locus.result, "alleles": t.alleles}
t = (t.key_by(**row_key_expr)
if isinstance(t, hl.Table) else t.key_rows_by(**row_key_expr))
logger.info("Writing out lifted over data")
t = t.checkpoint(
get_checkpoint_path(gnomad, data_type, path, isinstance(t, hl.Table)),
overwrite=overwrite,
)
return t
def liftover_expr(
locus: hl.expr.LocusExpression,
alleles: hl.expr.ArrayExpression,
destination_reference: hl.ReferenceGenome,
) -> hl.expr.StructExpression:
"""
Generates struct liftover expression.
Struct contains:
- locus: Liftover coordinates
- alleles: Liftover alleles
- original_locus: Locus prior to liftover
- original_alleles: Alleles prior to liftover
- locus_fail_liftover: Whether the locus failed liftover
- ref_allele_mismatch: Whether the allele at index 0 of alleles (lifted over reference allele)
doesn't match the allele at that position in the destination reference
:param locus: Input locus.
:param alleles: Input alleles.
:param destination_reference: Desired reference genome build for liftover.
:return: Struct containing expressions for lifted over locus/alleles as well as original locus/alleles.
"""
lifted_over_locus = hl.liftover(locus, destination_reference, include_strand=True)
lifted_over_alleles = alleles.map(
lambda a: hl.if_else(
lifted_over_locus.is_negative_strand, hl.reverse_complement(a), a
)
)
return hl.struct(
new_locus=lifted_over_locus.result,
new_alleles=lifted_over_alleles,
original_locus=locus,
original_alleles=alleles,
locus_fail_liftover=hl.is_missing(lifted_over_locus),
ref_allele_mismatch=lifted_over_locus.result.sequence_context()
!= lifted_over_alleles[0],
)
def query(output): # pylint: disable=too-many-locals
"""Query script entry point."""
hl.init(default_reference='GRCh38')
gnomad_loadings_path = f'{output}/gnomad_loadings_90k_liftover.ht'
# liftover and get variants
ht_gnomad_loadings = hl.read_table(GNOMAD_V2_LOADINGS)
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', rg38)
ht_gnomad_loadings_liftover = ht_gnomad_loadings.annotate(
liftover=hl.liftover(ht_gnomad_loadings.locus,
'GRCh38',
include_strand=False),
old_locus=ht_gnomad_loadings.locus,
)
ht_gnomad_loadings_liftover = ht_gnomad_loadings_liftover.key_by(
locus=ht_gnomad_loadings_liftover.liftover)
# save gnomad loadings
ht_gnomad_loadings_liftover.write(gnomad_loadings_path, overwrite=True)
def main():
# # Args (local)
# chrom = 11
# chain_file = '/Users/em21/Projects/ot_genetics/genetics-sumstats_data/extras/prepare_uk_biobank_gwas_catalog/sitelist/input_data/grch37_to_grch38.over.chain.gz'
# in_bgen = 'example_data/ukb_imp_chr{chrom}_v3.example.bgen'
# in_sample = 'output/ukb_10k_downsampled.sample'
# to_keep_list = 'output/ukb_10k_downsampled.sample_list.tsv'
# out_plink = 'output/ukb_v3_downsampled10k_plink/ukb_v3_chr{chrom}.downsampled10k'
# cores = 1 # Use "*" for all
# maf_threshold = 0.001
# Args (server)
chrom = sys.argv[1]
chain_file = '/nfs/users/nfs_e/em21/otcoregen/em21/uk_biobank_analysis/create_10k_subsample/input_data/grch37_to_grch38.over.chain.gz'
in_bgen = '/nfs/users/nfs_e/em21/otcoregen/uk_biobank_data/data/genetics/imputation/ukb_imp_chr{chrom}_v3.bgen'
in_sample = '/nfs/users/nfs_e/em21/otcoregen/em21/uk_biobank_analysis/create_10k_subsample/input_data/ukb_10k_downsampled.sample'
to_keep_list = '/nfs/users/nfs_e/em21/otcoregen/em21/uk_biobank_analysis/create_10k_subsample/input_data/ukb_10k_downsampled.sample_list.tsv'
out_plink = '/nfs/users/nfs_e/em21/otcoregen/em21/uk_biobank_analysis/create_10k_subsample/output/ukb_v3_downsampled10k_plink/ukb_v3_chr{chrom}.downsampled10k'
cores = sys.argv[2] # Use "*" for all
maf_threshold = 0.001
# Set the maximum number of cores
hl.init(master="local[{}]".format(cores))
# Prepare liftover
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(chain_file, rg38)
# Create my own rg38 with altered names
rg38_custom_contigs = [
contig.replace('chr', '') for contig in rg38.contigs
]
rg38_custom_lens = {}
for contig in rg38.lengths:
rg38_custom_lens[contig.replace('chr', '')] = rg38.lengths[contig]
rg38_custom = hl.ReferenceGenome('rg38_custom', rg38_custom_contigs,
rg38_custom_lens)
print('Processing chromosome {0}'.format(chrom))
# Index bgen if not existing
if not hl.hadoop_exists(in_bgen.format(chrom=chrom) + '.idx2'):
hl.index_bgen(in_bgen.format(chrom=chrom),
contig_recoding={
"01": "1",
"02": "2",
"03": "3",
"04": "4",
"05": "5",
"06": "6",
"07": "7",
"08": "8",
"09": "9"
},
reference_genome='GRCh37')
# Load bgen
mt = hl.import_bgen(in_bgen.format(chrom=chrom),
entry_fields=['GT'],
sample_file=in_sample)
# Load list samples to keep
samples_to_keep = hl.import_table(to_keep_list,
no_header=True,
impute=False,
types={
'f0': hl.tstr
}).key_by('f0')
# Downsample to required subset of samples
mt = mt.filter_cols(hl.is_defined(samples_to_keep[mt.s]))
# Re-call to remove phasing (required for plink output)
# mt = mt.annotate_entries(GT=hl.call(mt.GT[0], mt.GT[1], phased=False))
# Filter on MAF
mt = hl.variant_qc(mt)
mt = mt.annotate_rows(variant_qc=mt.variant_qc.annotate(
MAF=hl.min(mt.variant_qc.AF)))
mt = mt.filter_rows(mt.variant_qc.MAF >= maf_threshold)
# Liftover
mt = mt.annotate_rows(locus_GRCh38=hl.liftover(mt.locus, 'GRCh38'))
# Strip chr from contig name (causes problems with GCTA)
mt = mt.annotate_rows(
contig_GRCh38=mt.locus_GRCh38.contig.replace('chr', ''))
# Swap GRCh37 locus for GRCh38 (but have to use rg38_custom)
mt = mt.key_rows_by()
mt = mt.annotate_rows(locus=hl.locus(mt.contig_GRCh38,
mt.locus_GRCh38.position,
reference_genome=rg38_custom))
mt = mt.key_rows_by(mt.locus, mt.alleles)
# Remove rows with missing locus (after liftover)
mt = mt.filter_rows(hl.is_defined(mt.locus))
# Write plink format
hl.export_plink(dataset=mt, output=out_plink.format(chrom=chrom))
return 0
parser.add_argument('-d', required=True, choices=['scores', 'elements'], help='GERP++ dataset to load.')
parser.add_argument('-b', required=True, choices=['GRCh37', 'GRCh38'], help='Reference genome build to load.')
args = parser.parse_args()
hg19 = hl.ReferenceGenome.from_fasta_file('hg19',
'gs://hail-datasets-extracted-data/assemblies/ucsc.hg19.fasta.gz',
'gs://hail-datasets-extracted-data/assemblies/ucsc.hg19.fasta.fai')
if args.d == 'scores':
name = 'GERP_scores'
ht = hl.import_table('gs://hail-datasets-extracted-data/GERP++/GERP++_scores.hg19.tsv.bgz',
types={'position': hl.tint, 'N': hl.tfloat, 'S': hl.tfloat}, min_partitions=300)
ht = ht.annotate(locus=hl.locus('chr' + ht['chromosome'].replace('MT', 'M'), ht['position'], 'hg19'))
if args.b == 'GRCh37':
hg19.add_liftover('gs://hail-datasets-extracted-data/assemblies/hg19tob37.chain.gz', 'GRCh37')
ht = ht.annotate(locus=hl.liftover(ht['locus'], 'GRCh37'))
if args.b == 'GRCh38':
hg19.add_liftover('gs://hail-datasets-extracted-data/assemblies/hg19ToHg38.over.chain.gz', 'GRCh38')
ht = ht.annotate(locus=hl.liftover(ht['locus'], 'GRCh38'))
ht = ht.filter(hl.is_defined(ht['locus']))
ht = ht.select('locus', 'N', 'S')
ht = ht.key_by('locus')
if args.d == 'elements':
name = 'GERP_elements'
ht = hl.import_table('gs://hail-datasets-extracted-data/GERP++/GERP++_elements.hg19.tsv.bgz',
types={'start': hl.tint, 'end': hl.tint, 'S': hl.tfloat, 'p_value': hl.tfloat})
ht = ht.annotate(interval=hl.interval(hl.locus(ht['chromosome'], ht['start'], 'hg19'),
hl.locus(ht['chromosome'], ht['end'], 'hg19')))
if args.b == 'GRCh37':
hg19.add_liftover('gs://hail-datasets-extracted-data/assemblies/hg19tob37.chain.gz', 'GRCh37')
import hail as hl
mt = hl.read_matrix_table(
'gs://hail-datasets/hail-data/gtex_v7_exon_read_counts.GRCh37.mt')
b37 = hl.get_reference('GRCh37')
b37.add_liftover('gs://hail-common/references/grch37_to_grch38.over.chain.gz',
'GRCh38')
mt = mt.annotate_rows(interval=hl.liftover(mt.interval, 'GRCh38'))
mt.describe()
mt.write(
'gs://hail-datasets/hail-data/gtex_v7_exon_read_counts.GRCh38.liftover.mt',
overwrite=True)
'position': hl.tint,
'N': hl.tfloat,
'S': hl.tfloat
})
hg19 = hl.ReferenceGenome.from_fasta_file(
'hg19', 'gs://hail-datasets/raw-data/assemblies/ucsc.hg19.fasta.gz',
'gs://hail-datasets/raw-data/assemblies/ucsc.hg19.fasta.fai')
hg19.add_liftover('gs://hail-datasets/raw-data/assemblies/hg19tob37.chain.gz',
'GRCh37')
ht = ht.annotate(locus=hl.locus(ht.contig, ht.position, 'hg19'))
ht.write('hdfs:///tmp/tmp.ht', overwrite=True)
ht = hl.read_table('hdfs:///tmp/gerp_scores.hg19.ht')
ht = ht.annotate(locus=hl.liftover(ht.locus, 'GRCh37'))
ht = ht.filter(hl.is_defined(ht.locus), keep=True)
ht = ht.select(ht.locus, ht.N, ht.N)
ht = ht.key_by(ht.locus)
n_rows = ht.count()
n_partitions = ht.n_partitions()
ht = ht.annotate_globals(name=name,
version=version,
reference_genome=reference_genome,
n_rows=n_rows,
n_partitions=n_partitions)
ht.describe()
ht.write('gs://hail-datasets/hail-data/{n}.{rg}.ht'.format(
import hail as hl
mt = hl.read_matrix_table(
'gs://hail-datasets/hail-data/gtex_v7_eqtl_significant_associations.GRCh37.mt'
)
mt.describe()
b37 = hl.get_reference('GRCh37')
b37.add_liftover('gs://hail-common/references/grch37_to_grch38.over.chain.gz',
'GRCh38')
mt = mt.annotate_rows(liftover_locus=hl.liftover(mt.locus, 'GRCh38'))
mt = mt.filter_rows(hl.is_defined(mt.liftover_locus), keep=True)
mt = mt.partition_rows_by(['liftover_locus'], 'liftover_locus', 'alleles',
'gene_id')
mt = mt.drop(mt.locus)
mt = mt.rename({'liftover_locus': 'locus'})
mt.describe()
mt.write(
'gs://hail-datasets/hail-data/gtex_v7_eqtl_significant_associations.GRCh38.liftover.mt',
overwrite=True)
build = args.b
ht = hl.import_table(f'{raw_data_root}/DANN_GRCh37.tsv.bgz',
types={
'position': hl.tint,
'DANN_score': hl.tfloat
})
ht = ht.annotate(locus=hl.locus(ht['chromosome'], ht['position'], 'GRCh37'),
alleles=hl.array([ht['ref'], ht['alt']]))
if build == 'GRCh38':
b37 = hl.get_reference('GRCh37')
b37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz', 'GRCh38')
ht = ht.annotate(locus=hl.liftover(ht['locus'], 'GRCh38'))
ht = ht.filter(hl.is_defined(ht['locus']))
n_rows = ht.count()
n_partitions = ht.n_partitions()
ht = ht.key_by('locus', 'alleles')
ht = ht.rename({'DANN_score': 'score'})
ht = ht.select('score')
ht = ht.annotate_globals(metadata=hl.struct(name=name,
version=hl.null(hl.tstr),
reference_genome=build,
n_rows=n_rows,
n_partitions=n_partitions))
def main(args):
ht_snp = hl.import_table(args.snp, impute=True)
ht_snp = ht_snp.annotate(variant=hl.delimit([
ht_snp.chromosome,
hl.str(ht_snp.position), ht_snp.allele1, ht_snp.allele2
],
delimiter=':'))
ht_snp = ht_snp.annotate(
**hl.parse_variant(ht_snp.variant, reference_genome='GRCh38'))
ht_snp = ht_snp.key_by('locus', 'alleles')
ht_snp = ht_snp.add_index('idx_snp')
ht_snp = ht_snp.checkpoint(new_temp_file())
# annotate vep
gnomad = hl.read_table(
'gs://gnomad-public-requester-pays/release/3.0/ht/genomes/gnomad.genomes.r3.0.sites.ht'
)
ht_snp = ht_snp.join(gnomad.select('vep'), how='left')
ht_snp = process_consequences(ht_snp)
# extract most severe
ht_snp = ht_snp.annotate(vep=(hl.case().when(
hl.is_defined(ht_snp.vep.worst_csq_for_variant_canonical),
ht_snp.vep.worst_csq_for_variant_canonical).when(
hl.is_defined(ht_snp.vep.worst_csq_for_variant),
ht_snp.vep.worst_csq_for_variant).or_missing()),
is_canonical_vep=hl.is_defined(
ht_snp.vep.worst_csq_for_variant_canonical))
ht_snp = ht_snp.annotate(most_severe=hl.if_else(
hl.is_defined(ht_snp.vep), ht_snp.vep.most_severe_consequence,
'intergenic_variant'),
gene_most_severe=ht_snp.vep.gene_symbol)
ht_snp = ht_snp.select_globals()
ht_snp = ht_snp.drop('vep')
ht_snp = ht_snp.annotate(
**annotate_consequence_category(ht_snp.most_severe))
ht_snp = ht_snp.checkpoint(new_temp_file())
df = ht_snp.key_by().drop('locus', 'alleles', 'variant',
'idx_snp').to_pandas()
# annotate LD
for pop in POPS:
ht = hl.read_table(
f'gs://gnomad-public-requester-pays/release/2.1.1/ld/gnomad.genomes.r2.1.1.{pop}.common.adj.ld.variant_indices.ht'
)
ht = ht.annotate(locus_hg38=hl.liftover(ht.locus, 'GRCh38'))
ht = ht.filter(hl.is_defined(ht.locus_hg38))
ht = ht.key_by('locus_hg38', 'alleles').drop('locus')
ht = ht_snp.join(ht, 'inner')
ht = ht.checkpoint(new_temp_file())
lead_idx = ht.order_by(hl.desc(ht.prob)).head(1).idx.collect()
idx = ht.idx.collect()
bm = BlockMatrix.read(
f'gs://gnomad-public-requester-pays/release/2.1.1/ld/gnomad.genomes.r2.1.1.{pop}.common.ld.bm'
)
bm = bm.filter(idx, idx)
# re-densify triangluar matrix
bm = bm + bm.T - get_diag_mat(bm.diagonal())
bm = bm.filter_rows(
np.where(np.array(idx) == lead_idx[0])[0].tolist())**2
idx_snp = ht.idx_snp.collect()
r2 = bm.to_numpy()[0]
df[f'gnomad_lead_r2_{pop}'] = np.nan
df[f'gnomad_lead_r2_{pop}'].iloc[idx_snp] = r2
if args.out.startswith('gs://'):
fopen = hl.hadoop_open
else:
fopen = open
with fopen(args.out, 'w') as f:
df.to_csv(f, sep='\t', na_rep='NA', index=False)
def main(gnomad_file, chain_file, out_folder, test=None):
# Output files:
out_parquet = f'{out_folder}/variant-annotation.parquet'
# Load data
ht = hl.read_table(gnomad_file)
# If process is being tested, take head:
if test:
ht = ht.head(test)
# Assert that all alleles are biallelic:
assert ht.all(ht.alleles.length() == 2), 'Mono- or multiallelic variants have been found.'
# Extracting AF indices of populations:
population_indices = ht.globals.freq_index_dict.collect()[0]
population_indices = {pop: population_indices[f'{pop}-adj'] for pop in POPULATIONS}
# Generate struct for alt. allele frequency in selected populations:
ht = ht.annotate(af=hl.struct(**{pop: ht.freq[index].AF for pop, index in population_indices.items()}))
# Add chain file
grch37 = hl.get_reference('GRCh37')
grch38 = hl.get_reference('GRCh38')
grch38.add_liftover(chain_file, grch37)
# Liftover
ht = ht.annotate(
locus_GRCh37=hl.liftover(ht.locus, 'GRCh37')
)
# Adding build-specific coordinates to the table:
ht = ht.annotate(
chrom_b38=ht.locus.contig.replace('chr', ''),
pos_b38=ht.locus.position,
chrom_b37=ht.locus_GRCh37.contig.replace('chr', ''),
pos_b37=ht.locus_GRCh37.position,
ref=ht.alleles[0],
alt=ht.alleles[1],
allele_type=ht.allele_info.allele_type
)
# Updating table:
ht = ht.annotate(
# Updating CADD column:
cadd=ht.cadd.rename({'raw_score': 'raw'}).drop('has_duplicate'),
# Adding locus as new column:
locus_GRCh38=ht.locus
)
# Drop all global annotations:
ht = ht.select_globals()
# Drop unnecessary VEP fields
ht = ht.annotate(
vep=ht.vep.drop(
'assembly_name',
'allele_string',
'ancestral',
'context',
'end',
'id',
'input',
'intergenic_consequences',
'seq_region_name',
'start',
'strand',
'variant_class'
)
)
# Sort columns
col_order = [
'locus_GRCh38', 'chrom_b38', 'pos_b38',
'chrom_b37', 'pos_b37',
'ref', 'alt', 'allele_type', 'vep', 'rsid', 'af', 'cadd', 'filters'
]
# Repartition and write parquet file
(
ht
.select(*col_order)
.to_spark(flatten=False)
.coalesce(OUT_PARTITIONS)
.write.mode('overwrite').parquet(out_parquet)
)
import hail as hl
ht = hl.read_table(
'gs://hail-datasets/hail-data/gerp_scores.GRCh37.liftover.ht')
b37 = hl.get_reference('GRCh37')
b37.add_liftover('gs://hail-common/references/grch37_to_grch38.over.chain.gz',
'GRCh38')
ht = ht.annotate(liftover_locus=hl.liftover(ht.locus, 'GRCh38'))
ht = ht.filter(hl.is_defined(ht.liftover_locus), keep=True)
ht = ht.key_by(ht.liftover_locus)
ht = ht.drop('locus')
ht = ht.rename({'liftover_locus': 'locus'})
ht.describe()
ht.write('gs://hail-datasets/hail-data/gerp_scores.GRCh38.liftover.ht',
overwrite=True)
def main():
# Args (global)
chain_file = 'gs://hail-common/references/grch37_to_grch38.over.chain.gz'
inf = 'gs://genetics-portal-raw/uk_biobank_sumstats/variant_sitelist/ukbiobank_neale_saige_sitelist.190321.tsv'
in_ensembl = 'gs://genetics-portal-raw/ensembl_grch37_r95/homo_sapiens-chr*.vcf.*.gz'
out_parquet = 'gs://genetics-portal-raw/uk_biobank_sumstats/variant_sitelist/ukbiobank_neale_saige_sitelist.190321.annotated.parquet'
# # Args (local)
# chain_file = 'input_data/grch37_to_grch38.over.chain.gz'
# inf = 'ukbiobank_neale_saige_sitelist.head100k.tsv'
# in_ensembl = 'input_data/homo_sapiens-chr1.head.vcf'
# out_parquet = 'ukbiobank_neale_saige_sitelist.annotated.parquet'
#
# Load sitelist ------------------------------------------------------------
#
# Load data
ht = hl.import_table(inf,
no_header=True,
min_partitions=128,
types={
'f0': 'str',
'f1': 'int32',
'f2': 'str',
'f3': 'str'
})
# Rename columns
ht = ht.rename({
'f0': 'chrom_b37',
'f1': 'pos_b37',
'f2': 'ref',
'f3': 'alt'
})
# Create locus and allele
ht = ht.annotate(locus=hl.locus(ht.chrom_b37, ht.pos_b37, 'GRCh37'),
alleles=hl.array([ht.ref,
ht.alt])).key_by('locus', 'alleles')
#
# Do liftover --------------------------------------------------------------
#
# Add chain file
rg37 = hl.get_reference('GRCh37')
rg38 = hl.get_reference('GRCh38')
rg37.add_liftover(chain_file, rg38)
# Liftover
ht = ht.annotate(locus_GRCh38=hl.liftover(ht.locus, 'GRCh38'))
# Convert to spark
df = (ht.to_spark().withColumnRenamed(
'locus_GRCh38.contig',
'chrom_b38').withColumnRenamed('locus_GRCh38.position',
'pos_b38').drop('locus.contig',
'locus.position',
'alleles'))
#
# Annotate with rsids ------------------------------------------------------
#
# Load ensembl
ensembl = load_ensembl_vcf(in_ensembl)
# Join
df = df.join(ensembl,
on=['chrom_b37', 'pos_b37', 'ref', 'alt'],
how='left')
#
# Write output -------------------------------------------------------------
#
# Write
(df.select('chrom_b37', 'pos_b37', 'chrom_b38', 'pos_b38', 'ref', 'alt',
'rsid').write.parquet(out_parquet, mode='overwrite'))
return 0
Returns the complement of a base
:param str base: Base to be flipped
:return: Complement of input base
:rtype: str
"""
return (hl.switch(base).when('A', 'T').when('T', 'A').when('G', 'C').when(
'C', 'G').default(base))
mpc_ht = hl.import_table(MPC_SCORE, impute=True)
mpc_ht = mpc_ht.annotate(locus=hl.locus(contig=mpc_ht.chrom, pos=mpc_ht.pos),
alleles=[mpc_ht.ref, mpc_ht.alt])
mpc_ht = mpc_ht.key_by(mpc_ht.locus, mpc_ht.alleles).select('MPC')
mpc_ht = mpc_ht.annotate(
new_locus=hl.liftover(mpc_ht.locus, 'GRCh38', include_strand=True))
mpc_ht = mpc_ht.filter(hl.is_defined(mpc_ht.new_locus))
mpc_ht = mpc_ht.annotate(new_alleles=hl.cond(
mpc_ht.new_locus.is_negative_strand,
[flip_base(mpc_ht.alleles[0]),
flip_base(mpc_ht.alleles[1])], mpc_ht.alleles))
mpc_ht = mpc_ht.key_by(locus=mpc_ht.new_locus.result,
alleles=mpc_ht.new_alleles)
# Write the result to file.
mpc_ht.write(
'gs://raw_data_bipolar_dalio_w1_w2/inputs/fordist_constraint_official_mpc_values_v2_GRCh38.ht',
overwrite=True)
Returns the complement of a base
:param str base: Base to be flipped
:return: Complement of input base
:rtype: str
"""
return (hl.switch(base).when('A', 'T').when('T', 'A').when('G', 'C').when(
'C', 'G').default(base))
ht_bsc = hl.import_table(BSC_COUNTS, impute=True)
ht_bsc = ht_bsc.annotate(locus=hl.locus(contig=ht_bsc.chrom, pos=ht_bsc.pos),
alleles=[ht_bsc.ref, ht_bsc.alt])
ht_bsc = ht_bsc.key_by(ht_bsc.locus, ht_bsc.alleles)
ht_bsc = ht_bsc.annotate(
new_locus=hl.liftover(ht_bsc.locus, 'GRCh38', include_strand=True))
ht_bsc = ht_bsc.filter(hl.is_defined(ht_bsc.new_locus))
ht_bsc = ht_bsc.annotate(new_alleles=hl.cond(
ht_bsc.new_locus.is_negative_strand,
[flip_base(ht_bsc.alleles[0]),
flip_base(ht_bsc.alleles[1])], ht_bsc.alleles))
ht_bsc = ht_bsc.key_by(locus=ht_bsc.new_locus.result,
alleles=ht_bsc.new_alleles)
# Write the result to file.
ht_bsc.write(
'gs://raw_data_bipolar_dalio_w1_w2/inputs/BSC_MAC5_counts_GRCh38.ht',
overwrite=True)
def liftover_intervals(t: hl.Table,
keep_missing_interval: bool = False) -> hl.Table:
"""
Liftover locus in intervals from one coordinate system (hg37) to another (hg38)
# Example input table description
#
# ----------------------------------------
# Global fields:
# None
# ----------------------------------------
# Row fields:
# 'interval': interval<locus<GRCh37>>
# ----------------------------------------
# Key: ['interval']
# ----------------------------------------
:param t: Table of intervals on GRCh37
:param keep_missing_interval: If True, keep missing (non-lifted) intervals in the output Table.
:return: Table with intervals lifted over GRCh38 added.
"""
rg37 = hl.get_reference("GRCh37")
rg38 = hl.get_reference("GRCh38")
if not rg37.has_liftover("GRCh38"):
rg37.add_liftover(
f'{nfs_dir}/resources/liftover/grch37_to_grch38.over.chain.gz',
rg38)
t = t.annotate(
start=hl.liftover(t.interval.start, "GRCh38"),
end=hl.liftover(t.interval.end, "GRCh38"),
)
t = t.filter((t.start.contig == "chr" + t.interval.start.contig)
& (t.end.contig == "chr" + t.interval.end.contig))
t = t.key_by()
t = (t.select(interval=hl.locus_interval(t.start.contig,
t.start.position,
t.end.position,
reference_genome=rg38,
invalid_missing=True),
interval_hg37=t.interval))
# bad intervals
missing = t.aggregate(hl.agg.counter(~hl.is_defined(t.interval)))
logger.info(
f"Number of missing intervals: {missing[True]} out of {t.count()}...")
# update globals annotations
global_ann_expr = {
'date': current_date(),
'reference_genome': 'GRCh38',
'was_lifted': True
}
t = t.annotate_globals(**global_ann_expr)
if not keep_missing_interval:
logger.info(f"Filtering out {missing[True]} missing intervals...")
t = t.filter(hl.is_defined(t.interval), keep=True)
return t.key_by("interval")
'Name': 'gene_id',
'x': 'TPM'
})
mt = mt_counts.annotate_entries(TPM=mt_tpm[mt_counts.gene_id,
mt_counts.sample_id]['TPM'])
mt = mt.annotate_rows(**ht_genes[mt.gene_id])
mt = mt.annotate_cols(**ht_sample_attributes[mt.sample_id])
if reference_genome == 'GRCh38':
b37 = hl.get_reference('GRCh37')
b37.add_liftover(
'gs://hail-common/references/grch37_to_grch38.over.chain.gz',
'GRCh38')
mt = mt.annotate_rows(
gene_interval=hl.liftover(mt['gene_interval'], 'GRCh38'))
mt = mt.filter_rows(hl.is_defined(mt['gene_interval']))
mt = mt.repartition(20)
elif dataset == 'transcripts':
name = 'GTEx_transcript_expression'
ht_transcripts = import_gtf(path=EXTRACT_BUCKET +
'GTEx/v7/GTEx_transcripts.v7.GRCh37.gtf.bgz',
reference_genome='GRCh37')
ht_transcripts = ht_transcripts.filter(
ht_transcripts['feature'] == 'transcript')
ht_transcripts = ht_transcripts.select(
'transcript_id', 'strand', 'transcript_name', 'transcript_type',