def build_vcf_export_reference(
name: str,
build: str = "GRCh38",
keep_contigs: List[str] = [f"chr{i}" for i in range(1, 23)] +
["chrX", "chrY", "chrM"],
) -> hl.ReferenceGenome:
"""
Create export reference based on reference genome defined by `build`.
By default this will return a new reference with all non-standard contigs eliminated. Keeps chr 1-22, Y, X, and M.
An example of a non-standard contig is: ##contig=<ID=chr3_GL000221v1_random,length=155397,assembly=GRCh38>
:param name: Name to use for new reference.
:param build: Reference genome build to use as starting reference genome.
:param keep_contigs: Contigs to keep from reference genome defined by `build`. Default is autosomes, sex chromosomes, and chrM.
:return: Reference genome for VCF export containing only contigs in `keep_contigs`.
"""
ref = hl.get_reference(build)
export_reference = hl.ReferenceGenome(
name=name,
contigs=keep_contigs,
lengths={contig: ref.lengths[contig]
for contig in keep_contigs},
x_contigs=ref.x_contigs,
y_contigs=ref.y_contigs,
par=[(interval.start.contig, interval.start.position,
interval.end.position) for interval in ref.par],
mt_contigs=ref.mt_contigs,
)
return export_reference
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 test_constructors(self):
rg = hl.ReferenceGenome("foo", ["1"], {"1": 100})
schema = hl.tstruct(a=hl.tfloat64, b=hl.tfloat64, c=hl.tint32, d=hl.tint32)
rows = [{'a': 2.0, 'b': 4.0, 'c': 1, 'd': 5}]
kt = hl.Table.parallelize(rows, schema)
kt = kt.annotate(d=hl.int64(kt.d))
kt = kt.annotate(l1=hl.parse_locus("1:51"),
l2=hl.locus("1", 51, reference_genome=rg),
i1=hl.parse_locus_interval("1:51-56", reference_genome=rg),
i2=hl.interval(hl.locus("1", 51, reference_genome=rg),
hl.locus("1", 56, reference_genome=rg)))
expected_schema = {'a': hl.tfloat64, 'b': hl.tfloat64, 'c': hl.tint32, 'd': hl.tint64,
'l1': hl.tlocus(), 'l2': hl.tlocus(rg),
'i1': hl.tinterval(hl.tlocus(rg)), 'i2': hl.tinterval(hl.tlocus(rg))}
self.assertTrue(all([expected_schema[f] == t for f, t in kt.row.dtype.items()]))
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
"chr14": 107043718,
"chr15": 101991189,
"chr16": 90338345,
"chr17": 83257441,
"chr18": 80373285,
"chr19": 58617616,
"chr20": 64444167,
"chr21": 46709983,
"chr22": 50818468,
"chrX": 156040895,
"chrY": 57227415
}
ref = hl.ReferenceGenome(name="hg38",
contigs=contigs,
lengths=lengths,
x_contigs="chrX",
y_contigs="chrY")
all_datasets = hl.import_vcf(files, reference_genome=ref, force_bgz=True)
# union_rows approach causes ClassTooLargeException
# mt = hl.MatrixTable.union_rows(*all_datasets)
mt = all_datasets
# rest the qual to missing because hail by default populates it with -1.00e+01
merged_reset_qual = mt.annotate_rows(qual=hl.missing('float64'))
hl.export_vcf(merged_reset_qual,
"gs://{}/{}/merged.vcf.bgz".format(args.out_bucket,
args.cluster_name),
metadata=hl.get_vcf_metadata(files[0]))