def generate_allele_data(ht: hl.Table) -> hl.Table:
"""
Returns bi-allelic sites HT with the following annotations:
- allele_data (nonsplit_alleles, has_star, variant_type, and n_alt_alleles)
:param Table ht: Full unsplit HT
:return: Table with allele data annotations
:rtype: Table
"""
ht = ht.select()
allele_data = hl.struct(nonsplit_alleles=ht.alleles,
has_star=hl.any(lambda a: a == "*", ht.alleles))
ht = ht.annotate(allele_data=allele_data.annotate(
**add_variant_type(ht.alleles)))
ht = hl.split_multi_hts(ht)
ht = ht.filter(hl.len(ht.alleles) > 1)
allele_type = (hl.case().when(
hl.is_snp(ht.alleles[0], ht.alleles[1]),
"snv").when(hl.is_insertion(ht.alleles[0], ht.alleles[1]),
"ins").when(hl.is_deletion(ht.alleles[0], ht.alleles[1]),
"del").default("complex"))
ht = ht.annotate(allele_data=ht.allele_data.annotate(
allele_type=allele_type,
was_mixed=ht.allele_data.variant_type == "mixed"))
return ht
def generate_allele_data(mt: hl.MatrixTable) -> hl.Table:
"""
Writes bi-allelic sites MT with the following annotations:
- allele_data (nonsplit_alleles, has_star, variant_type, and n_alt_alleles)
:param MatrixTable mt: Full unsplit MT
:return: Table with allele data annotations
:rtype: Table
"""
ht = mt.rows().select()
allele_data = hl.struct(nonsplit_alleles=ht.alleles,
has_star=hl.any(lambda a: a == '*', ht.alleles))
ht = ht.annotate(allele_data=allele_data.annotate(
**add_variant_type(ht.alleles)))
ht = hl.split_multi_hts(ht)
allele_type = (hl.case().when(
hl.is_snp(ht.alleles[0], ht.alleles[1]),
'snv').when(hl.is_insertion(ht.alleles[0], ht.alleles[1]),
'ins').when(hl.is_deletion(ht.alleles[0], ht.alleles[1]),
'del').default('complex'))
ht = ht.annotate(allele_data=ht.allele_data.annotate(
allele_type=allele_type,
was_mixed=ht.allele_data.variant_type == 'mixed'))
return ht
def main(args):
print("main")
run_hash = "91b132aa"
ht = hl.read_table(
f'{temp_dir}/ddd-elgh-ukbb/variant_qc/models/{run_hash}/{run_hash}_rf_result_ranked_denovo_ddd_comp.ht'
)
mt = hl.read_matrix_table(
f'{temp_dir}/ddd-elgh-ukbb/Sanger_cohorts_chr1-7and20_split_sampleqc_filtered.mt'
)
mt = mt.annotate_rows(Variant_Type=hl.cond(
(hl.is_snp(mt.alleles[0], mt.alleles[1])), "SNP",
hl.cond(
hl.is_insertion(mt.alleles[0], mt.alleles[1]), "INDEL",
hl.cond(hl.is_deletion(mt.alleles[0], mt.alleles[1]), "INDEL",
"Other"))))
mt = mt.annotate_rows(info=mt.info.annotate(
rf_probability=ht[mt.row_key].rf_probability['TP']))
mt = mt.annotate_rows(info=mt.info.annotate(score=ht[mt.row_key].score))
filter_column_annotation = (
hl.case().when(
((mt.Variant_Type == "SNP") & (mt.info.rf_probability <= 0.90)),
"PASS").when(((mt.Variant_Type == "INDEL") &
(mt.info.rf_probability <= 0.80)),
"PASS").default(".") # remove everything else
)
# mt_annotated = mt.annotate_rows(mt.filters=filter_column_annotation)
mt1 = mt.annotate_rows(filtercol=((filter_column_annotation)))
mt_fail = mt1.filter_rows(mt1.filtercol == ".")
print(mt_fail.count())
mt2 = mt1.annotate_rows(filters=mt1.filters.add(mt1.filtercol))
mt_fail2 = mt2.filter_rows(mt2.filters.contains("."))
mt_pass = mt2.filter_rows(mt2.filters.contains("PASS"))
print(mt_fail2.count())
print(mt_pass.count())
mt2 = mt2.checkpoint(
f'{tmp_dir}/Sanger_cohorts_chr1-7and20_after_RF_final.mt',
overwrite=True)
hl.export_vcf(
mt2,
f'{tmp_dir}/Sanger_cohorts_chr1-7and20_after_RF_final.vcf.bgz',
parallel='separate_header')
def generate_split_alleles(mt: hl.MatrixTable) -> hl.Table:
allele_data = hl.struct(nonsplit_alleles=mt.alleles,
has_star=hl.any(lambda a: a == '*', mt.alleles))
mt = mt.annotate_rows(allele_data=allele_data.annotate(
**add_variant_type(mt.alleles)))
mt = hl.split_multi_hts(mt, left_aligned=True)
allele_type = (hl.case().when(
hl.is_snp(mt.alleles[0], mt.alleles[1]),
'snv').when(hl.is_insertion(mt.alleles[0], mt.alleles[1]),
'ins').when(hl.is_deletion(mt.alleles[0], mt.alleles[1]),
'del').default('complex'))
mt = mt.annotate_rows(allele_data=mt.allele_data.annotate(
allele_type=allele_type,
was_mixed=mt.allele_data.variant_type == 'mixed'))
return mt
def create_binned_data_initial(ht: hl.Table, data: str, data_type: str, n_bins: int) -> hl.Table:
# Count variants for ranking
count_expr = {x: hl.agg.filter(hl.is_defined(ht[x]), hl.agg.counter(hl.cond(hl.is_snp(
ht.alleles[0], ht.alleles[1]), 'snv', 'indel'))) for x in ht.row if x.endswith('rank')}
rank_variant_counts = ht.aggregate(hl.Struct(**count_expr))
logger.info(
f"Found the following variant counts:\n {pformat(rank_variant_counts)}")
ht_truth_data = hl.read_table(
f"{temp_dir}/ddd-elgh-ukbb/variant_qc/truthset_table.ht")
ht = ht.annotate_globals(rank_variant_counts=rank_variant_counts)
ht = ht.annotate(
**ht_truth_data[ht.key],
# **fam_ht[ht.key],
# **gnomad_ht[ht.key],
# **denovo_ht[ht.key],
# clinvar=hl.is_defined(clinvar_ht[ht.key]),
indel_length=hl.abs(ht.alleles[0].length()-ht.alleles[1].length()),
rank_bins=hl.array(
[hl.Struct(
rank_id=rank_name,
bin=hl.int(hl.ceil(hl.float(ht[rank_name] + 1) / hl.floor(ht.globals.rank_variant_counts[rank_name][hl.cond(
hl.is_snp(ht.alleles[0], ht.alleles[1]), 'snv', 'indel')] / n_bins)))
)
for rank_name in rank_variant_counts]
),
# lcr=hl.is_defined(lcr_intervals[ht.locus])
)
ht = ht.explode(ht.rank_bins)
ht = ht.transmute(
rank_id=ht.rank_bins.rank_id,
bin=ht.rank_bins.bin
)
ht = ht.filter(hl.is_defined(ht.bin))
ht = ht.checkpoint(
f'{tmp_dir}/gnomad_score_binning_tmp.ht', overwrite=True)
# Create binned data
return (
ht
.group_by(
rank_id=ht.rank_id,
contig=ht.locus.contig,
snv=hl.is_snp(ht.alleles[0], ht.alleles[1]),
bi_allelic=hl.is_defined(ht.biallelic_rank),
singleton=ht.transmitted_singleton,
trans_singletons=hl.is_defined(ht.singleton_rank),
de_novo_high_quality=ht.de_novo_high_quality_rank,
de_novo_medium_quality=hl.is_defined(
ht.de_novo_medium_quality_rank),
de_novo_synonymous=hl.is_defined(ht.de_novo_synonymous_rank),
# release_adj=ht.ac > 0,
bin=ht.bin
)._set_buffer_size(20000)
.aggregate(
min_score=hl.agg.min(ht.score),
max_score=hl.agg.max(ht.score),
n=hl.agg.count(),
n_ins=hl.agg.count_where(
hl.is_insertion(ht.alleles[0], ht.alleles[1])),
n_del=hl.agg.count_where(
hl.is_deletion(ht.alleles[0], ht.alleles[1])),
n_ti=hl.agg.count_where(hl.is_transition(
ht.alleles[0], ht.alleles[1])),
n_tv=hl.agg.count_where(hl.is_transversion(
ht.alleles[0], ht.alleles[1])),
n_1bp_indel=hl.agg.count_where(ht.indel_length == 1),
n_mod3bp_indel=hl.agg.count_where((ht.indel_length % 3) == 0),
# n_clinvar=hl.agg.count_where(ht.clinvar),
n_singleton=hl.agg.count_where(ht.transmitted_singleton),
n_high_quality_de_novos=hl.agg.count_where(
ht.de_novo_data.p_de_novo[0] > 0.99),
n_validated_DDD_denovos=hl.agg.count_where(
ht.inheritance.contains("De novo")),
n_medium_quality_de_novos=hl.agg.count_where(
ht.de_novo_data.p_de_novo[0] > 0.5),
n_high_confidence_de_novos=hl.agg.count_where(
ht.de_novo_data.confidence[0] == 'HIGH'),
n_de_novo=hl.agg.filter(ht.family_stats.unrelated_qc_callstats.AC[0][1] == 0, hl.agg.sum(
ht.family_stats.mendel[0].errors)),
n_high_quality_de_novos_synonymous=hl.agg.count_where(
(ht.de_novo_data.p_de_novo[0] > 0.99) & (ht.consequence == "synonymous_variant")),
# n_de_novo_no_lcr=hl.agg.filter(~ht.lcr & (
# ht.family_stats.unrelated_qc_callstats.AC[1] == 0), hl.agg.sum(ht.family_stats.mendel.errors)),
n_de_novo_sites=hl.agg.filter(ht.family_stats.unrelated_qc_callstats.AC[0][1] == 0, hl.agg.count_where(
ht.family_stats.mendel[0].errors > 0)),
# n_de_novo_sites_no_lcr=hl.agg.filter(~ht.lcr & (
# ht.family_stats.unrelated_qc_callstats.AC[1] == 0), hl.agg.count_where(ht.family_stats.mendel.errors > 0)),
n_trans_singletons=hl.agg.filter((ht.ac_raw < 3) & (
ht.family_stats.unrelated_qc_callstats.AC[0][1] == 1), hl.agg.sum(ht.family_stats.tdt[0].t)),
n_trans_singletons_synonymous=hl.agg.filter((ht.ac_raw < 3) & (ht.consequence == "synonymous_variant") & (
ht.family_stats.unrelated_qc_callstats.AC[0][1] == 1), hl.agg.sum(ht.family_stats.tdt[0].t)),
n_untrans_singletons=hl.agg.filter((ht.ac_raw < 3) & (
ht.family_stats.unrelated_qc_callstats.AC[0][1] == 1), hl.agg.sum(ht.family_stats.tdt[0].u)),
n_untrans_singletons_synonymous=hl.agg.filter((ht.ac_raw < 3) & (ht.consequence == "synonymous_variant") & (
ht.family_stats.unrelated_qc_callstats.AC[0][1] == 1), hl.agg.sum(ht.family_stats.tdt[0].u)),
n_train_trans_singletons=hl.agg.count_where(
(ht.family_stats.unrelated_qc_callstats.AC[0][1] == 1) & (ht.family_stats.tdt[0].t == 1)),
n_omni=hl.agg.count_where(ht.omni),
n_mills=hl.agg.count_where(ht.mills),
n_hapmap=hl.agg.count_where(ht.hapmap),
n_kgp_high_conf_snvs=hl.agg.count_where(
ht.kgp_phase1_hc),
fail_hard_filters=hl.agg.count_where(ht.fail_hard_filters),
# n_vqsr_pos_train=hl.agg.count_where(ht.vqsr_positive_train_site),
# n_vqsr_neg_train=hl.agg.count_where(ht.vqsr_negative_train_site)
)
)
def create_binned_data(ht: hl.Table, data: str, data_type: str,
n_bins: int) -> hl.Table:
"""
Creates binned data from a rank Table grouped by rank_id (rank, biallelic, etc.), contig, snv, bi_allelic and singleton
containing the information needed for evaluation plots.
:param Table ht: Input rank table
:param str data: Which data/run hash is being created
:param str data_type: one of 'exomes' or 'genomes'
:param int n_bins: Number of bins.
:return: Binned Table
:rtype: Table
"""
# Count variants for ranking
count_expr = {
x: hl.agg.filter(
hl.is_defined(ht[x]),
hl.agg.counter(
hl.cond(hl.is_snp(ht.alleles[0], ht.alleles[1]), 'snv',
'indel')))
for x in ht.row if x.endswith('rank')
}
rank_variant_counts = ht.aggregate(hl.Struct(**count_expr))
logger.info(
f"Found the following variant counts:\n {pformat(rank_variant_counts)}"
)
ht = ht.annotate_globals(rank_variant_counts=rank_variant_counts)
# Load external evaluation data
clinvar_ht = hl.read_table(clinvar_ht_path)
denovo_ht = get_validated_denovos_ht()
if data_type == 'exomes':
denovo_ht = denovo_ht.filter(denovo_ht.gnomad_exomes.high_quality)
else:
denovo_ht = denovo_ht.filter(denovo_ht.gnomad_genomes.high_quality)
denovo_ht = denovo_ht.select(
validated_denovo=denovo_ht.validated,
high_confidence_denovo=denovo_ht.Confidence == 'HIGH')
ht_truth_data = hl.read_table(annotations_ht_path(data_type, 'truth_data'))
fam_ht = hl.read_table(annotations_ht_path(data_type, 'family_stats'))
fam_ht = fam_ht.select(family_stats=fam_ht.family_stats[0])
gnomad_ht = get_gnomad_data(data_type).rows()
gnomad_ht = gnomad_ht.select(
vqsr_negative_train_site=gnomad_ht.info.NEGATIVE_TRAIN_SITE,
vqsr_positive_train_site=gnomad_ht.info.POSITIVE_TRAIN_SITE,
fail_hard_filters=(gnomad_ht.info.QD < 2) | (gnomad_ht.info.FS > 60) |
(gnomad_ht.info.MQ < 30))
lcr_intervals = hl.import_locus_intervals(lcr_intervals_path)
ht = ht.annotate(
**ht_truth_data[ht.key],
**fam_ht[ht.key],
**gnomad_ht[ht.key],
**denovo_ht[ht.key],
clinvar=hl.is_defined(clinvar_ht[ht.key]),
indel_length=hl.abs(ht.alleles[0].length() - ht.alleles[1].length()),
rank_bins=hl.array([
hl.Struct(
rank_id=rank_name,
bin=hl.int(
hl.ceil(
hl.float(ht[rank_name] + 1) / hl.floor(
ht.globals.rank_variant_counts[rank_name][hl.cond(
hl.is_snp(ht.alleles[0], ht.alleles[1]), 'snv',
'indel')] / n_bins))))
for rank_name in rank_variant_counts
]),
lcr=hl.is_defined(lcr_intervals[ht.locus]))
ht = ht.explode(ht.rank_bins)
ht = ht.transmute(rank_id=ht.rank_bins.rank_id, bin=ht.rank_bins.bin)
ht = ht.filter(hl.is_defined(ht.bin))
ht = ht.checkpoint(
f'gs://gnomad-tmp/gnomad_score_binning_{data_type}_tmp_{data}.ht',
overwrite=True)
# Create binned data
return (ht.group_by(
rank_id=ht.rank_id,
contig=ht.locus.contig,
snv=hl.is_snp(ht.alleles[0], ht.alleles[1]),
bi_allelic=hl.is_defined(ht.biallelic_rank),
singleton=ht.singleton,
release_adj=ht.ac > 0,
bin=ht.bin)._set_buffer_size(20000).aggregate(
min_score=hl.agg.min(ht.score),
max_score=hl.agg.max(ht.score),
n=hl.agg.count(),
n_ins=hl.agg.count_where(
hl.is_insertion(ht.alleles[0], ht.alleles[1])),
n_del=hl.agg.count_where(
hl.is_deletion(ht.alleles[0], ht.alleles[1])),
n_ti=hl.agg.count_where(
hl.is_transition(ht.alleles[0], ht.alleles[1])),
n_tv=hl.agg.count_where(
hl.is_transversion(ht.alleles[0], ht.alleles[1])),
n_1bp_indel=hl.agg.count_where(ht.indel_length == 1),
n_mod3bp_indel=hl.agg.count_where((ht.indel_length % 3) == 0),
n_clinvar=hl.agg.count_where(ht.clinvar),
n_singleton=hl.agg.count_where(ht.singleton),
n_validated_de_novos=hl.agg.count_where(ht.validated_denovo),
n_high_confidence_de_novos=hl.agg.count_where(
ht.high_confidence_denovo),
n_de_novo=hl.agg.filter(
ht.family_stats.unrelated_qc_callstats.AC[1] == 0,
hl.agg.sum(ht.family_stats.mendel.errors)),
n_de_novo_no_lcr=hl.agg.filter(
~ht.lcr & (ht.family_stats.unrelated_qc_callstats.AC[1] == 0),
hl.agg.sum(ht.family_stats.mendel.errors)),
n_de_novo_sites=hl.agg.filter(
ht.family_stats.unrelated_qc_callstats.AC[1] == 0,
hl.agg.count_where(ht.family_stats.mendel.errors > 0)),
n_de_novo_sites_no_lcr=hl.agg.filter(
~ht.lcr & (ht.family_stats.unrelated_qc_callstats.AC[1] == 0),
hl.agg.count_where(ht.family_stats.mendel.errors > 0)),
n_trans_singletons=hl.agg.filter(
(ht.info_ac < 3) &
(ht.family_stats.unrelated_qc_callstats.AC[1] == 1),
hl.agg.sum(ht.family_stats.tdt.t)),
n_untrans_singletons=hl.agg.filter(
(ht.info_ac < 3) &
(ht.family_stats.unrelated_qc_callstats.AC[1] == 1),
hl.agg.sum(ht.family_stats.tdt.u)),
n_train_trans_singletons=hl.agg.count_where(
(ht.family_stats.unrelated_qc_callstats.AC[1] == 1)
& (ht.family_stats.tdt.t == 1)),
n_omni=hl.agg.count_where(ht.truth_data.omni),
n_mills=hl.agg.count_where(ht.truth_data.mills),
n_hapmap=hl.agg.count_where(ht.truth_data.hapmap),
n_kgp_high_conf_snvs=hl.agg.count_where(
ht.truth_data.kgp_high_conf_snvs),
fail_hard_filters=hl.agg.count_where(ht.fail_hard_filters),
n_vqsr_pos_train=hl.agg.count_where(ht.vqsr_positive_train_site),
n_vqsr_neg_train=hl.agg.count_where(ht.vqsr_negative_train_site)))
def score_bin_agg(
ht: hl.GroupedTable, fam_stats_ht: hl.Table
) -> Dict[str, hl.expr.Aggregation]:
"""
Default aggregation function to add aggregations for min/max of score, number of ClinVar variants, number of truth
variants (omni, mills, hapmap, and kgp_phase1), and family statistics.
.. note::
This function uses `ht._parent` to get the origin Table from the GroupedTable for the aggregation
This can easily be combined with the GroupedTable returned by `compute_grouped_binned_ht`
Example:
.. code-block:: python
binned_ht = create_binned_ht(...)
grouped_binned_ht = compute_grouped_binned_ht(binned_ht)
agg_ht = grouped_binned_ht.aggregate(score_bin_agg(**grouped_binned_ht, ...))
.. note::
The following annotations should be present:
In ht:
- score
- singleton
- positive_train_site
- negative_train_site
- ac_raw - expected that this is the raw allele count before adj filtering
- ac - expected that this is the allele count after adj filtering
- ac_qc_samples_unrelated_raw - allele count before adj filtering for unrelated samples passing sample QC
- info - struct that includes QD, FS, and MQ in order to add an annotation for fail_hard_filters
In truth_ht:
- omni
- mills
- hapmap
- kgp_phase1_hc
In fam_stats_ht:
- n_de_novos_adj
- n_de_novos_raw
- n_transmitted_raw
- n_untransmitted_raw
Automatic aggregations that will be done are:
- `min_score` - minimun of score annotation per group
- `max_score` - maiximum of score annotation per group
- `n` - count of variants per group
- `n_ins` - count of insertion per group
- `n_ins` - count of insertion per group
- `n_del` - count of deletions per group
- `n_ti` - count of transitions per group
- `n_tv` - count of trnasversions per group
- `n_1bp_indel` - count of one base pair indels per group
- `n_mod3bp_indel` - count of indels with a length divisible by three per group
- `n_singleton` - count of singletons per group
- `fail_hard_filters` - count of variants per group with QD < 2 | FS > 60 | MQ < 30
- `n_vqsr_pos_train` - count of variants that were a VQSR positive train site per group
- `n_vqsr_neg_train` - count of variants that were a VQSR negative train site per group
- `n_clinvar` - count of clinvar variants
- `n_de_novos_singleton_adj` - count of singleton de novo variants after adj filtration
- `n_de_novo_singleton` - count of raw unfiltered singleton de novo variants
- `n_de_novos_adj` - count of adj filtered de novo variants
- `n_de_novos` - count of raw unfiltered de novo variants
- `n_trans_singletons` - count of transmitted singletons
- `n_untrans_singletons` - count of untransmitted singletons
- `n_omni` - count of omni truth variants
- `n_mills` - count of mills truth variants
- `n_hapmap` - count of hapmap truth variants
- `n_kgp_phase1_hc` - count of 1000 genomes phase 1 high confidence truth variants
:param ht: Table that aggregation will be performed on
:param fam_stats_ht: Path to family statistics HT
:return: a dictionary containing aggregations to perform on ht
"""
# Annotate binned table with the evaluation data
ht = ht._parent
indel_length = hl.abs(ht.alleles[0].length() - ht.alleles[1].length())
# Load external evaluation data
build = get_reference_genome(ht.locus).name
clinvar = (
grch37_resources.reference_data.clinvar
if build == "GRCh37"
else grch38_resources.reference_data.clinvar
).ht()[ht.key]
truth_data = (
grch37_resources.reference_data.get_truth_ht()
if build == "GRCh37"
else grch38_resources.reference_data.get_truth_ht()
)[ht.key]
fam = fam_stats_ht[ht.key]
return dict(
min_score=hl.agg.min(ht.score),
max_score=hl.agg.max(ht.score),
n=hl.agg.count(),
n_ins=hl.agg.count_where(hl.is_insertion(ht.alleles[0], ht.alleles[1])),
n_del=hl.agg.count_where(hl.is_deletion(ht.alleles[0], ht.alleles[1])),
n_ti=hl.agg.count_where(hl.is_transition(ht.alleles[0], ht.alleles[1])),
n_tv=hl.agg.count_where(hl.is_transversion(ht.alleles[0], ht.alleles[1])),
n_1bp_indel=hl.agg.count_where(indel_length == 1),
n_mod3bp_indel=hl.agg.count_where((indel_length % 3) == 0),
n_singleton=hl.agg.count_where(ht.singleton),
fail_hard_filters=hl.agg.count_where(
(ht.info.QD < 2) | (ht.info.FS > 60) | (ht.info.MQ < 30)
),
n_pos_train=hl.agg.count_where(ht.positive_train_site),
n_neg_train=hl.agg.count_where(ht.negative_train_site),
n_clinvar=hl.agg.count_where(hl.is_defined(clinvar)),
n_de_novos_singleton_adj=hl.agg.filter(
ht.ac == 1, hl.agg.sum(fam.n_de_novos_adj)
),
n_de_novo_singleton=hl.agg.filter(
ht.ac_raw == 1, hl.agg.sum(fam.n_de_novos_raw)
),
n_de_novos_adj=hl.agg.sum(fam.n_de_novos_adj),
n_de_novo=hl.agg.sum(fam.n_de_novos_raw),
n_trans_singletons=hl.agg.filter(
ht.ac_raw == 2, hl.agg.sum(fam.n_transmitted_raw)
),
n_untrans_singletons=hl.agg.filter(
(ht.ac_raw < 3) & (ht.ac_qc_samples_unrelated_raw == 1),
hl.agg.sum(fam.n_untransmitted_raw),
),
n_train_trans_singletons=hl.agg.filter(
(ht.ac_raw == 2) & ht.positive_train_site, hl.agg.sum(fam.n_transmitted_raw)
),
n_omni=hl.agg.count_where(truth_data.omni),
n_mills=hl.agg.count_where(truth_data.mills),
n_hapmap=hl.agg.count_where(truth_data.hapmap),
n_kgp_phase1_hc=hl.agg.count_where(truth_data.kgp_phase1_hc),
)
#2. Remove samples that have not passed initial QC:
print("2. Remove samples that have not passed initial QC:")
mt_result = mt.filter_cols(hl.is_defined(exclude_samples_table[mt.s]),
keep=False)
#3. Split multi
print("3. Split multi")
mt_split = hl.split_multi_hts(mt_result, keep_star=False)
# 4. annotate SNPs,indels
print('Annotating rows with snp and indel info')
mt = mt_split.annotate_rows(Variant_Type=hl.cond(
(hl.is_snp(mt_split.alleles[0], mt_split.alleles[1])), "SNP",
hl.cond(
hl.is_insertion(mt_split.alleles[0], mt_split.alleles[1]), "INDEL",
hl.cond(hl.is_deletion(mt_split.alleles[0], mt_split.alleles[1]),
"INDEL", "Other"))))
#4. Sample qc and variant qc
print("4. Sample qc and variant qc ")
mt_sampleqc = hl.sample_qc(mt, name='sample_QC_Hail')
mt2 = hl.variant_qc(mt_sampleqc, name='variant_QC_Hail')
#5.Annotate COMMON AND RARE VARIANTS to apply separate filters
print("Annotate COMMON AND RARE VARIANTS to apply separate filters")
#mt_common = mt_filtered.filter_rows(mt_filtered.variant_qc.AF[1] > 0.05)
mt2 = mt2.annotate_rows(
maf=hl.cond(mt2.variant_QC_Hail.AF[1] < 0.01, "< 1%",
hl.cond(mt2.variant_QC_Hail.AF[1] < 0.05, "1%-5%", ">5%")))
#6. Common variants filtering:
def main():
print("main")
run_hash = "91ba5f38"
ht=hl.read_table(f'{lustre_dir}/variant_qc/models/{run_hash}_score_binning.ht')
mt = hl.read_matrix_table(
f'{lustre_dir}/MegaWESSanger_cohorts_sampleQC_filtered.mt')
table_cohort = hl.import_table(
f"{lustre_dir}/sanger_cohorts_corrected_ukbb_july_2020.tsv", delimiter="\t").key_by('s')
mt = mt.annotate_cols(cohort=table_cohort[mt.s].cohort)
df = pd.read_csv(
f"{lustre_dir}/sanger_cohorts_corrected_ukbb_july_2020.tsv", sep="\t")
cohorts_array = df.cohort.unique()
mt = mt.annotate_rows(
MAF_cohorts=hl.agg.group_by(mt.cohort,
hl.min(hl.agg.call_stats(mt.GT, mt.alleles).AF))
)
mt = mt.annotate_rows(
AN_cohorts=hl.agg.group_by(mt.cohort,
hl.min(hl.agg.call_stats(mt.GT, mt.alleles).AN))
)
mt = mt.annotate_rows(
AC_cohorts=hl.agg.group_by(mt.cohort,
hl.min(hl.agg.call_stats(mt.GT, mt.alleles).AC))
)
mt = mt.annotate_rows(
missingness_cohorts=hl.agg.group_by(mt.cohort, hl.min(
(hl.agg.count_where(hl.is_missing(mt['GT']))) / mt.count_rows()*2))
)
mt = mt.annotate_rows(
info=mt.info.annotate(cohort_names=mt.MAF_cohorts.keys())
)
mt = mt.annotate_rows(
info=mt.info.annotate(MAF_cohorts_values=mt.MAF_cohorts.values())
)
mt = mt.annotate_rows(
info=mt.info.annotate(AN_cohorts_values=mt.AN_cohorts.values())
)
mt = mt.annotate_rows(
info=mt.info.annotate(AC_cohorts=mt.AC_cohorts.values())
)
mt = mt.annotate_rows(
info=mt.info.annotate(
missingness_cohorts_values=mt.missingness_cohorts.values())
)
mt = mt.annotate_rows(
Variant_Type=hl.cond((hl.is_snp(mt.alleles[0], mt.alleles[1])), "SNP",
hl.cond(
hl.is_insertion(
mt.alleles[0], mt.alleles[1]),
"INDEL",
hl.cond(hl.is_deletion(mt.alleles[0],
mt.alleles[1]), "INDEL",
"Other"))))
mt = mt.annotate_rows(
info=mt.info.annotate(
rf_probability=ht[mt.row_key].rf_probability['TP'])
)
mt = mt.annotate_rows(
info=mt.info.annotate(score=ht[mt.row_key].score)
)
mt = mt.annotate_rows(
info=mt.info.annotate(bin=ht[mt.row_key].bin)
)
filter_column_annotation = (
hl.case()
.when(((mt.Variant_Type == "SNP") & (mt.info.bin <= SNV_PASS_BIN)), "PASS")
.when(((mt.Variant_Type == "INDEL") & (mt.info.bin <= INDEL_PASS_BIN)), "PASS")
.default(".") # not pass for rest
)
# mt_annotated = mt.annotate_rows(mt.filters=filter_column_annotation)
mt1 = mt.annotate_rows(
filtercol=((filter_column_annotation))
)
mt_fail = mt1.filter_rows(mt1.filtercol == ".")
print(mt_fail.count())
mt2 = mt1.annotate_rows(filters=mt1.filters.add(mt1.filtercol))
mt_fail2 = mt2.filter_rows(mt2.filters.contains("."))
mt_pass = mt2.filter_rows(mt2.filters.contains("PASS"))
print(f'Failed:{mt_fail2.count()}')
print(f'Passed:{mt_pass.count()}')
mt2 = mt2.checkpoint(
f'{lustre_dir}/variant_qc/megaWES_final_after_RF_{run_hash}.mt', overwrite=True)
#Remove gt and entries and samples
mt1 = mt2.select_entries()
mt_fin = mt2.filter_cols(mt2['s'] == 'sample')
chroms=[*range(1,23),"X","Y"]
chromosomes=["chr"+ str(chr) for chr in chroms]
for chromosome in chromosomes:
print(chromosome)
mt=mt_fin.filter_rows(mt_fin.locus.contig==chromosome)
mt.write(f'{lustre_dir}/final_matrixtables_VCFs/{chromosome}_after_RF_{run_hash}_NOSAMPLES_GT.mt',overwrite=True)
hl.export_vcf(
mt, f'{lustre_dir}/final_matrixtables_VCFs/VCFs/{chromosome}_after_RF_{run_hash}_LOCI_only',parallel='separate_header')
