How to use the gnomad.resources.grch38 function in gnomad

To help you get started, we’ve selected a few gnomad examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github macarthur-lab / gnomad_hail / gnomad / variant_qc / pipeline.py View on Github external
: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)
github macarthur-lab / gnomad_hail / gnomad / variant_qc / pipeline.py View on Github external
- `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])),
github macarthur-lab / gnomad_hail / gnomad / resources / import_resources.py View on Github external
itertools.chain.from_iterable(
            [
                f"{resource_arg}:",
                wrapper.fill(
                    f"import {getattr(resource, 'import_args', {}).get('path', '???')}"
                ),
                wrapper.fill(f"to {resource.path}"),
                "",
            ]
            for resource_arg, (resource_name, resource) in resources.items()
        )
    )


grch37_resources = get_module_importable_resources(grch37, "grch37")
grch38_resources = get_module_importable_resources(grch38, "grch38")
all_resources = {**grch37_resources, **grch38_resources}


def main(args):
    for resource_arg in args.resources:
        resource_name, resource = all_resources[resource_arg]
        print(f"Importing {resource_name}...")
        resource.import_resource(args.overwrite)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
    parser.add_argument(
        "resources",
        choices=list(all_resources.keys()),
        metavar="resource",