from util import Timer
'''
This script is the baseline that we later compare to.
It loops over genes and performs score-tests, using pre-computed indicator variables (0/1)
'''
# covariates loader
covariatesloader = CovariatesLoaderCSV(
snakemake.params.phenotype,
snakemake.input.covariates_tsv,
snakemake.params.covariate_column_names,
sep='\t',
path_to_phenotypes=snakemake.input.phenotypes_tsv)
# set up burden loaders
bloader_lof = BurdenLoaderHDF5(snakemake.input.h5_lof, snakemake.input.iid_lof,
snakemake.input.gid_lof)
bloader_missense = BurdenLoaderHDF5(snakemake.input.h5_missense,
snakemake.input.iid_missense,
snakemake.input.gid_missense)
# make sure individuals are in the same order
bloader_lof.update_individuals(covariatesloader.get_iids())
bloader_missense.update_individuals(covariatesloader.get_iids())
# gene names to iterate over
genes = np.union1d(bloader_lof.get_vids(), bloader_missense.get_vids())
if isinstance(genes, str):
genes = [genes]
# set up the null model
Y, X = covariatesloader.get_one_hot_covariates_and_phenotype('NoK')
regions.columns = ['chrom', 'start', 'end', 'name']
# discard all genes for which we don't have annotations
regions['gene'] = regions.name.str.split('_', expand=True)[0]
regions.set_index('gene', inplace=True)
genes = intersect_ids(np.unique(regions.index.values), np.unique(eveploader.pos_df.gene))
regions = regions.loc[genes].reset_index()
regions = regions.sort_values(['chrom','start','end'])[['chrom','start','end','name','gene']]
# set up the variant loader (missense variants) for the chromosome
plinkloader = VariantLoaderSnpReader(Bed(bed, count_A1=True, num_threads=4))
plinkloader.update_variants(eveploader.get_vids())
plinkloader.update_individuals(covariatesloader.get_iids())
# set up the protein LOF burden loader
bloader_lof = BurdenLoaderHDF5(h5_lof, iid_lof, gid_lof)
bloader_lof.update_individuals(covariatesloader.get_iids())
# set up local collapsing
collapser = LocalCollapsing(distance_threshold=1.)
# set up the missense genotype + vep loading function
def get_missense(interval):
try:
V1 = eveploader.anno_by_interval(interval, gene=interval['name'].split('_')[0])
except KeyError:
raise GotNone
if V1.index.empty:
raise GotNone