Variant Prioritization

Basic Filtering Pipeline

import pandas as pd

def prioritize_variants(df, gnomad_af_col='gnomad_af', clinvar_col='clinvar_sig'):
    '''Basic variant prioritization pipeline

    Filters:
    1. Rare in population (gnomAD AF < 0.01)
    2. Pathogenic/likely pathogenic in ClinVar OR VUS with low AF
    '''
    # Filter rare variants (ACMG PM2: AF < 1%)
    rare = df[df[gnomad_af_col].isna() | (df[gnomad_af_col] < 0.01)]