vcf2dataframe.py 文件源码

def calc_AB(vcf):
    ''' Calculate allele balance for all samples in a given 
        pdVCF. Also converts DP & GQ to numeric type.

    Args:
        vcf: pdVCF with genotype information extracted

    Notes:
        ONLY WORKS FOR BIALLELIC VARIANTS
    '''
    sam = vcf.columns.levels[0][0]
    vcf[sam,'DP'] = pd.to_numeric(vcf[sam,'DP'].str.replace('.', '0')) # bcftools places '.' in empty fields
    vcf[sam,'GQ'] = pd.to_numeric(vcf[sam,'GQ'].str.replace('.', '0'))
    AD = vcf.xs('AD', level=1, axis=1).unstack().str.split(",", n=2)
    DP = vcf.xs('DP', level=1, axis=1).unstack()
    AB = round(pd.to_numeric(AD.str[1]) / pd.to_numeric(DP), 2)
    vcf[sam, 'AB'] = AB.tolist()
    return vcf