查看vcf基因型

import argparse

def extract_genotypes(input_vcf, output_file):
    with open(input_vcf, 'r') as infile, open(output_file, 'w') as outfile:
        for line in infile:
            if line.startswith('#'):
                continue  # 跳过注释行
            parts = line.split('\t')
            genotype = parts[9].split(':')[0]  # 假设基因型在第 10 列（索引 9），且以冒号分割的第一个部分为基因型
            outfile.write(genotype + '\n')

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Extract genotypes from VCF file')
    parser.add_argument('-i', '--input_vcf', required=True, help='Input VCF file')
    parser.add_argument('-o', '--output_file', required=True, help='Output file to save genotypes')
    args = parser.parse_args()

    extract_genotypes(args.input_vcf, args.output_file)

过滤基因型

import argparse

def extract_genotypes(input_vcf, output_file):
    with open(input_vcf, 'r') as infile, open(output_file, 'w') as outfile:
        # 写入 VCF 文件头部
        for line in infile:
            if line.startswith('#'):
                outfile.write(line)
            else:
                break

        # 处理数据行
        for line in infile:
            parts = line.split('\t')
            genotype = parts[9].split(':')[0]
            if genotype not in ['./.', '0/0']:
                outfile.write(line)

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Extract genotypes from VCF file')
    parser.add_argument('-i', '--input_vcf', required=True, help='Input VCF file')
    parser.add_argument('-o', '--output_file', required=True, help='Output file to save genotypes')
    args = parser.parse_args()

    extract_genotypes(args.input_vcf, args.output_file)