def simplify_transcript_data(input_file, output_file):
    with open(input_file, 'r') as file:
        lines = file.readlines()

    with open(output_file, 'w') as file:
        for line in lines:
            if line.startswith('>'):
                # 提取转录本ID
                transcript_id = line.split()[0]
                file.write(transcript_id + '\n')
            else:
                # 写入蛋白质序列
                file.write(line)

if __name__ == "__main__":
    input_file = 'final.modified.gene.pep.fa'  # 输入文件路径
    output_file = 'path_to_your_output_file.txt'  # 输出文件路径
    simplify_transcript_data(input_file, output_file)