extract_fasta_序列提取_

# -*- coding: utf-8 -*- import os import sys import shutil from pprint import pprint def extract_fasta(file1, match_list): """ 从file1里检索match_list的内容，并写入new_file :param file1: 输入文件的路径 :param match_list: list 格式的检索字段 :return: new_file: 新文件的路径 """ if not os.path.isabs(file1): file1 = os.path.abspath(file1) part = file1.rpartition('.') new_file = part[0] + '_1_taxa.' + part[2] with open(file1) as f1, open(new_file, 'w') as f2: content = f1.readlines() lines_num = len(content) for match_str in match_list: for line_num in range(lines_num): if match_str in content[line_num]: f2.write(content[line_num]) f2.write(content[line_num+1]) break return new_file def batch_extract_fasta(path, match_list, file_type='.fas'): """ 读取 path 路径下的所有 fasta 文件，并提取出现在 match_list 中的字符串至当前路径下的 new 文件夹中 :param path: fasta 文件所在的路径 :param match_list: 需要匹配的字符串列表 :param file_type: None :return: """ if not os.path.isabs(path): path = os.path.abspath(path) result_path = os.path.join(path, 'new') if not os.path.exists(result_path): os.makedirs(result_path) file_list = [os.path.join(path, file) for file in os.listdir(path) if file.endswith(file_type)] for file in file_list: new_file = extract_fasta(file, match_list) # 将结果移动至 new 文件夹下 part = new_file.rpartition(os.sep) result_file = os.path.join(part[0], 'new', part[2]) shutil.move(new_file, result_file) # cmd 直接传参调用 if __name__ == '__main__': path = sys.argv[1] file = sys.argv[2] with open(file) as f: content_list = [line.strip() for line in f.readlines() if len(line) > 1] batch_extract_fasta(path, content_list) # 内部调试代码块 # if __name__ == '__main__': # path = 'data' # file = 'extracted.txt' # with open(file) as f: # content_list = [line.strip() for line in f.readlines() if len(line) > 1] # batch_extract_fasta(path, content_list)