38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
import sys
|
||
|
|
from Bio import SeqIO
|
||
|
|
|
||
|
|
def normalize_id(header):
|
||
|
|
"""用于匹配的标准化ID：去掉版本号，统一大写"""
|
||
|
|
main_id = header.split()[0] # 去掉空格后的描述
|
||
|
|
main_id = main_id.split('.')[0] # 去掉 .1/.2 等版本号
|
||
|
|
return main_id.upper()
|
||
|
|
|
||
|
|
def main():
|
||
|
|
if len(sys.argv) != 4:
|
||
|
|
print(f"用法: python {sys.argv[0]} <input_fasta> <id_list> <output_fasta>")
|
||
|
|
sys.exit(1)
|
||
|
|
|
||
|
|
fasta_file = sys.argv[1]
|
||
|
|
id_list_file = sys.argv[2]
|
||
|
|
output_file = sys.argv[3]
|
||
|
|
|
||
|
|
# 读取 ID list，并统一大写
|
||
|
|
with open(id_list_file) as f:
|
||
|
|
id_list = set(line.strip().upper() for line in f if line.strip())
|
||
|
|
|
||
|
|
# 提取序列并修订 header
|
||
|
|
with open(output_file, "w") as out_f:
|
||
|
|
for record in SeqIO.parse(fasta_file, "fasta"):
|
||
|
|
norm_id = normalize_id(record.id)
|
||
|
|
if norm_id in id_list:
|
||
|
|
# 修订 header，只保留第一个空格前部分
|
||
|
|
record.id = record.id.split()[0]
|
||
|
|
record.description = "" # 去掉原 description
|
||
|
|
SeqIO.write(record, out_f, "fasta")
|
||
|
|
|
||
|
|
print(f"提取完成，输出文件：{output_file}")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|