RSV——提取fasta中的信息

1. 提取序列ID

 10 def extract_ids(fasta_file):
 11     ids = []
 12     with open(fasta_file, "r") as handle:
 13         # 读取包含多个序列的 fasta 格式文件
 14         for record in SeqIO.parse(handle, "fasta"):
 15             # Fasta 文件中序列名所在行的第一个词被作为 id 和 name
 16             ids.append(record.id)
 17     return ids

2. 对齐ID

 19 def alphaname_to_fastaname(ids):
 20     #命名对齐
 21     alpha_name = []
 22     #get the number of alphafold_*.pdb
 23     model_num = os.popen('ls alphafold_*.pdb | wc -l').read().strip('\n')
 24     for i in range(int(model_num)):
 25         alpha_name.append('alphafold_'+ str(i))
 26 
 27     #alphafold_name to oscar_name
 28     name_map = dict(zip(alpha_name, ids))
 29     return name_map