从FASTA文件中，仅提取具有指定分类的条目

import re

def extract_entries_with_category(fasta_file, category):
    entries = []
    current_entry = {"header": "", "sequence": ""}
    
    with open(fasta_file, "r") as file:
        for line in file:
            line = line.strip()
            
            if line.startswith(">"):
                if current_entry["header"] != "" and current_entry["sequence"] != "":
                    entries.append(current_entry)
                
                current_entry = {"header": line, "sequence": ""}
            else:
                current_entry["sequence"] += line
        
        # 添加最后一个条目
        if current_entry["header"] != "" and current_entry["sequence"] != "":
            entries.append(current_entry)
    
    # 提取指定分类的条目
    filtered_entries = [entry for entry in entries if re.search(category, entry["header"], re.IGNORECASE)]
    
    # 写入新的FASTA文件
    output_file = fasta_file.split(".")[0] + "_filtered.fasta"
    with open(output_file, "w") as file:
        for entry in filtered_entries:
            file.write(entry["header"] + "\n")
            file.write(entry["sequence"] + "\n")
    
    return output_file

# 示例用法
fasta_file = "example.fasta"
category = "bacteria"
filtered_file = extract_entries_with_category(fasta_file, category)
print("提取的条目已保存到文件:", filtered_file)