聚类方法,聚类后选择打分最高那个分子,并对 karamadock 的结果求交集

scripts/extract_and_intersect.py

@@ -0,0 +1,59 @@
+import pandas as pd
+from pathlib import Path
+import os
+
+def process_cluster_file(cluster_file, score_file, output_file):
+    # 检查文件是否存在
+    if not os.path.exists(cluster_file):
+        raise FileNotFoundError(f"聚类文件不存在: {cluster_file}")
+    if not os.path.exists(score_file):
+        raise FileNotFoundError(f"评分文件不存在: {score_file}")
+    
+    # 读取聚类结果文件
+    cluster_df = pd.read_csv(cluster_file)
+    
+    # 提取filename列的stem属性
+    cluster_df['filename_stem'] = cluster_df['filename'].apply(
+        lambda x: Path(x).stem.split('_out')[0]
+    )
+    
+    # 读取score文件
+    score_df = pd.read_csv(score_file)
+    
+    # 获取两个文件的交集
+    intersection = pd.merge(
+        cluster_df, 
+        score_df, 
+        left_on='filename_stem', 
+        right_on='pdb_id',
+        how='inner'
+    )
+    
+    # 保存结果
+    intersection.to_csv(output_file, index=False)
+    
+    return len(intersection)
+
+if __name__ == "__main__":
+    # 使用绝对路径确保文件位置正确
+    base_dir = "/Users/lingyuzeng/Downloads/211.69.141.180/202508021824/vina"
+    
+    # 处理fgbar数据
+    fgbar_count = process_cluster_file(
+        f"{base_dir}/scripts/finally_data/cluster_best/fgbar_cluster_best_vina_butina_butina.csv",
+        f"{base_dir}/result/karamadock/FgBar1_score.csv",
+        f"{base_dir}/scripts/finally_data/cluster_best/fgbar_intersection.csv"
+    )
+    
+    # 处理trpe数据
+    trpe_count = process_cluster_file(
+        f"{base_dir}/scripts/finally_data/cluster_best/trpe_cluster_best_vina_butina_butina.csv",
+        f"{base_dir}/result/karamadock/TrpE_score.csv",
+        f"{base_dir}/scripts/finally_data/cluster_best/trpe_intersection.csv"
+    )
+    
+    print(f"fgbar交集数量: {fgbar_count}")
+    print(f"trpe交集数量: {trpe_count}")
+    
+    # 验证输出文件是否生成
+    print("脚本执行完成")