add convert name propety

scripts/sdf_to_smiles.py

@@ -2,43 +2,45 @@
 # -*- coding: utf-8 -*-
 
 import os
+import csv
 from rdkit import Chem
+from pathlib import Path
+
 
 # 当前目录路径
 current_dir = os.path.dirname(os.path.abspath(__file__))
 
 # 输入SDF文件路径
-sdf_file = os.path.join(current_dir, 'fgbar_vina_SP_1_pv.sdf')
+sdf_file = Path(current_dir) / "../data/fgbar_vina_SP_1_pv.sdf"
 
-# 输出SMILES文件路径
+# 输出CSV文件路径
-smiles_file = os.path.join(current_dir, 'molecules.txt')
+csv_file = Path(current_dir) / "../data/molecules.csv"
 
-def sdf_to_smiles(sdf_path, output_path):
+
-    """读取SDF文件中的分子并将其转换为SMILES格式保存到文本文件"""
+def sdf_to_csv(sdf_path, output_path):
-    # 读取SDF文件
+    """读取SDF文件中的分子并将其转换为SMILES和IDENTIFIER保存到CSV文件"""
     suppl = Chem.SDMolSupplier(sdf_path)
-    
-    # 计数有效分子数量
     valid_mol_count = 0
 
-    # 打开输出文件
+    with open(output_path, 'w', newline='', encoding='utf-8') as f:
-    with open(output_path, 'w') as f:
+        writer = csv.writer(f)
-        # 遍历所有分子
+        # 写表头
-        for i, mol in enumerate(suppl):
+        writer.writerow(["smiles", "name"])
-            if mol is not None:  # 确保分子有效
+
-                # 获取SMILES
+        for mol in suppl:
+            if mol is not None:
                 smiles = Chem.MolToSmiles(mol)
-                # 写入文件
+                name = mol.GetProp("_Name") if mol.HasProp("_Name") else ""
-                f.write(f"{smiles}\n")
+                writer.writerow([smiles, name])
                 valid_mol_count += 1
 
     return valid_mol_count
 
 def main():
     print(f"正在读取SDF文件: {sdf_file}")
-    mol_count = sdf_to_smiles(sdf_file, smiles_file)
+    mol_count = sdf_to_csv(sdf_file.as_posix(), csv_file)
     print(f"成功处理了 {mol_count} 个分子")
-    print(f"SMILES已保存到: {smiles_file}")
+    print(f"结果已保存到: {csv_file}")
 
 if __name__ == "__main__":
     main()