add log_numbering_error

analysis_pdb.py

@@ -106,6 +106,7 @@ class PDBAnalyzer:
     log_file: Path = field(init=False)
     logger: logging.Logger = field(init=False)
     ca_distances: List[float] = field(init=False)
+    renumber_errors: List[Dict[str, Tuple[int, int, int]]] = field(default_factory=list)
 
     def __post_init__(self):
         """ 
@@ -197,6 +198,55 @@ class PDBAnalyzer:
         # Return a new instance of PDBAnalyzer pointing to the cleaned file
         return cls(out_file)
     
+    def collect_renumbering_info(self):
+        """
+        收集需要重新编号的残基信息。
+        """
+        self.renumbering_info = {}  # Chain ID as key, list of (original_res_num, new_res_num) tuples as value
+        for chain_id in self.chain_id_list:
+            residues = self.biodata.df['ATOM'][self.biodata.df['ATOM']['chain_id'] == chain_id]
+            unique_residues = residues['residue_number'].unique()
+            sorted_residues = sorted(unique_residues)
+
+            new_res_num = 1
+            self.renumbering_info[chain_id] = []
+            for orig_res_num in sorted_residues:
+                self.renumbering_info[chain_id].append((orig_res_num, new_res_num))
+                new_res_num += 1
+    
+    def log_numbering_error(self, chain_id: str, start_residue: int, end_residue: int, estimated_missing: int):
+        """
+        记录编号错误的信息。
+
+        Args:
+        chain_id (str): 链的ID。
+        start_residue (int): 错误开始的残基编号。
+        end_residue (int): 错误结束的残基编号。
+        estimated_missing (int): 估计的缺失残基数量。
+        """
+        self.renumber_errors.append({
+            "chain_id": chain_id,
+            "start_residue": start_residue,
+            "end_residue": end_residue,
+            "estimated_missing": estimated_missing
+        })
+        
+    # def renumber_residues(self):
+    #     """
+    #     根据收集的残基信息重新编号所有残基。
+    #     """
+    #     for chain_id, res_pairs in self.renumbering_info.items():
+    #         for orig_res_num, new_res_num in res_pairs:
+    #             self.modify_residue_number(chain_id, orig_res_num, new_res_num)
+                
+    # def modify_residue_number(self, chain_id, original_res_num, new_res_num):
+    #     """
+    #     修改指定链上的残基编号。
+    #     """
+    #     mask = (self.biodata.df['ATOM']['chain_id'] == chain_id) & \
+    #         (self.biodata.df['ATOM']['residue_number'] == original_res_num)
+    #     self.biodata.df['ATOM'].loc[mask, 'residue_number'] = new_res_num
+    
     def check_and_log_sequence_issues(self):
         """
         检测并记录每条链的编号问题，并计算相邻残基间的距离。
@@ -224,6 +274,7 @@ class PDBAnalyzer:
                     else:
                         missing_number = int(np.round(distance / 3.8 ) - 1)
                         self.logger.warning(f"Wrong sequence numbering in chain {chain_id} between residues {prev_res[0]} and {next_res[0]}, distance: {distance:.2f} Å, missing residue number: {missing_number}")
+                        self.log_numbering_error(chain_id, prev_res[0], next_res[0], missing_number)
                     
     @classmethod
     def renumber_residues_based_on_issues_and_clean(cls, input_file: Path, out_ext: str = ".renumbered.pdb", chains: Union[List[str], str, None] = None) -> 'PDBAnalyzer':