add sequence_similarity func

analysis_pdb.py

@@ -13,6 +13,7 @@
 from dataclasses import dataclass, field
 from Bio.PDB import PDBParser
 from Bio.SeqUtils import seq1
+from Bio.Data import IUPACData
 from typing import List, Dict, Tuple, Optional
 from functools import reduce, partial
 from Bio.PDB import MMCIFIO, PDBIO, Chain, Structure
@@ -26,6 +27,8 @@ from copy import deepcopy
 from pymol import cmd
 import pymol
 import os
+# 使用 BioPython 导入氨基酸缩写
+AMINO_ACIDS = set(IUPACData.protein_letters)
 
 @dataclass
 class PDBAnalyzer:
@@ -78,7 +81,23 @@ class PDBAnalyzer:
         with open(out_file, "w") as fid:
             fid.writelines(good)
         return Path(out_file)
+    
+    def sequence_similarity(self, seq1: str, seq2: str) -> float:
+        """
+        Calculate the similarity between two sequences.
 
+        Args:
+        seq1 (str): First sequence.
+        seq2 (str): Second sequence.
+
+        Returns:
+        float: Similarity score between 0 and 1, where 1 is identical.
+        """
+        aligner = PairwiseAligner()
+        aligner.mode = 'global'
+        score = aligner.score(seq1, seq2)
+        max_score = min(len(seq1), len(seq2)) * aligner.match_score
+        return score / max_score
 
     def check_continuity(self, chain, missing_char):
         """