use sequence_base.py

tcr_pmhc_complexes.py

@@ -12,34 +12,10 @@ from Bio.Data import IUPACData
 from pydantic import BaseModel, Field, FilePath, field_validator
 from typing import Optional, Dict, List, Any, Union
 from pathlib import Path
-
+from sequence_base import ProteinSequence, BaseProteinSequence
 # 使用 BioPython 导入氨基酸缩写
 AMINO_ACIDS = set(IUPACData.protein_letters)
 
-class BaseProteinSequence(BaseModel):
-    sequence: str
-
-    @classmethod
-    def validate_amino_acids(cls, sequence: str) -> str:
-        if not set(sequence).issubset(AMINO_ACIDS):
-            raise ValueError('Sequence contains invalid amino acids, not conforming to IUPAC standards')
-        return sequence
-
-class ProteinSequence(BaseModel):
-    label_asym_id: str
-    auth_asym_id: str
-    sequence: str
-    is_id_consistent: bool = Field(default=False)
-
-    @property
-    def is_id_consistent(self) -> bool:
-        return self.label_asym_id == self.auth_asym_id
-
-    def display_chain_id(self) -> str:
-        if not self.is_id_consistent:
-            return f"{self.label_asym_id} [auth {self.auth_asym_id}]"
-        return self.label_asym_id
-
 class ProteinComplex(BaseModel):
     pdb_id: str
     tcr_alpha: Optional[ProteinSequence] = None