improve bond recognition and glycine recognition

app.py

@@ -17,11 +17,12 @@ from rdkit import Chem
 class PeptideAnalyzer:
     def __init__(self):
         self.bond_patterns = [
-            r'OC\(=O\)',  # ester bond
-            r'N\(C\)C\(=O\)',  # N-methylated peptide bond
-            r'N[12]?C\(=O\)',  # peptide bond (including Pro N1/N2)
-            r'C\(=O\)N\(C\)',  # N-methylated peptide bond reverse
-            r'C\(=O\)N'  # peptide bond reverse
+            (r'OC\(=O\)', 'ester'),  # Ester bond
+            (r'N\(C\)C\(=O\)', 'n_methyl'),  # N-methylated peptide bond
+            (r'N[12]C\(=O\)', 'proline'),  # Proline peptide bond
+            (r'NC\(=O\)', 'peptide'),  # Standard peptide bond
+            (r'C\(=O\)N\(C\)', 'n_methyl_reverse'),  # Reverse N-methylated
+            (r'C\(=O\)N[12]?', 'peptide_reverse')  # Reverse peptide bond
         ]
     
     def is_peptide(self, smiles):
@@ -39,12 +40,7 @@ class PeptideAnalyzer:
         n_methyl_pattern = Chem.MolFromSmarts('[N;H0;$(NC)](C)[C](=O)')
         if mol.HasSubstructMatch(n_methyl_pattern):
             return True
-            
-        # Look for ester bonds in cyclic depsipeptides: OC(=O) pattern
-        ester_bond_pattern = Chem.MolFromSmarts('O[C](=O)')
-        if mol.HasSubstructMatch(ester_bond_pattern):
-            return True
-            
+        
         return False
 
     def is_cyclic(self, smiles):
@@ -107,18 +103,8 @@ class PeptideAnalyzer:
                     'pattern': match.group()
                 })
                 used.update(range(match.start(), match.end()))
-
-        # Then find all bonds, including N2C(=O)
-        bond_patterns = [
-            (r'OC\(=O\)', 'ester'),
-            (r'N\(C\)C\(=O\)', 'n_methyl'),
-            (r'N[12]C\(=O\)', 'peptide'),  # Pro peptide bonds
-            (r'NC\(=O\)', 'peptide'),  # Regular peptide bonds
-            (r'C\(=O\)N\(C\)', 'n_methyl'),
-            (r'C\(=O\)N[12]?', 'peptide')
-        ]
         
-        for pattern, bond_type in bond_patterns:
+        for pattern, bond_type in self.bond_patterns:
             for match in re.finditer(pattern, smiles):
                 if not any(p in range(match.start(), match.end()) for p in used):
                     positions.append({
@@ -216,8 +202,14 @@ class PeptideAnalyzer:
             return '4F-Phe', mods
         
         # Regular residue identification
-        if 'NCC(=O)' in content:
-            return 'Gly', mods
+        if ('NCC(=O)' in content) or (content == 'C'):
+            # Middle case - between bonds
+            if segment.get('bond_before') and segment.get('bond_after'):
+                if ('C(=O)N' in segment['bond_before'] or 'C(=O)N(C)' in segment['bond_before']):
+                    return 'Gly', mods
+            # Terminal case - at the end
+            elif segment.get('bond_before') and segment.get('bond_before').startswith('C(=O)N'):
+                return 'Gly', mods
             
         if 'CC(C)C[C@H]' in content or 'CC(C)C[C@@H]' in content:
             return 'Leu', mods
@@ -694,7 +686,7 @@ def process_input(smiles_input=None, file_obj=None, show_linear=False, show_segm
     return "No input provided.", None, None
 
 iface = gr.Interface(
-    fn=process_input,  # Your processing function
+    fn=process_input,
     inputs=[
         gr.Textbox(
             label="Enter SMILES string",