boltz-vsynthes 1.0.29__py3-none-any.whl → 1.0.31__py3-none-any.whl

boltz/data/parse/schema.py

@@ -1024,12 +1024,12 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
                     # This is a PDB ID
                     from boltz.data.parse.pdb_download import parse_pdb_id
                     target = parse_pdb_id(pdb_path.stem, ccd, mol_dir, pdb_path.parent)
-                    seq = target["sequences"][0]["protein"]["sequence"]  # Access sequence from dict
+                    seq = target["sequences"][0]["protein"]["sequence"]
                 else:
                     # This is a PDB file
                     from boltz.data.parse.pdb import parse_pdb
                     target = parse_pdb(pdb_path, ccd, mol_dir)
-                    seq = target["sequences"][0]["protein"]["sequence"]  # Access sequence from dict
+                    seq = target["sequences"][0]["protein"]["sequence"]
             else:
                 msg = f"Protein must have either 'sequence' or 'pdb' field: {item}"
                 raise ValueError(msg)
@@ -1041,7 +1041,7 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
                 sdf_path = Path(item[entity_type]["sdf"])
                 from boltz.data.parse.sdf import parse_sdf
                 target = parse_sdf(sdf_path, ccd, mol_dir)
-                seq = target["sequences"][0]["ligand"]["smiles"]  # Access sequence from dict
+                seq = target["sequences"][0]["ligand"]["smiles"]
             elif "ccd" in item[entity_type]:
                 seq = str(item[entity_type]["ccd"])
             else:
@@ -1059,6 +1059,7 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
 
     # Check if any affinity ligand is present
     affinity_ligands = set()
+    affinity_proteins = set()
     properties = schema.get("properties", [])
     if properties and not boltz_2:
         msg = "Affinity prediction is only supported for Boltz2!"
@@ -1069,7 +1070,6 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
         if prop_type == "affinity":
             binder = prop["affinity"]["binder"]
             if not isinstance(binder, str):
-                # TODO: support multi residue ligands and ccd's
                 msg = "Binder must be a single chain."
                 raise ValueError(msg)
 
@@ -1077,18 +1077,21 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
                 msg = f"Could not find binder with name {binder} in the input!"
                 raise ValueError(msg)
 
-            if chain_name_to_entity_type[binder] != "ligand":
+            # Allow both protein and ligand as binders
+            if chain_name_to_entity_type[binder] == "protein":
+                affinity_proteins.add(binder)
+            elif chain_name_to_entity_type[binder] == "ligand":
+                affinity_ligands.add(binder)
+            else:
                 msg = (
-                    f"Chain {binder} is not a ligand! "
-                    "Affinity is currently only supported for ligands."
+                    f"Chain {binder} is not a protein or ligand! "
+                    "Affinity is currently only supported for proteins and ligands."
                 )
                 raise ValueError(msg)
 
-            affinity_ligands.add(binder)
-
-    # Check only one affinity ligand is present
-    if len(affinity_ligands) > 1:
-        msg = "Only one affinity ligand is currently supported!"
+    # Check if any affinity binder is present
+    if len(affinity_proteins) + len(affinity_ligands) > 1:
+        msg = "Only one affinity binder is currently supported!"
         raise ValueError(msg)
 
     # Go through entities and parse them
@@ -1111,12 +1114,15 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
             elif isinstance(item[entity_type]["id"], list):
                 ids.extend(item[entity_type]["id"])
 
-        # Check if any affinity ligand is present
+        # Check if any affinity binder is present
         if len(ids) == 1:
-            affinity = ids[0] in affinity_ligands
+            affinity = ids[0] in affinity_ligands or ids[0] in affinity_proteins
         elif (len(ids) > 1) and any(x in affinity_ligands for x in ids):
             msg = "Cannot compute affinity for a ligand that has multiple copies!"
             raise ValueError(msg)
+        elif (len(ids) > 1) and any(x in affinity_proteins for x in ids):
+            # If binder is a protein, allow multiple ligands
+            affinity = True
         else:
             affinity = False
 
@@ -1171,7 +1177,25 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
             unk_token = const.unk_token[entity_type.upper()]
 
             # Extract sequence
-            raw_seq = items[0][entity_type]["sequence"]
+            if "sequence" in items[0][entity_type]:
+                raw_seq = items[0][entity_type]["sequence"]
+            elif "pdb" in items[0][entity_type]:
+                # Handle PDB file
+                pdb_path = Path(items[0][entity_type]["pdb"])
+                if len(pdb_path.stem) == 4 and pdb_path.stem.isalnum():
+                    # This is a PDB ID
+                    from boltz.data.parse.pdb_download import parse_pdb_id
+                    target = parse_pdb_id(pdb_path.stem, ccd, mol_dir, pdb_path.parent)
+                    raw_seq = target["sequences"][0]["protein"]["sequence"]
+                else:
+                    # This is a PDB file
+                    from boltz.data.parse.pdb import parse_pdb
+                    target = parse_pdb(pdb_path, ccd, mol_dir)
+                    raw_seq = target["sequences"][0]["protein"]["sequence"]
+            else:
+                msg = f"Protein must have either 'sequence' or 'pdb' field: {items[0]}"
+                raise ValueError(msg)
+
             entity_to_seq[entity_id] = raw_seq
 
             # Convert sequence to tokens

{boltz_vsynthes-1.0.29.dist-info → boltz_vsynthes-1.0.31.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.29
+Version: 1.0.31
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.29.dist-info → boltz_vsynthes-1.0.31.dist-info}/RECORD

@@ -40,7 +40,7 @@ boltz/data/parse/mmcif.py,sha256=25kEXCkx-OuaawAs7cdz0fxdRu5_CCO0AV00u84PrjQ,368
 boltz/data/parse/mmcif_with_constraints.py,sha256=WHYZckSqUwu-Nb9vmVmxHmC7uxwVrF7AVUeVKsc5wGQ,51473
 boltz/data/parse/pdb.py,sha256=iybk4p2UgUy_ABGprDq_xxyPSdm1HAZsGTM0lhxVEwM,1654
 boltz/data/parse/pdb_download.py,sha256=wge-scX-lOatX0q83W1wOsaql99rYp-6uGWSHEc995M,2718
-boltz/data/parse/schema.py,sha256=CcK-9F7h3fG7VI5zMNzhi2Yjqfq30z-ndBstO_2mx8o,60908
+boltz/data/parse/schema.py,sha256=9H7ZJpKb22KHXmfJAjG_0jz7VbZ1LAYt5eVp34_nwVw,62176
 boltz/data/parse/sdf.py,sha256=fs3MQVClDcCzxJaeVYiDuoh-fUrYc8Tcd5Bz8ws3FKI,2052
 boltz/data/parse/yaml.py,sha256=GRFRMtDD4PQ4PIpA_S1jj0vRaEu2LlZd_g4rN1zUrNo,1505
 boltz/data/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -107,9 +107,9 @@ boltz/model/optim/scheduler.py,sha256=nB4jz0CZ4pR4n08LQngExL_pNycIdYI8AXVoHPnZWQ
 boltz/model/potentials/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 boltz/model/potentials/potentials.py,sha256=vev8Vjfs-ML1hyrdv_R8DynG4wSFahJ6nzPWp7CYQqw,17507
 boltz/model/potentials/schedules.py,sha256=m7XJjfuF9uTX3bR9VisXv1rvzJjxiD8PobXRpcBBu1c,968
-boltz_vsynthes-1.0.29.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
-boltz_vsynthes-1.0.29.dist-info/METADATA,sha256=2NGfvz95nz21zJeUKD-q9ymclZarT3dPCq4dxFXQztw,7171
-boltz_vsynthes-1.0.29.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-boltz_vsynthes-1.0.29.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
-boltz_vsynthes-1.0.29.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
-boltz_vsynthes-1.0.29.dist-info/RECORD,,
+boltz_vsynthes-1.0.31.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
+boltz_vsynthes-1.0.31.dist-info/METADATA,sha256=4hMLLLOG2rXQo4bR4F_kU_jxyKnOVVQhrXiwwsHxDtk,7171
+boltz_vsynthes-1.0.31.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+boltz_vsynthes-1.0.31.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
+boltz_vsynthes-1.0.31.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
+boltz_vsynthes-1.0.31.dist-info/RECORD,,