boltz-vsynthes 1.0.28__py3-none-any.whl → 1.0.30__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]  # Access sequence directly from the dictionary
+                    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]  # Access sequence directly from the dictionary
+                    seq = target["sequences"][0]["protein"]["sequence"]
             else:
                 msg = f"Protein must have either 'sequence' or 'pdb' field: {item}"
                 raise ValueError(msg)
@@ -1041,9 +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)
-                print(target)
-                seq = target.sequences[0]
-                print(seq)
+                seq = target["sequences"][0]["ligand"]["smiles"]
             elif "ccd" in item[entity_type]:
                 seq = str(item[entity_type]["ccd"])
             else:
@@ -1173,7 +1171,25 @@ 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
@@ -1199,7 +1215,7 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
             )
 
         # Parse a non-polymer
-        elif (entity_type == "ligand") and "ccd" in (items[0][entity_type]):
+        elif (entity_type == "ligand") and ("ccd" in items[0][entity_type]):
             seq = items[0][entity_type]["ccd"]
 
             if isinstance(seq, str):
@@ -1291,6 +1307,60 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
                 "cyclic", False
             ), "Cyclic flag is not supported for ligands"
 
+        elif (entity_type == "ligand") and ("sdf" in items[0][entity_type]):
+            # Handle SDF file
+            sdf_path = Path(items[0][entity_type]["sdf"])
+            from boltz.data.parse.sdf import parse_sdf
+            target = parse_sdf(sdf_path, ccd, mol_dir)
+            mol = target["sequences"][0]["ligand"]["smiles"]
+
+            if affinity:
+                mol = standardize(mol)
+
+            mol = AllChem.MolFromSmiles(mol)
+            mol = AllChem.AddHs(mol)
+
+            # Set atom names
+            canonical_order = AllChem.CanonicalRankAtoms(mol)
+            for atom, can_idx in zip(mol.GetAtoms(), canonical_order):
+                atom_name = atom.GetSymbol().upper() + str(can_idx + 1)
+                if len(atom_name) > 4:
+                    msg = (
+                        f"{mol} has an atom with a name longer than "
+                        f"4 characters: {atom_name}."
+                    )
+                    raise ValueError(msg)
+                atom.SetProp("name", atom_name)
+
+            success = compute_3d_conformer(mol)
+            if not success:
+                msg = f"Failed to compute 3D conformer for {mol}"
+                raise ValueError(msg)
+
+            mol_no_h = AllChem.RemoveHs(mol, sanitize=False)
+            affinity_mw = AllChem.Descriptors.MolWt(mol_no_h) if affinity else None
+            extra_mols[f"LIG{ligand_id}"] = mol_no_h
+            residue = parse_ccd_residue(
+                name=f"LIG{ligand_id}",
+                ref_mol=mol,
+                res_idx=0,
+            )
+
+            ligand_id += 1
+            parsed_chain = ParsedChain(
+                entity=entity_id,
+                residues=[residue],
+                type=const.chain_type_ids["NONPOLYMER"],
+                cyclic_period=0,
+                sequence=None,
+                affinity=affinity,
+                affinity_mw=affinity_mw,
+            )
+
+            assert not items[0][entity_type].get(
+                "cyclic", False
+            ), "Cyclic flag is not supported for ligands"
+
         else:
             msg = f"Invalid entity type: {entity_type}"
             raise ValueError(msg)

{boltz_vsynthes-1.0.28.dist-info → boltz_vsynthes-1.0.30.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.28
+Version: 1.0.30
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.28.dist-info → boltz_vsynthes-1.0.30.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=578YHuUxV-L9LooF-ONet1zuX2HjRp8crMbIJBYw-cM,60899
+boltz/data/parse/schema.py,sha256=kNu28U2_MGiecwWNlcxgaDH3WOcO0P-q2LdoSPSb66w,63826
 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-1.0.28.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
-boltz_vsynthes-1.0.28.dist-info/METADATA,sha256=1YykYGlaJ5sJTxTb--lf-99d_oBzJ_XE4HvVrQFANZ8,7171
-boltz_vsynthes-1.0.28.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-boltz_vsynthes-1.0.28.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
-boltz_vsynthes-1.0.28.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
-boltz_vsynthes-1.0.28.dist-info/RECORD,,
+boltz_vsynthes-1.0.30.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
+boltz_vsynthes-1.0.30.dist-info/METADATA,sha256=LCqHhIkKBAtMf8t6kbT4xoPr54lLZb86Tuy9KOgWYdc,7171
+boltz_vsynthes-1.0.30.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+boltz_vsynthes-1.0.30.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
+boltz_vsynthes-1.0.30.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
+boltz_vsynthes-1.0.30.dist-info/RECORD,,