boltz-vsynthes 1.0.15__py3-none-any.whl → 1.0.17__py3-none-any.whl

boltz/data/parse/pdb.py

@@ -1,17 +1,19 @@
+import os
 from pathlib import Path
 from typing import Optional
 
 from Bio import PDB
-from Bio.Data.IUPACData import protein_letters_3to1
+from Bio.PDB.PDBParser import PDBParser
+from Bio.PDB.Polypeptide import PPBuilder
 from rdkit import Chem
 from rdkit.Chem.rdchem import Mol
 
 from boltz.data.types import Target
-from boltz.data.parse.yaml import parse_boltz_schema
+from boltz.data.parse.schema import parse_boltz_schema
 
 
 def parse_pdb(
-    path: Path,
+    pdb_path: Path,
     ccd: dict[str, Mol],
     mol_dir: Path,
     boltz2: bool = False,
@@ -20,14 +22,14 @@ def parse_pdb(
 
     Parameters
     ----------
-    path : Path
+    pdb_path : Path
         Path to the PDB file.
     ccd : Dict
         Dictionary of CCD components.
     mol_dir : Path
         Path to the directory containing the molecules.
-    boltz2 : bool
-        Whether to parse the input for Boltz2.
+    boltz2 : bool, optional
+        Whether to use Boltz2 format, by default False.
 
     Returns
     -------
@@ -35,31 +37,25 @@ def parse_pdb(
         The parsed target.
     """
     # Read PDB file
-    parser = PDB.PDBParser(QUIET=True)
-    structure = parser.get_structure("protein", str(path))
+    parser = PDBParser(QUIET=True)
+    structure = parser.get_structure("protein", str(pdb_path))
+    ppb = PPBuilder()
 
     # Convert to yaml format
     sequences = []
     for model in structure:
         for chain in model:
-            # Get chain sequence
-            seq = ""
-            for residue in chain:
-                if residue.id[0] == " ":  # Only standard residues
-                    try:
-                        seq += protein_letters_3to1[residue.resname]
-                    except KeyError:
-                        continue
-
-            if seq:  # Only add if sequence is not empty
-                molecule = {
-                    "protein": {
-                        "id": chain.id,
-                        "sequence": seq,
-                        "modifications": [],
-                    },
-                }
-                sequences.append(molecule)
+            for pp in ppb.build_peptides(chain):
+                seq = str(pp.get_sequence())
+                if seq:  # Only add if sequence is not empty
+                    molecule = {
+                        "protein": {
+                            "id": chain.id,
+                            "sequence": seq,
+                            "modifications": [],
+                        },
+                    }
+                    sequences.append(molecule)
 
     data = {
         "sequences": sequences,
@@ -67,5 +63,4 @@ def parse_pdb(
         "version": 1,
     }
 
-    name = path.stem
-    return parse_boltz_schema(name, data, ccd, mol_dir, boltz2) 
+    return parse_boltz_schema(pdb_path.stem, data, ccd, mol_dir, boltz2) 

boltz/data/parse/pdb_download.py

@@ -4,12 +4,13 @@ from typing import Optional
 
 import requests
 from Bio import PDB
-from Bio.Data.IUPACData import protein_letters_3to1
+from Bio.PDB.PDBParser import PDBParser
+from Bio.PDB.PPBuilder import PPBuilder
 from rdkit import Chem
 from rdkit.Chem.rdchem import Mol
 
 from boltz.data.types import Target
-from boltz.data.parse.yaml import parse_boltz_schema
+from boltz.data.parse.schema import parse_boltz_schema
 
 
 def download_pdb(pdb_id: str, cache_dir: Path) -> Path:
@@ -67,8 +68,8 @@ def parse_pdb_id(
         Path to the directory containing the molecules.
     cache_dir : Path
         The directory to cache downloaded PDB files.
-    boltz2 : bool
-        Whether to parse the input for Boltz2.
+    boltz2 : bool, optional
+        Whether to use Boltz2 format, by default False.
 
     Returns
     -------
@@ -79,31 +80,25 @@ def parse_pdb_id(
     pdb_path = download_pdb(pdb_id, cache_dir)
     
     # Read PDB file
-    parser = PDB.PDBParser(QUIET=True)
+    parser = PDBParser(QUIET=True)
     structure = parser.get_structure("protein", str(pdb_path))
+    ppb = PPBuilder()
 
     # Convert to yaml format
     sequences = []
     for model in structure:
         for chain in model:
-            # Get chain sequence
-            seq = ""
-            for residue in chain:
-                if residue.id[0] == " ":  # Only standard residues
-                    try:
-                        seq += protein_letters_3to1[residue.resname]
-                    except KeyError:
-                        continue
-
-            if seq:  # Only add if sequence is not empty
-                molecule = {
-                    "protein": {
-                        "id": chain.id,
-                        "sequence": seq,
-                        "modifications": [],
-                    },
-                }
-                sequences.append(molecule)
+            for pp in ppb.build_peptides(chain):
+                seq = str(pp.get_sequence())
+                if seq:  # Only add if sequence is not empty
+                    molecule = {
+                        "protein": {
+                            "id": chain.id,
+                            "sequence": seq,
+                            "modifications": [],
+                        },
+                    }
+                    sequences.append(molecule)
 
     data = {
         "sequences": sequences,

boltz/data/parse/schema.py

@@ -1024,12 +1024,14 @@ 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)
+                    # Get sequence from the first chain
+                    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)
-                # Get sequence from the first chain
-                seq = target.sequences[0]
+                    # Get sequence from the first chain
+                    seq = target.sequences[0]["protein"]["sequence"]
             else:
                 msg = f"Protein must have either 'sequence' or 'pdb' field: {item}"
                 raise ValueError(msg)
@@ -1042,7 +1044,7 @@ def parse_boltz_schema(  # noqa: C901, PLR0915, PLR0912
                 from boltz.data.parse.sdf import parse_sdf
                 target = parse_sdf(sdf_path, ccd, mol_dir)
                 # Get sequence from the first ligand
-                seq = target.sequences[0]
+                seq = target.sequences[0]["ligand"]["sequence"]
             elif "ccd" in item[entity_type]:
                 seq = str(item[entity_type]["ccd"])
             else:

boltz/data/parse/sdf.py

@@ -1,15 +1,49 @@
+import os
 from pathlib import Path
 from typing import Optional
 
 from rdkit import Chem
+from rdkit.Chem import AllChem
 from rdkit.Chem.rdchem import Mol
+import rdkit.Chem.rdmolfiles as rdmolfiles
 
 from boltz.data.types import Target
-from boltz.data.parse.yaml import parse_boltz_schema
+from boltz.data.parse.schema import parse_boltz_schema
+
+
+def _process_sdf(sdf_path: str) -> dict[str, str]:
+    """Process an SDF file and extract SMILES strings.
+
+    Parameters
+    ----------
+    sdf_path : str
+        Path to the SDF file.
+
+    Returns
+    -------
+    dict[str, str]
+        Dictionary mapping molecule names to SMILES strings.
+    """
+    output_dict = {}
+    suppl = rdmolfiles.ForwardSDMolSupplier(sdf_path)
+
+    for mol in suppl:
+        if mol is not None:
+            mol_smiles = rdmolfiles.MolToSmiles(mol)
+            if mol.HasProp("_Name"):
+                mol_name = mol.GetProp("_Name")
+                if mol_name == "":
+                    mol_name = mol_smiles
+            else:
+                mol_name = mol_smiles
+
+            output_dict[mol_name] = mol_smiles
+
+    return output_dict
 
 
 def parse_sdf(
-    path: Path,
+    sdf_path: Path,
     ccd: dict[str, Mol],
     mol_dir: Path,
     boltz2: bool = False,
@@ -18,37 +52,34 @@ def parse_sdf(
 
     Parameters
     ----------
-    path : Path
+    sdf_path : Path
         Path to the SDF file.
     ccd : Dict
         Dictionary of CCD components.
     mol_dir : Path
         Path to the directory containing the molecules.
-    boltz2 : bool
-        Whether to parse the input for Boltz2.
+    boltz2 : bool, optional
+        Whether to use Boltz2 format, by default False.
 
     Returns
     -------
     Target
         The parsed target.
     """
-    # Read SDF file
-    supplier = Chem.SDMolSupplier(str(path))
-    
+    # Process SDF file
+    mol_dict = _process_sdf(str(sdf_path))
+
     # Convert to yaml format
     sequences = []
-    for i, mol in enumerate(supplier):
-        if mol is not None:
-            # Get SMILES
-            smiles = Chem.MolToSmiles(mol)
-            
-            molecule = {
-                "ligand": {
-                    "id": f"L{i+1}",  # Use L1, L2, etc. as chain IDs
-                    "smiles": smiles,
-                },
-            }
-            sequences.append(molecule)
+    for mol_name, smiles in mol_dict.items():
+        molecule = {
+            "ligand": {
+                "id": mol_name,
+                "sequence": smiles,
+                "modifications": [],
+            },
+        }
+        sequences.append(molecule)
 
     data = {
         "sequences": sequences,
@@ -56,5 +87,4 @@ def parse_sdf(
         "version": 1,
     }
 
-    name = path.stem
-    return parse_boltz_schema(name, data, ccd, mol_dir, boltz2) 
+    return parse_boltz_schema(sdf_path.stem, data, ccd, mol_dir, boltz2) 

{boltz_vsynthes-1.0.15.dist-info → boltz_vsynthes-1.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.15
+Version: 1.0.17
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.15.dist-info → boltz_vsynthes-1.0.17.dist-info}/RECORD

@@ -38,10 +38,10 @@ boltz/data/parse/csv.py,sha256=Hcq8rJW2njczahEr8jfd_o-zxLaNSgJ3YIoC9srIqpw,2518
 boltz/data/parse/fasta.py,sha256=taI4s_CqPtyF0XaLJAsVAJHCL0GXm2g1g8Qeccdxikk,3906
 boltz/data/parse/mmcif.py,sha256=25kEXCkx-OuaawAs7cdz0fxdRu5_CCO0AV00u84PrjQ,36822
 boltz/data/parse/mmcif_with_constraints.py,sha256=WHYZckSqUwu-Nb9vmVmxHmC7uxwVrF7AVUeVKsc5wGQ,51473
-boltz/data/parse/pdb.py,sha256=o2gGGVDxLaKhqPaZjuwfY6gdIyu4iUxczmkvDnEnNls,1808
-boltz/data/parse/pdb_download.py,sha256=FJTX7qHKJ_sBRcHg1PLKlqy6gVuluPDAWOAuYKI4-gM,2931
-boltz/data/parse/schema.py,sha256=uKv1toawysagqi7wnl1njCDrQKM1tNCNDxvcNc6VXK0,60801
-boltz/data/parse/sdf.py,sha256=myFA3bL6MkdPdMFfZHotxJ8yNMGpsc_u6w06YFadeiw,1364
+boltz/data/parse/pdb.py,sha256=R6rDCh6AKLn7n9ELltF1wDORDtR1CFgFnjFdYXKJCNg,1697
+boltz/data/parse/pdb_download.py,sha256=YEvSoYqKAan6EizCICMruC_3v-Vpvc4vpCpwmHPY67E,2808
+boltz/data/parse/schema.py,sha256=pq9PRrm3pyaOH0kJEjtG-rVHEPpr_KmiykvxKsMWnn0,60979
+boltz/data/parse/sdf.py,sha256=z7XTH-a38Rq-grC8bEZUPxGmLyP-g17LCxYWzVkBS_0,2107
 boltz/data/parse/yaml.py,sha256=GRFRMtDD4PQ4PIpA_S1jj0vRaEu2LlZd_g4rN1zUrNo,1505
 boltz/data/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 boltz/data/sample/cluster.py,sha256=9Sx8qP7zGZOAyEspwYFtCTbGTBZnuN-zfCKFbbA_6oI,8175
@@ -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-1.0.15.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
-boltz_vsynthes-1.0.15.dist-info/METADATA,sha256=dZV2p_UkKrGC3QZh40tY3ZEYLO7MylqdH77xA5pSe9I,7171
-boltz_vsynthes-1.0.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-boltz_vsynthes-1.0.15.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
-boltz_vsynthes-1.0.15.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
-boltz_vsynthes-1.0.15.dist-info/RECORD,,
+boltz_vsynthes-1.0.17.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
+boltz_vsynthes-1.0.17.dist-info/METADATA,sha256=s2lJPUPQJ4BMEFa2Hc57Q8e5EYMPuEKr5IO_SxCVTmc,7171
+boltz_vsynthes-1.0.17.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+boltz_vsynthes-1.0.17.dist-info/entry_points.txt,sha256=n5a5I35ntu9lmyr16oZgHPFY0b0YxjiixY7m7nbMTLc,41
+boltz_vsynthes-1.0.17.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
+boltz_vsynthes-1.0.17.dist-info/RECORD,,