boltz-vsynthes 1.0.15__tar.gz → 1.0.16__tar.gz

{boltz_vsynthes-1.0.15/src/boltz_vsynthes.egg-info → boltz_vsynthes-1.0.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.15
+Version: 1.0.16
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.15 → boltz_vsynthes-1.0.16}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "boltz-vsynthes"
-version = "1.0.15"
+version = "1.0.16"
 requires-python = ">=3.10,<3.13"
 description = "Boltz for VSYNTHES"
 readme = "README.md"

boltz_vsynthes-1.0.16/src/boltz/data/parse/pdb.py

@@ -0,0 +1,66 @@
+import os
+from pathlib import Path
+from typing import Optional
+
+from Bio import PDB
+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.schema import parse_boltz_schema
+
+
+def parse_pdb(
+    pdb_path: Path,
+    ccd: dict[str, Mol],
+    mol_dir: Path,
+    boltz2: bool = False,
+) -> Target:
+    """Parse a PDB file.
+
+    Parameters
+    ----------
+    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, optional
+        Whether to use Boltz2 format, by default False.
+
+    Returns
+    -------
+    Target
+        The parsed target.
+    """
+    # Read PDB file
+    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:
+            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,
+        "bonds": [],
+        "version": 1,
+    }
+
+    return parse_boltz_schema(pdb_path.stem, data, ccd, mol_dir, boltz2) 

{boltz_vsynthes-1.0.15 → boltz_vsynthes-1.0.16}/src/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_vsynthes-1.0.15 → boltz_vsynthes-1.0.16}/src/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_vsynthes-1.0.16/src/boltz/data/parse/sdf.py

@@ -0,0 +1,90 @@
+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.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(
+    sdf_path: Path,
+    ccd: dict[str, Mol],
+    mol_dir: Path,
+    boltz2: bool = False,
+) -> Target:
+    """Parse an SDF file.
+
+    Parameters
+    ----------
+    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, optional
+        Whether to use Boltz2 format, by default False.
+
+    Returns
+    -------
+    Target
+        The parsed target.
+    """
+    # Process SDF file
+    mol_dict = _process_sdf(str(sdf_path))
+
+    # Convert to yaml format
+    sequences = []
+    for mol_name, smiles in mol_dict.items():
+        molecule = {
+            "ligand": {
+                "id": mol_name,
+                "sequence": smiles,
+                "modifications": [],
+            },
+        }
+        sequences.append(molecule)
+
+    data = {
+        "sequences": sequences,
+        "bonds": [],
+        "version": 1,
+    }
+
+    return parse_boltz_schema(sdf_path.stem, data, ccd, mol_dir, boltz2) 

{boltz_vsynthes-1.0.15 → boltz_vsynthes-1.0.16/src/boltz_vsynthes.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.15
+Version: 1.0.16
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

boltz_vsynthes-1.0.15/src/boltz/data/parse/pdb.py

@@ -1,71 +0,0 @@
-from pathlib import Path
-from typing import Optional
-
-from Bio import PDB
-from Bio.Data.IUPACData import protein_letters_3to1
-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
-
-
-def parse_pdb(
-    path: Path,
-    ccd: dict[str, Mol],
-    mol_dir: Path,
-    boltz2: bool = False,
-) -> Target:
-    """Parse a PDB file.
-
-    Parameters
-    ----------
-    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.
-
-    Returns
-    -------
-    Target
-        The parsed target.
-    """
-    # Read PDB file
-    parser = PDB.PDBParser(QUIET=True)
-    structure = parser.get_structure("protein", str(path))
-
-    # 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)
-
-    data = {
-        "sequences": sequences,
-        "bonds": [],
-        "version": 1,
-    }
-
-    name = path.stem
-    return parse_boltz_schema(name, data, ccd, mol_dir, boltz2) 

boltz_vsynthes-1.0.15/src/boltz/data/parse/sdf.py

@@ -1,60 +0,0 @@
-from pathlib import Path
-from typing import Optional
-
-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
-
-
-def parse_sdf(
-    path: Path,
-    ccd: dict[str, Mol],
-    mol_dir: Path,
-    boltz2: bool = False,
-) -> Target:
-    """Parse an SDF file.
-
-    Parameters
-    ----------
-    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.
-
-    Returns
-    -------
-    Target
-        The parsed target.
-    """
-    # Read SDF file
-    supplier = Chem.SDMolSupplier(str(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)
-
-    data = {
-        "sequences": sequences,
-        "bonds": [],
-        "version": 1,
-    }
-
-    name = path.stem
-    return parse_boltz_schema(name, data, ccd, mol_dir, boltz2)