boltz-vsynthes 1.0.41__tar.gz → 1.0.43__tar.gz

{boltz_vsynthes-1.0.41/src/boltz_vsynthes.egg-info → boltz_vsynthes-1.0.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.41
+Version: 1.0.43
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.41 → boltz_vsynthes-1.0.43}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "boltz-vsynthes"
-version = "1.0.41"
+version = "1.0.43"
 requires-python = ">=3.10,<3.13"
 description = "Boltz for VSYNTHES"
 readme = "README.md"
@@ -39,6 +39,8 @@ dependencies = [
 
 [project.scripts]
 boltz = "boltz.main:cli"
+boltz-split-sdf = "boltz.utils.sdf_splitter:main"
+boltz-generate-yaml = "boltz.utils.yaml_generator:main"
 
 [project.optional-dependencies]
 lint = ["ruff"]

boltz_vsynthes-1.0.43/src/boltz/utils/sdf_splitter.py

@@ -0,0 +1,63 @@
+from pathlib import Path
+from typing import Optional
+from rdkit import Chem
+
+def split_sdf_to_individuals(
+    input_sdf: Path,
+    output_dir: Path,
+    prefix: str = "ligand_",
+    start_index: int = 1,
+) -> None:
+    """Split a large SDF file into individual SDF files, one molecule per file.
+    
+    Parameters
+    ----------
+    input_sdf : Path
+        Path to the input SDF file.
+    output_dir : Path
+        Path to the output directory where individual files will be saved.
+    prefix : str, optional
+        Prefix for output filenames, by default "ligand_".
+    start_index : int, optional
+        Starting index for output filenames, by default 1.
+    """
+    # Create output directory if it doesn't exist
+    output_dir.mkdir(parents=True, exist_ok=True)
+    
+    # Read all molecules from input SDF
+    supplier = Chem.SDMolSupplier(str(input_sdf))
+    molecules = [mol for mol in supplier if mol is not None]
+    total_molecules = len(molecules)
+    
+    # Write each molecule to a separate file
+    for i, mol in enumerate(molecules):
+        # Create output filename
+        output_file = output_dir / f"{prefix}{start_index + i}.sdf"
+        
+        # Write molecule to file
+        writer = Chem.SDWriter(str(output_file))
+        writer.write(mol)
+        writer.close()
+        
+        print(f"Created {output_file}")
+
+def main():
+    import argparse
+    
+    parser = argparse.ArgumentParser(description="Split a large SDF file into individual files")
+    parser.add_argument("input_sdf", type=str, help="Path to input SDF file")
+    parser.add_argument("output_dir", type=str, help="Path to output directory")
+    parser.add_argument("--prefix", type=str, default="ligand_", help="Prefix for output filenames")
+    parser.add_argument("--start-index", type=int, default=1, help="Starting index for output filenames")
+    
+    args = parser.parse_args()
+    
+    split_sdf_to_individuals(
+        input_sdf=Path(args.input_sdf),
+        output_dir=Path(args.output_dir),
+        prefix=args.prefix,
+        start_index=args.start_index,
+    )
+
+if __name__ == "__main__":
+    main() 

boltz_vsynthes-1.0.43/src/boltz/utils/yaml_generator.py

@@ -0,0 +1,120 @@
+from pathlib import Path
+import yaml
+from typing import Optional, Dict, Any
+import string
+
+def get_next_ligand_id(config: Dict[str, Any]) -> str:
+    """Get the next available ligand ID based on existing IDs in the config.
+    
+    Parameters
+    ----------
+    config : Dict[str, Any]
+        The configuration dictionary.
+        
+    Returns
+    -------
+    str
+        The next available ligand ID.
+    """
+    # Get all existing IDs
+    existing_ids = set()
+    for item in config["sequences"]:
+        for key in item:
+            if "id" in item[key]:
+                existing_ids.add(item[key]["id"])
+    
+    # Find the first available letter
+    for letter in string.ascii_uppercase:
+        if letter not in existing_ids:
+            return letter
+    
+    # If we run out of single letters, use AA, AB, etc.
+    for first in string.ascii_uppercase:
+        for second in string.ascii_uppercase:
+            new_id = first + second
+            if new_id not in existing_ids:
+                return new_id
+    
+    raise ValueError("Ran out of available ligand IDs!")
+
+def generate_yamls_from_sdfs(
+    template_yaml: Path,
+    sdf_dir: Path,
+    output_dir: Path,
+    yaml_prefix: str = "config_",
+    start_index: int = 1,
+) -> None:
+    """Generate YAML files from a template and a folder of SDF files.
+    
+    Parameters
+    ----------
+    template_yaml : Path
+        Path to the template YAML file.
+    sdf_dir : Path
+        Path to the directory containing SDF files.
+    output_dir : Path
+        Path to the output directory where YAML files will be saved.
+    yaml_prefix : str, optional
+        Prefix for output YAML filenames, by default "config_".
+    start_index : int, optional
+        Starting index for output filenames, by default 1.
+    """
+    # Create output directory if it doesn't exist
+    output_dir.mkdir(parents=True, exist_ok=True)
+    
+    # Load template YAML
+    with open(template_yaml) as f:
+        template = yaml.safe_load(f)
+    
+    # Get all SDF files
+    sdf_files = sorted(sdf_dir.glob("*.sdf"))
+    
+    # Generate YAML for each SDF
+    for i, sdf_file in enumerate(sdf_files):
+        # Create a copy of the template
+        config = template.copy()
+        
+        # Get next available ligand ID
+        ligand_id = get_next_ligand_id(config)
+        
+        # Update ligand information
+        for item in config["sequences"]:
+            if "ligand" in item:
+                item["ligand"]["id"] = ligand_id
+                item["ligand"]["sdf"] = str(sdf_file)
+        
+        # Update affinity information if present
+        if "properties" in config:
+            for prop in config["properties"]:
+                if "affinity" in prop:
+                    prop["affinity"]["binder"] = ligand_id
+        
+        # Write YAML file
+        output_file = output_dir / f"{yaml_prefix}{start_index + i}.yaml"
+        with open(output_file, "w") as f:
+            yaml.dump(config, f, default_flow_style=False)
+        
+        print(f"Created {output_file} with ligand ID {ligand_id}")
+
+def main():
+    import argparse
+    
+    parser = argparse.ArgumentParser(description="Generate YAML files from a template and SDF files")
+    parser.add_argument("template_yaml", type=str, help="Path to template YAML file")
+    parser.add_argument("sdf_dir", type=str, help="Path to directory containing SDF files")
+    parser.add_argument("output_dir", type=str, help="Path to output directory")
+    parser.add_argument("--yaml-prefix", type=str, default="config_", help="Prefix for output YAML filenames")
+    parser.add_argument("--start-index", type=int, default=1, help="Starting index for output filenames")
+    
+    args = parser.parse_args()
+    
+    generate_yamls_from_sdfs(
+        template_yaml=Path(args.template_yaml),
+        sdf_dir=Path(args.sdf_dir),
+        output_dir=Path(args.output_dir),
+        yaml_prefix=args.yaml_prefix,
+        start_index=args.start_index,
+    )
+
+if __name__ == "__main__":
+    main() 

{boltz_vsynthes-1.0.41 → boltz_vsynthes-1.0.43/src/boltz_vsynthes.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 1.0.41
+Version: 1.0.43
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-1.0.41 → boltz_vsynthes-1.0.43}/src/boltz_vsynthes.egg-info/SOURCES.txt

@@ -110,6 +110,8 @@ src/boltz/model/optim/scheduler.py
 src/boltz/model/potentials/__init__.py
 src/boltz/model/potentials/potentials.py
 src/boltz/model/potentials/schedules.py
+src/boltz/utils/sdf_splitter.py
+src/boltz/utils/yaml_generator.py
 src/boltz_vsynthes.egg-info/PKG-INFO
 src/boltz_vsynthes.egg-info/SOURCES.txt
 src/boltz_vsynthes.egg-info/dependency_links.txt

boltz_vsynthes-1.0.43/src/boltz_vsynthes.egg-info/entry_points.txt

@@ -0,0 +1,4 @@
+[console_scripts]
+boltz = boltz.main:cli
+boltz-generate-yaml = boltz.utils.yaml_generator:main
+boltz-split-sdf = boltz.utils.sdf_splitter:main

boltz_vsynthes-1.0.41/src/boltz_vsynthes.egg-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-boltz = boltz.main:cli