# Design ## Start `small_molecule.design.start(DesignStartParams**kwargs) -> DesignStartResponse` **post** `/compute/v1/small-molecule/design` Create a new design run that generates novel small molecule candidates for a protein target ### Parameters - `num_molecules: int` Number of molecules to generate. Must be between 10 and 1,000,000. - `target: Target` Target protein with binding pocket for small molecule design or screening - `entities: Iterable[TargetEntity]` Protein entities defining the target structure. Each entity represents a protein chain. - `chain_ids: SequenceNotStr[str]` Chain IDs for this entity - `type: Literal["protein"]` - `"protein"` - `value: str` Amino acid sequence (one-letter codes) - `cyclic: Optional[bool]` Whether the sequence is cyclic - `modifications: Optional[Iterable[TargetEntityModification]]` Post-translational modifications. Optional; defaults to an empty list when omitted. - `class TargetEntityModificationCcdModification: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["ccd"]` - `"ccd"` - `value: str` CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine) - `class TargetEntityModificationSmilesModification: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["smiles"]` - `"smiles"` - `value: str` SMILES string for the modification - `bonds: Optional[Iterable[TargetBond]]` Covalent bond constraints between atoms in the target complex. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `atom1: TargetBondAtom1` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetBondAtom1LigandAtom: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class TargetBondAtom1PolymerAtom: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `atom2: TargetBondAtom2` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetBondAtom2LigandAtom: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class TargetBondAtom2PolymerAtom: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `constraints: Optional[Iterable[TargetConstraint]]` Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `class TargetConstraintPocketConstraint: …` Constrains the binder to interact with specific pocket residues on the target. - `binder_chain_id: str` Chain ID of the binder molecule - `contact_residues: Dict[str, Iterable[int]]` Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain. - `max_distance_angstrom: float` Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A. - `type: Literal["pocket"]` - `"pocket"` - `force: Optional[bool]` Whether to force the constraint - `class TargetConstraintContactConstraint: …` Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `max_distance_angstrom: float` Maximum distance in Angstroms - `token1: TargetConstraintContactConstraintToken1` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetConstraintContactConstraintToken1PolymerContactToken: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class TargetConstraintContactConstraintToken1LigandContactToken: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `token2: TargetConstraintContactConstraintToken2` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetConstraintContactConstraintToken2PolymerContactToken: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class TargetConstraintContactConstraintToken2LigandContactToken: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `type: Literal["contact"]` - `"contact"` - `force: Optional[bool]` Whether to force the constraint - `pocket_residues: Optional[Dict[str, Iterable[int]]]` Binding pocket residues, keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the binding pocket on that chain. When provided, these residues guide pocket extraction and add a derived pocket constraint during affinity predictions. That derived constraint remains separate from any explicit pocket constraints in target.constraints. When omitted, the model auto-detects the pocket. - `reference_ligands: Optional[SequenceNotStr[str]]` Reference ligands as SMILES strings that help the model identify the binding pocket. When omitted, a set of drug-like default ligands is used for pocket detection. - `chemical_space: Optional[Literal["enamine_real"]]` Chemical space to constrain generated molecules. Currently only 'enamine_real' (Enamine REAL chemical space) is supported. Additional options may be added in the future. - `"enamine_real"` - `idempotency_key: Optional[str]` Client-provided key to prevent duplicate submissions on retries - `molecule_filters: Optional[MoleculeFilters]` Molecule filtering configuration. Controls both Boltz built-in SMARTS filtering and custom filters. - `boltz_smarts_catalog_filter_level: Optional[Literal["recommended", "extra", "aggressive", "disabled"]]` Controls the stringency of Boltz's built-in SMARTS structural alert filtering, which removes molecules matching known problematic substructures. 'recommended' (default): applies a curated set of alerts balancing safety and hit rate. 'extra': adds additional alerts beyond the recommended set for stricter filtering. 'aggressive': applies the most comprehensive alert set — may reject viable molecules. 'disabled': turns off Boltz SMARTS filtering entirely; only custom_filters will be applied. - `"recommended"` - `"extra"` - `"aggressive"` - `"disabled"` - `custom_filters: Optional[Iterable[MoleculeFiltersCustomFilter]]` Custom filters to apply. Molecules must pass all filters (AND logic). - `class MoleculeFiltersCustomFilterLipinskiFilter: …` Lipinski's Rule of Five filter. Rejects molecules that violate drug-likeness criteria based on molecular weight, LogP, hydrogen bond donors, and hydrogen bond acceptors. - `max_hba: float` Maximum number of hydrogen bond acceptors. Lipinski threshold: 10 - `max_hbd: float` Maximum number of hydrogen bond donors. Lipinski threshold: 5 - `max_logp: float` Maximum LogP. Lipinski threshold: 5 - `max_mw: float` Maximum molecular weight (Da). Lipinski threshold: 500 - `type: Literal["lipinski_filter"]` - `"lipinski_filter"` - `allow_single_violation: Optional[bool]` If true, one rule violation is allowed (classic Rule of Five). Defaults to false (all rules must pass). - `class MoleculeFiltersCustomFilterRdkitDescriptorFilter: …` Filter molecules by RDKit molecular descriptors. Each descriptor is constrained to a min/max range. Only descriptors you provide are checked — omitted descriptors are unconstrained. - `type: Literal["rdkit_descriptor_filter"]` - `"rdkit_descriptor_filter"` - `fraction_csp3: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterFractionCsp3]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_logp: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterMolLogp]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_wt: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterMolWt]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_aromatic_rings: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumAromaticRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_acceptors: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHAcceptors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_donors: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHDonors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_heteroatoms: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHeteroatoms]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rings: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rotatable_bonds: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumRotatableBonds]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `tpsa: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterTpsa]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `class MoleculeFiltersCustomFilterSmartsCustomFilter: …` Filter molecules by custom SMARTS patterns. Molecules matching any pattern are rejected. - `patterns: SequenceNotStr[str]` SMARTS patterns. Molecules matching any pattern are rejected. - `type: Literal["smarts_custom_filter"]` - `"smarts_custom_filter"` - `class MoleculeFiltersCustomFilterSmartsCatalogFilter: …` Filter molecules using a predefined SMARTS catalog of structural alerts. - `catalog: Literal["PAINS", "PAINS_A", "PAINS_B", 11 more]` Predefined SMARTS catalog to apply. PAINS, BRENK, ChEMBL, and NIH catalogs reject known problematic substructures. - `"PAINS"` - `"PAINS_A"` - `"PAINS_B"` - `"PAINS_C"` - `"BRENK"` - `"CHEMBL"` - `"CHEMBL_BMS"` - `"CHEMBL_Dundee"` - `"CHEMBL_Glaxo"` - `"CHEMBL_Inpharmatica"` - `"CHEMBL_LINT"` - `"CHEMBL_MLSMR"` - `"CHEMBL_SureChEMBL"` - `"NIH"` - `type: Literal["smarts_catalog_filter"]` - `"smarts_catalog_filter"` - `class MoleculeFiltersCustomFilterSmilesRegexFilter: …` Filter molecules by regex patterns on their SMILES representation. - `patterns: SequenceNotStr[str]` Regex patterns applied to SMILES strings. Molecules matching any pattern are rejected. - `type: Literal["smiles_regex_filter"]` - `"smiles_regex_filter"` - `workspace_id: Optional[str]` Target workspace ID (admin keys only; ignored for workspace keys) ### Returns - `class DesignStartResponse: …` A small molecule design engine run that generates novel molecules - `id: str` Unique SmDesignRun identifier - `completed_at: Optional[datetime]` - `created_at: datetime` - `data_deleted_at: Optional[datetime]` When the input, output, and result data was permanently deleted. Null if data has not been deleted. - `engine: Literal["boltz-sm-design"]` Engine used for small molecule design - `"boltz-sm-design"` - `engine_version: str` Engine version used for small molecule design - `error: Optional[Error]` - `code: str` Machine-readable error code - `message: str` Human-readable error message - `details: Optional[object]` Additional field-level error details keyed by input path, when available. - `input: Optional[Input]` Pipeline input (null if data deleted) - `num_molecules: int` Number of molecules to generate. Must be between 10 and 1,000,000. - `target: InputTarget` Target protein with binding pocket for small molecule design or screening - `entities: List[InputTargetEntity]` Protein entities defining the target structure. Each entity represents a protein chain. - `chain_ids: List[str]` Chain IDs for this entity - `type: Literal["protein"]` - `"protein"` - `value: str` Amino acid sequence (one-letter codes) - `cyclic: Optional[bool]` Whether the sequence is cyclic - `modifications: Optional[List[InputTargetEntityModification]]` Post-translational modifications. Optional; defaults to an empty list when omitted. - `class InputTargetEntityModificationCcdModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["ccd"]` - `"ccd"` - `value: str` CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine) - `class InputTargetEntityModificationSmilesModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["smiles"]` - `"smiles"` - `value: str` SMILES string for the modification - `bonds: Optional[List[InputTargetBond]]` Covalent bond constraints between atoms in the target complex. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `atom1: InputTargetBondAtom1` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom1LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom1PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `atom2: InputTargetBondAtom2` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom2LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom2PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `constraints: Optional[List[InputTargetConstraint]]` Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `class InputTargetConstraintPocketConstraintResponse: …` Constrains the binder to interact with specific pocket residues on the target. - `binder_chain_id: str` Chain ID of the binder molecule - `contact_residues: Dict[str, List[int]]` Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain. - `max_distance_angstrom: float` Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A. - `type: Literal["pocket"]` - `"pocket"` - `force: Optional[bool]` Whether to force the constraint - `class InputTargetConstraintContactConstraintResponse: …` Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `max_distance_angstrom: float` Maximum distance in Angstroms - `token1: InputTargetConstraintContactConstraintResponseToken1` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken1PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken1LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `token2: InputTargetConstraintContactConstraintResponseToken2` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken2PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken2LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `type: Literal["contact"]` - `"contact"` - `force: Optional[bool]` Whether to force the constraint - `pocket_residues: Optional[Dict[str, List[int]]]` Binding pocket residues, keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the binding pocket on that chain. When provided, these residues guide pocket extraction and add a derived pocket constraint during affinity predictions. That derived constraint remains separate from any explicit pocket constraints in target.constraints. When omitted, the model auto-detects the pocket. - `reference_ligands: Optional[List[str]]` Reference ligands as SMILES strings that help the model identify the binding pocket. When omitted, a set of drug-like default ligands is used for pocket detection. - `chemical_space: Optional[Literal["enamine_real"]]` Chemical space to constrain generated molecules. Currently only 'enamine_real' (Enamine REAL chemical space) is supported. Additional options may be added in the future. - `"enamine_real"` - `idempotency_key: Optional[str]` Client-provided key to prevent duplicate submissions on retries - `molecule_filters: Optional[InputMoleculeFilters]` Molecule filtering configuration. Controls both Boltz built-in SMARTS filtering and custom filters. - `boltz_smarts_catalog_filter_level: Optional[Literal["recommended", "extra", "aggressive", "disabled"]]` Controls the stringency of Boltz's built-in SMARTS structural alert filtering, which removes molecules matching known problematic substructures. 'recommended' (default): applies a curated set of alerts balancing safety and hit rate. 'extra': adds additional alerts beyond the recommended set for stricter filtering. 'aggressive': applies the most comprehensive alert set — may reject viable molecules. 'disabled': turns off Boltz SMARTS filtering entirely; only custom_filters will be applied. - `"recommended"` - `"extra"` - `"aggressive"` - `"disabled"` - `custom_filters: Optional[List[InputMoleculeFiltersCustomFilter]]` Custom filters to apply. Molecules must pass all filters (AND logic). - `class InputMoleculeFiltersCustomFilterLipinskiFilterResponse: …` Lipinski's Rule of Five filter. Rejects molecules that violate drug-likeness criteria based on molecular weight, LogP, hydrogen bond donors, and hydrogen bond acceptors. - `max_hba: float` Maximum number of hydrogen bond acceptors. Lipinski threshold: 10 - `max_hbd: float` Maximum number of hydrogen bond donors. Lipinski threshold: 5 - `max_logp: float` Maximum LogP. Lipinski threshold: 5 - `max_mw: float` Maximum molecular weight (Da). Lipinski threshold: 500 - `type: Literal["lipinski_filter"]` - `"lipinski_filter"` - `allow_single_violation: Optional[bool]` If true, one rule violation is allowed (classic Rule of Five). Defaults to false (all rules must pass). - `class InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponse: …` Filter molecules by RDKit molecular descriptors. Each descriptor is constrained to a min/max range. Only descriptors you provide are checked — omitted descriptors are unconstrained. - `type: Literal["rdkit_descriptor_filter"]` - `"rdkit_descriptor_filter"` - `fraction_csp3: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseFractionCsp3]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_logp: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolLogp]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_wt: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolWt]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_aromatic_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumAromaticRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_acceptors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHAcceptors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_donors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHDonors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_heteroatoms: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHeteroatoms]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rotatable_bonds: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRotatableBonds]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `tpsa: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseTpsa]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `class InputMoleculeFiltersCustomFilterSmartsCustomFilterResponse: …` Filter molecules by custom SMARTS patterns. Molecules matching any pattern are rejected. - `patterns: List[str]` SMARTS patterns. Molecules matching any pattern are rejected. - `type: Literal["smarts_custom_filter"]` - `"smarts_custom_filter"` - `class InputMoleculeFiltersCustomFilterSmartsCatalogFilterResponse: …` Filter molecules using a predefined SMARTS catalog of structural alerts. - `catalog: Literal["PAINS", "PAINS_A", "PAINS_B", 11 more]` Predefined SMARTS catalog to apply. PAINS, BRENK, ChEMBL, and NIH catalogs reject known problematic substructures. - `"PAINS"` - `"PAINS_A"` - `"PAINS_B"` - `"PAINS_C"` - `"BRENK"` - `"CHEMBL"` - `"CHEMBL_BMS"` - `"CHEMBL_Dundee"` - `"CHEMBL_Glaxo"` - `"CHEMBL_Inpharmatica"` - `"CHEMBL_LINT"` - `"CHEMBL_MLSMR"` - `"CHEMBL_SureChEMBL"` - `"NIH"` - `type: Literal["smarts_catalog_filter"]` - `"smarts_catalog_filter"` - `class InputMoleculeFiltersCustomFilterSmilesRegexFilterResponse: …` Filter molecules by regex patterns on their SMILES representation. - `patterns: List[str]` Regex patterns applied to SMILES strings. Molecules matching any pattern are rejected. - `type: Literal["smiles_regex_filter"]` - `"smiles_regex_filter"` - `workspace_id: Optional[str]` Target workspace ID (admin keys only; ignored for workspace keys) - `livemode: bool` Whether this resource was created with a live API key. - `progress: Optional[Progress]` - `num_molecules_generated: int` Number of molecules generated so far - `total_molecules_to_generate: int` Total number of molecules requested - `latest_result_id: Optional[str]` ID of the most recently generated result - `started_at: Optional[datetime]` - `status: Literal["pending", "running", "succeeded", 2 more]` - `"pending"` - `"running"` - `"succeeded"` - `"failed"` - `"stopped"` - `stopped_at: Optional[datetime]` - `workspace_id: str` Workspace ID - `idempotency_key: Optional[str]` Client-provided idempotency key ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) response = client.small_molecule.design.start( num_molecules=10, target={ "entities": [{ "chain_ids": ["string"], "type": "protein", "value": "value", }] }, ) print(response.id) ``` ## List `small_molecule.design.list(DesignListParams**kwargs) -> SyncCursorPage[DesignListResponse]` **get** `/compute/v1/small-molecule/design` List small molecule design runs, optionally filtered by workspace ### Parameters - `after_id: Optional[str]` Return results after this ID - `before_id: Optional[str]` Return results before this ID - `limit: Optional[int]` Max items to return. Defaults to 100. - `workspace_id: Optional[str]` Filter by workspace ID. Only used with admin API keys. If not provided, defaults to the workspace associated with the API key, or the default workspace for admin keys. ### Returns - `class DesignListResponse: …` Summary of a small molecule design engine run (excludes input) - `id: str` Unique SmDesignRunSummary identifier - `completed_at: Optional[datetime]` - `created_at: datetime` - `data_deleted_at: Optional[datetime]` When the input, output, and result data was permanently deleted. Null if data has not been deleted. - `engine: Literal["boltz-sm-design"]` Engine used for small molecule design - `"boltz-sm-design"` - `engine_version: str` Engine version used for small molecule design - `error: Optional[Error]` - `code: str` Machine-readable error code - `message: str` Human-readable error message - `details: Optional[object]` Additional field-level error details keyed by input path, when available. - `livemode: bool` Whether this resource was created with a live API key. - `progress: Optional[Progress]` - `num_molecules_generated: int` Number of molecules generated so far - `total_molecules_to_generate: int` Total number of molecules requested - `latest_result_id: Optional[str]` ID of the most recently generated result - `started_at: Optional[datetime]` - `status: Literal["pending", "running", "succeeded", 2 more]` - `"pending"` - `"running"` - `"succeeded"` - `"failed"` - `"stopped"` - `stopped_at: Optional[datetime]` - `workspace_id: str` Workspace ID - `idempotency_key: Optional[str]` Client-provided idempotency key ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) page = client.small_molecule.design.list() page = page.data[0] print(page.id) ``` ## Retrieve `small_molecule.design.retrieve(strid, DesignRetrieveParams**kwargs) -> DesignRetrieveResponse` **get** `/compute/v1/small-molecule/design/{id}` Retrieve a design run by ID, including progress and status ### Parameters - `id: str` - `workspace_id: Optional[str]` Workspace ID. Only used with admin API keys. Ignored (or validated) for workspace-scoped keys. ### Returns - `class DesignRetrieveResponse: …` A small molecule design engine run that generates novel molecules - `id: str` Unique SmDesignRun identifier - `completed_at: Optional[datetime]` - `created_at: datetime` - `data_deleted_at: Optional[datetime]` When the input, output, and result data was permanently deleted. Null if data has not been deleted. - `engine: Literal["boltz-sm-design"]` Engine used for small molecule design - `"boltz-sm-design"` - `engine_version: str` Engine version used for small molecule design - `error: Optional[Error]` - `code: str` Machine-readable error code - `message: str` Human-readable error message - `details: Optional[object]` Additional field-level error details keyed by input path, when available. - `input: Optional[Input]` Pipeline input (null if data deleted) - `num_molecules: int` Number of molecules to generate. Must be between 10 and 1,000,000. - `target: InputTarget` Target protein with binding pocket for small molecule design or screening - `entities: List[InputTargetEntity]` Protein entities defining the target structure. Each entity represents a protein chain. - `chain_ids: List[str]` Chain IDs for this entity - `type: Literal["protein"]` - `"protein"` - `value: str` Amino acid sequence (one-letter codes) - `cyclic: Optional[bool]` Whether the sequence is cyclic - `modifications: Optional[List[InputTargetEntityModification]]` Post-translational modifications. Optional; defaults to an empty list when omitted. - `class InputTargetEntityModificationCcdModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["ccd"]` - `"ccd"` - `value: str` CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine) - `class InputTargetEntityModificationSmilesModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["smiles"]` - `"smiles"` - `value: str` SMILES string for the modification - `bonds: Optional[List[InputTargetBond]]` Covalent bond constraints between atoms in the target complex. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `atom1: InputTargetBondAtom1` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom1LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom1PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `atom2: InputTargetBondAtom2` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom2LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom2PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `constraints: Optional[List[InputTargetConstraint]]` Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `class InputTargetConstraintPocketConstraintResponse: …` Constrains the binder to interact with specific pocket residues on the target. - `binder_chain_id: str` Chain ID of the binder molecule - `contact_residues: Dict[str, List[int]]` Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain. - `max_distance_angstrom: float` Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A. - `type: Literal["pocket"]` - `"pocket"` - `force: Optional[bool]` Whether to force the constraint - `class InputTargetConstraintContactConstraintResponse: …` Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `max_distance_angstrom: float` Maximum distance in Angstroms - `token1: InputTargetConstraintContactConstraintResponseToken1` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken1PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken1LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `token2: InputTargetConstraintContactConstraintResponseToken2` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken2PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken2LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `type: Literal["contact"]` - `"contact"` - `force: Optional[bool]` Whether to force the constraint - `pocket_residues: Optional[Dict[str, List[int]]]` Binding pocket residues, keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the binding pocket on that chain. When provided, these residues guide pocket extraction and add a derived pocket constraint during affinity predictions. That derived constraint remains separate from any explicit pocket constraints in target.constraints. When omitted, the model auto-detects the pocket. - `reference_ligands: Optional[List[str]]` Reference ligands as SMILES strings that help the model identify the binding pocket. When omitted, a set of drug-like default ligands is used for pocket detection. - `chemical_space: Optional[Literal["enamine_real"]]` Chemical space to constrain generated molecules. Currently only 'enamine_real' (Enamine REAL chemical space) is supported. Additional options may be added in the future. - `"enamine_real"` - `idempotency_key: Optional[str]` Client-provided key to prevent duplicate submissions on retries - `molecule_filters: Optional[InputMoleculeFilters]` Molecule filtering configuration. Controls both Boltz built-in SMARTS filtering and custom filters. - `boltz_smarts_catalog_filter_level: Optional[Literal["recommended", "extra", "aggressive", "disabled"]]` Controls the stringency of Boltz's built-in SMARTS structural alert filtering, which removes molecules matching known problematic substructures. 'recommended' (default): applies a curated set of alerts balancing safety and hit rate. 'extra': adds additional alerts beyond the recommended set for stricter filtering. 'aggressive': applies the most comprehensive alert set — may reject viable molecules. 'disabled': turns off Boltz SMARTS filtering entirely; only custom_filters will be applied. - `"recommended"` - `"extra"` - `"aggressive"` - `"disabled"` - `custom_filters: Optional[List[InputMoleculeFiltersCustomFilter]]` Custom filters to apply. Molecules must pass all filters (AND logic). - `class InputMoleculeFiltersCustomFilterLipinskiFilterResponse: …` Lipinski's Rule of Five filter. Rejects molecules that violate drug-likeness criteria based on molecular weight, LogP, hydrogen bond donors, and hydrogen bond acceptors. - `max_hba: float` Maximum number of hydrogen bond acceptors. Lipinski threshold: 10 - `max_hbd: float` Maximum number of hydrogen bond donors. Lipinski threshold: 5 - `max_logp: float` Maximum LogP. Lipinski threshold: 5 - `max_mw: float` Maximum molecular weight (Da). Lipinski threshold: 500 - `type: Literal["lipinski_filter"]` - `"lipinski_filter"` - `allow_single_violation: Optional[bool]` If true, one rule violation is allowed (classic Rule of Five). Defaults to false (all rules must pass). - `class InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponse: …` Filter molecules by RDKit molecular descriptors. Each descriptor is constrained to a min/max range. Only descriptors you provide are checked — omitted descriptors are unconstrained. - `type: Literal["rdkit_descriptor_filter"]` - `"rdkit_descriptor_filter"` - `fraction_csp3: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseFractionCsp3]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_logp: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolLogp]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_wt: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolWt]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_aromatic_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumAromaticRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_acceptors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHAcceptors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_donors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHDonors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_heteroatoms: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHeteroatoms]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rotatable_bonds: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRotatableBonds]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `tpsa: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseTpsa]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `class InputMoleculeFiltersCustomFilterSmartsCustomFilterResponse: …` Filter molecules by custom SMARTS patterns. Molecules matching any pattern are rejected. - `patterns: List[str]` SMARTS patterns. Molecules matching any pattern are rejected. - `type: Literal["smarts_custom_filter"]` - `"smarts_custom_filter"` - `class InputMoleculeFiltersCustomFilterSmartsCatalogFilterResponse: …` Filter molecules using a predefined SMARTS catalog of structural alerts. - `catalog: Literal["PAINS", "PAINS_A", "PAINS_B", 11 more]` Predefined SMARTS catalog to apply. PAINS, BRENK, ChEMBL, and NIH catalogs reject known problematic substructures. - `"PAINS"` - `"PAINS_A"` - `"PAINS_B"` - `"PAINS_C"` - `"BRENK"` - `"CHEMBL"` - `"CHEMBL_BMS"` - `"CHEMBL_Dundee"` - `"CHEMBL_Glaxo"` - `"CHEMBL_Inpharmatica"` - `"CHEMBL_LINT"` - `"CHEMBL_MLSMR"` - `"CHEMBL_SureChEMBL"` - `"NIH"` - `type: Literal["smarts_catalog_filter"]` - `"smarts_catalog_filter"` - `class InputMoleculeFiltersCustomFilterSmilesRegexFilterResponse: …` Filter molecules by regex patterns on their SMILES representation. - `patterns: List[str]` Regex patterns applied to SMILES strings. Molecules matching any pattern are rejected. - `type: Literal["smiles_regex_filter"]` - `"smiles_regex_filter"` - `workspace_id: Optional[str]` Target workspace ID (admin keys only; ignored for workspace keys) - `livemode: bool` Whether this resource was created with a live API key. - `progress: Optional[Progress]` - `num_molecules_generated: int` Number of molecules generated so far - `total_molecules_to_generate: int` Total number of molecules requested - `latest_result_id: Optional[str]` ID of the most recently generated result - `started_at: Optional[datetime]` - `status: Literal["pending", "running", "succeeded", 2 more]` - `"pending"` - `"running"` - `"succeeded"` - `"failed"` - `"stopped"` - `stopped_at: Optional[datetime]` - `workspace_id: str` Workspace ID - `idempotency_key: Optional[str]` Client-provided idempotency key ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) design = client.small_molecule.design.retrieve( id="id", ) print(design.id) ``` ## List Results `small_molecule.design.list_results(strid, DesignListResultsParams**kwargs) -> SyncCursorPage[DesignListResultsResponse]` **get** `/compute/v1/small-molecule/design/{id}/results` Retrieve paginated results from a design run ### Parameters - `id: str` - `after_id: Optional[str]` Return results after this ID - `before_id: Optional[str]` Return results before this ID - `limit: Optional[int]` Max results to return. Defaults to 100. - `workspace_id: Optional[str]` Workspace ID. Only used with admin API keys. Ignored (or validated) for workspace-scoped keys. ### Returns - `class DesignListResultsResponse: …` A single designed small molecule result - `id: str` Unique result ID - `artifacts: Artifacts` - `archive: ArtifactsArchive` - `url: str` URL to download the file - `url_expires_at: datetime` When the presigned URL expires - `structure: ArtifactsStructure` - `url: str` URL to download the file - `url_expires_at: datetime` When the presigned URL expires - `created_at: datetime` - `metrics: Metrics` Scoring metrics for a designed small molecule - `binding_confidence: float` Confidence that the molecule binds the target (0-1). Primary metric for hit discovery. - `complex_iplddt: float` Interface pLDDT for the complex (0-1 float). Confidence at the binding interface. - `complex_plddt: float` pLDDT for the full complex (0-1 float). - `iptm: float` Interface predicted TM score (0-1). Confidence in relative positioning of ligand and protein. - `optimization_score: float` Binding strength ranking score for lead optimization. Higher values indicate stronger predicted binding. - `ptm: float` Predicted TM score (0-1). Global structure quality metric. - `structure_confidence: float` Confidence in the predicted 3D structure (0-1). - `smiles: str` SMILES string of the designed molecule - `warnings: Optional[List[Warning]]` Warnings about potential quality issues with this result. - `code: str` Machine-readable warning code (e.g. "low_confidence", "unusual_geometry") - `message: str` Human-readable description of the warning ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) page = client.small_molecule.design.list_results( id="id", ) page = page.data[0] print(page.id) ``` ## Stop `small_molecule.design.stop(strid) -> DesignStopResponse` **post** `/compute/v1/small-molecule/design/{id}/stop` Stop an in-progress design run early ### Parameters - `id: str` ### Returns - `class DesignStopResponse: …` A small molecule design engine run that generates novel molecules - `id: str` Unique SmDesignRun identifier - `completed_at: Optional[datetime]` - `created_at: datetime` - `data_deleted_at: Optional[datetime]` When the input, output, and result data was permanently deleted. Null if data has not been deleted. - `engine: Literal["boltz-sm-design"]` Engine used for small molecule design - `"boltz-sm-design"` - `engine_version: str` Engine version used for small molecule design - `error: Optional[Error]` - `code: str` Machine-readable error code - `message: str` Human-readable error message - `details: Optional[object]` Additional field-level error details keyed by input path, when available. - `input: Optional[Input]` Pipeline input (null if data deleted) - `num_molecules: int` Number of molecules to generate. Must be between 10 and 1,000,000. - `target: InputTarget` Target protein with binding pocket for small molecule design or screening - `entities: List[InputTargetEntity]` Protein entities defining the target structure. Each entity represents a protein chain. - `chain_ids: List[str]` Chain IDs for this entity - `type: Literal["protein"]` - `"protein"` - `value: str` Amino acid sequence (one-letter codes) - `cyclic: Optional[bool]` Whether the sequence is cyclic - `modifications: Optional[List[InputTargetEntityModification]]` Post-translational modifications. Optional; defaults to an empty list when omitted. - `class InputTargetEntityModificationCcdModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["ccd"]` - `"ccd"` - `value: str` CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine) - `class InputTargetEntityModificationSmilesModificationResponse: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["smiles"]` - `"smiles"` - `value: str` SMILES string for the modification - `bonds: Optional[List[InputTargetBond]]` Covalent bond constraints between atoms in the target complex. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `atom1: InputTargetBondAtom1` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom1LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom1PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `atom2: InputTargetBondAtom2` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetBondAtom2LigandAtomResponse: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class InputTargetBondAtom2PolymerAtomResponse: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `constraints: Optional[List[InputTargetConstraint]]` Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `class InputTargetConstraintPocketConstraintResponse: …` Constrains the binder to interact with specific pocket residues on the target. - `binder_chain_id: str` Chain ID of the binder molecule - `contact_residues: Dict[str, List[int]]` Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain. - `max_distance_angstrom: float` Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A. - `type: Literal["pocket"]` - `"pocket"` - `force: Optional[bool]` Whether to force the constraint - `class InputTargetConstraintContactConstraintResponse: …` Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `max_distance_angstrom: float` Maximum distance in Angstroms - `token1: InputTargetConstraintContactConstraintResponseToken1` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken1PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken1LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `token2: InputTargetConstraintContactConstraintResponseToken2` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class InputTargetConstraintContactConstraintResponseToken2PolymerContactTokenResponse: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class InputTargetConstraintContactConstraintResponseToken2LigandContactTokenResponse: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `type: Literal["contact"]` - `"contact"` - `force: Optional[bool]` Whether to force the constraint - `pocket_residues: Optional[Dict[str, List[int]]]` Binding pocket residues, keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the binding pocket on that chain. When provided, these residues guide pocket extraction and add a derived pocket constraint during affinity predictions. That derived constraint remains separate from any explicit pocket constraints in target.constraints. When omitted, the model auto-detects the pocket. - `reference_ligands: Optional[List[str]]` Reference ligands as SMILES strings that help the model identify the binding pocket. When omitted, a set of drug-like default ligands is used for pocket detection. - `chemical_space: Optional[Literal["enamine_real"]]` Chemical space to constrain generated molecules. Currently only 'enamine_real' (Enamine REAL chemical space) is supported. Additional options may be added in the future. - `"enamine_real"` - `idempotency_key: Optional[str]` Client-provided key to prevent duplicate submissions on retries - `molecule_filters: Optional[InputMoleculeFilters]` Molecule filtering configuration. Controls both Boltz built-in SMARTS filtering and custom filters. - `boltz_smarts_catalog_filter_level: Optional[Literal["recommended", "extra", "aggressive", "disabled"]]` Controls the stringency of Boltz's built-in SMARTS structural alert filtering, which removes molecules matching known problematic substructures. 'recommended' (default): applies a curated set of alerts balancing safety and hit rate. 'extra': adds additional alerts beyond the recommended set for stricter filtering. 'aggressive': applies the most comprehensive alert set — may reject viable molecules. 'disabled': turns off Boltz SMARTS filtering entirely; only custom_filters will be applied. - `"recommended"` - `"extra"` - `"aggressive"` - `"disabled"` - `custom_filters: Optional[List[InputMoleculeFiltersCustomFilter]]` Custom filters to apply. Molecules must pass all filters (AND logic). - `class InputMoleculeFiltersCustomFilterLipinskiFilterResponse: …` Lipinski's Rule of Five filter. Rejects molecules that violate drug-likeness criteria based on molecular weight, LogP, hydrogen bond donors, and hydrogen bond acceptors. - `max_hba: float` Maximum number of hydrogen bond acceptors. Lipinski threshold: 10 - `max_hbd: float` Maximum number of hydrogen bond donors. Lipinski threshold: 5 - `max_logp: float` Maximum LogP. Lipinski threshold: 5 - `max_mw: float` Maximum molecular weight (Da). Lipinski threshold: 500 - `type: Literal["lipinski_filter"]` - `"lipinski_filter"` - `allow_single_violation: Optional[bool]` If true, one rule violation is allowed (classic Rule of Five). Defaults to false (all rules must pass). - `class InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponse: …` Filter molecules by RDKit molecular descriptors. Each descriptor is constrained to a min/max range. Only descriptors you provide are checked — omitted descriptors are unconstrained. - `type: Literal["rdkit_descriptor_filter"]` - `"rdkit_descriptor_filter"` - `fraction_csp3: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseFractionCsp3]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_logp: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolLogp]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_wt: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseMolWt]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_aromatic_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumAromaticRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_acceptors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHAcceptors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_donors: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHDonors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_heteroatoms: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumHeteroatoms]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rings: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rotatable_bonds: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseNumRotatableBonds]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `tpsa: Optional[InputMoleculeFiltersCustomFilterRdkitDescriptorFilterResponseTpsa]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `class InputMoleculeFiltersCustomFilterSmartsCustomFilterResponse: …` Filter molecules by custom SMARTS patterns. Molecules matching any pattern are rejected. - `patterns: List[str]` SMARTS patterns. Molecules matching any pattern are rejected. - `type: Literal["smarts_custom_filter"]` - `"smarts_custom_filter"` - `class InputMoleculeFiltersCustomFilterSmartsCatalogFilterResponse: …` Filter molecules using a predefined SMARTS catalog of structural alerts. - `catalog: Literal["PAINS", "PAINS_A", "PAINS_B", 11 more]` Predefined SMARTS catalog to apply. PAINS, BRENK, ChEMBL, and NIH catalogs reject known problematic substructures. - `"PAINS"` - `"PAINS_A"` - `"PAINS_B"` - `"PAINS_C"` - `"BRENK"` - `"CHEMBL"` - `"CHEMBL_BMS"` - `"CHEMBL_Dundee"` - `"CHEMBL_Glaxo"` - `"CHEMBL_Inpharmatica"` - `"CHEMBL_LINT"` - `"CHEMBL_MLSMR"` - `"CHEMBL_SureChEMBL"` - `"NIH"` - `type: Literal["smarts_catalog_filter"]` - `"smarts_catalog_filter"` - `class InputMoleculeFiltersCustomFilterSmilesRegexFilterResponse: …` Filter molecules by regex patterns on their SMILES representation. - `patterns: List[str]` Regex patterns applied to SMILES strings. Molecules matching any pattern are rejected. - `type: Literal["smiles_regex_filter"]` - `"smiles_regex_filter"` - `workspace_id: Optional[str]` Target workspace ID (admin keys only; ignored for workspace keys) - `livemode: bool` Whether this resource was created with a live API key. - `progress: Optional[Progress]` - `num_molecules_generated: int` Number of molecules generated so far - `total_molecules_to_generate: int` Total number of molecules requested - `latest_result_id: Optional[str]` ID of the most recently generated result - `started_at: Optional[datetime]` - `status: Literal["pending", "running", "succeeded", 2 more]` - `"pending"` - `"running"` - `"succeeded"` - `"failed"` - `"stopped"` - `stopped_at: Optional[datetime]` - `workspace_id: str` Workspace ID - `idempotency_key: Optional[str]` Client-provided idempotency key ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) response = client.small_molecule.design.stop( "id", ) print(response.id) ``` ## Delete Data `small_molecule.design.delete_data(strid) -> DesignDeleteDataResponse` **post** `/compute/v1/small-molecule/design/{id}/delete-data` Permanently delete the input, output, and result data associated with this design run. The design run record itself is retained with a `data_deleted_at` timestamp. This action is irreversible. ### Parameters - `id: str` ### Returns - `class DesignDeleteDataResponse: …` - `id: str` ID of the resource whose data was deleted - `data_deleted: Literal[true]` - `true` - `data_deleted_at: datetime` When the data was deleted ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) response = client.small_molecule.design.delete_data( "id", ) print(response.id) ``` ## Estimate Cost `small_molecule.design.estimate_cost(DesignEstimateCostParams**kwargs) -> DesignEstimateCostResponse` **post** `/compute/v1/small-molecule/design/estimate-cost` Estimate the billed cost of a small molecule design run without creating any resource or consuming GPU. Includes the SynFlowNet generation charges implied by the scheduler iteration cap plus Boltz2 scoring for each requested molecule. ### Parameters - `num_molecules: int` Number of molecules to generate. Must be between 10 and 1,000,000. - `target: Target` Target protein with binding pocket for small molecule design or screening - `entities: Iterable[TargetEntity]` Protein entities defining the target structure. Each entity represents a protein chain. - `chain_ids: SequenceNotStr[str]` Chain IDs for this entity - `type: Literal["protein"]` - `"protein"` - `value: str` Amino acid sequence (one-letter codes) - `cyclic: Optional[bool]` Whether the sequence is cyclic - `modifications: Optional[Iterable[TargetEntityModification]]` Post-translational modifications. Optional; defaults to an empty list when omitted. - `class TargetEntityModificationCcdModification: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["ccd"]` - `"ccd"` - `value: str` CCD code from RCSB PDB (e.g. 'MSE' for selenomethionine, 'SEP' for phosphoserine) - `class TargetEntityModificationSmilesModification: …` - `residue_index: int` 0-based index of the residue to modify - `type: Literal["smiles"]` - `"smiles"` - `value: str` SMILES string for the modification - `bonds: Optional[Iterable[TargetBond]]` Covalent bond constraints between atoms in the target complex. Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `atom1: TargetBondAtom1` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetBondAtom1LigandAtom: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class TargetBondAtom1PolymerAtom: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `atom2: TargetBondAtom2` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetBondAtom2LigandAtom: …` Ligand atom reference. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB). Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID containing the atom - `type: Literal["ligand_atom"]` - `"ligand_atom"` - `class TargetBondAtom2PolymerAtom: …` - `atom_name: str` Standardized atom name (verifiable in CIF file on RCSB) - `chain_id: str` Chain ID containing the atom - `residue_index: int` 0-based residue index - `type: Literal["polymer_atom"]` - `"polymer_atom"` - `constraints: Optional[Iterable[TargetConstraint]]` Structural constraints (pocket and contact). Atom-level ligand references currently support ligand_ccd only; ligand_smiles is unsupported. - `class TargetConstraintPocketConstraint: …` Constrains the binder to interact with specific pocket residues on the target. - `binder_chain_id: str` Chain ID of the binder molecule - `contact_residues: Dict[str, Iterable[int]]` Binding pocket residues keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the pocket on that chain. - `max_distance_angstrom: float` Maximum allowed distance in Angstroms between binder and pocket residues. Typical range: 4-8 A. - `type: Literal["pocket"]` - `"pocket"` - `force: Optional[bool]` Whether to force the constraint - `class TargetConstraintContactConstraint: …` Contact constraint between two tokens. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `max_distance_angstrom: float` Maximum distance in Angstroms - `token1: TargetConstraintContactConstraintToken1` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetConstraintContactConstraintToken1PolymerContactToken: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class TargetConstraintContactConstraintToken1LigandContactToken: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `token2: TargetConstraintContactConstraintToken2` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `class TargetConstraintContactConstraintToken2PolymerContactToken: …` - `chain_id: str` Chain ID - `residue_index: int` 0-based residue index - `type: Literal["polymer_contact"]` - `"polymer_contact"` - `class TargetConstraintContactConstraintToken2LigandContactToken: …` Ligand contact token. Atom-level ligand references currently support ligand_ccd entities only; ligand_smiles is unsupported. - `atom_name: str` Atom name. Atom-level references to ligand_smiles entities are currently unsupported; use ligand_ccd instead. - `chain_id: str` Chain ID - `type: Literal["ligand_contact"]` - `"ligand_contact"` - `type: Literal["contact"]` - `"contact"` - `force: Optional[bool]` Whether to force the constraint - `pocket_residues: Optional[Dict[str, Iterable[int]]]` Binding pocket residues, keyed by chain ID. Each key is a chain ID (e.g. "A") and the value is an array of 0-indexed residue indices that define the binding pocket on that chain. When provided, these residues guide pocket extraction and add a derived pocket constraint during affinity predictions. That derived constraint remains separate from any explicit pocket constraints in target.constraints. When omitted, the model auto-detects the pocket. - `reference_ligands: Optional[SequenceNotStr[str]]` Reference ligands as SMILES strings that help the model identify the binding pocket. When omitted, a set of drug-like default ligands is used for pocket detection. - `chemical_space: Optional[Literal["enamine_real"]]` Chemical space to constrain generated molecules. Currently only 'enamine_real' (Enamine REAL chemical space) is supported. Additional options may be added in the future. - `"enamine_real"` - `idempotency_key: Optional[str]` Client-provided key to prevent duplicate submissions on retries - `molecule_filters: Optional[MoleculeFilters]` Molecule filtering configuration. Controls both Boltz built-in SMARTS filtering and custom filters. - `boltz_smarts_catalog_filter_level: Optional[Literal["recommended", "extra", "aggressive", "disabled"]]` Controls the stringency of Boltz's built-in SMARTS structural alert filtering, which removes molecules matching known problematic substructures. 'recommended' (default): applies a curated set of alerts balancing safety and hit rate. 'extra': adds additional alerts beyond the recommended set for stricter filtering. 'aggressive': applies the most comprehensive alert set — may reject viable molecules. 'disabled': turns off Boltz SMARTS filtering entirely; only custom_filters will be applied. - `"recommended"` - `"extra"` - `"aggressive"` - `"disabled"` - `custom_filters: Optional[Iterable[MoleculeFiltersCustomFilter]]` Custom filters to apply. Molecules must pass all filters (AND logic). - `class MoleculeFiltersCustomFilterLipinskiFilter: …` Lipinski's Rule of Five filter. Rejects molecules that violate drug-likeness criteria based on molecular weight, LogP, hydrogen bond donors, and hydrogen bond acceptors. - `max_hba: float` Maximum number of hydrogen bond acceptors. Lipinski threshold: 10 - `max_hbd: float` Maximum number of hydrogen bond donors. Lipinski threshold: 5 - `max_logp: float` Maximum LogP. Lipinski threshold: 5 - `max_mw: float` Maximum molecular weight (Da). Lipinski threshold: 500 - `type: Literal["lipinski_filter"]` - `"lipinski_filter"` - `allow_single_violation: Optional[bool]` If true, one rule violation is allowed (classic Rule of Five). Defaults to false (all rules must pass). - `class MoleculeFiltersCustomFilterRdkitDescriptorFilter: …` Filter molecules by RDKit molecular descriptors. Each descriptor is constrained to a min/max range. Only descriptors you provide are checked — omitted descriptors are unconstrained. - `type: Literal["rdkit_descriptor_filter"]` - `"rdkit_descriptor_filter"` - `fraction_csp3: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterFractionCsp3]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_logp: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterMolLogp]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `mol_wt: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterMolWt]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_aromatic_rings: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumAromaticRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_acceptors: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHAcceptors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_h_donors: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHDonors]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_heteroatoms: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumHeteroatoms]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rings: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumRings]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `num_rotatable_bonds: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterNumRotatableBonds]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `tpsa: Optional[MoleculeFiltersCustomFilterRdkitDescriptorFilterTpsa]` Min/max range constraint for an RDKit molecular descriptor - `max: Optional[float]` Maximum allowed value (inclusive) - `min: Optional[float]` Minimum allowed value (inclusive) - `class MoleculeFiltersCustomFilterSmartsCustomFilter: …` Filter molecules by custom SMARTS patterns. Molecules matching any pattern are rejected. - `patterns: SequenceNotStr[str]` SMARTS patterns. Molecules matching any pattern are rejected. - `type: Literal["smarts_custom_filter"]` - `"smarts_custom_filter"` - `class MoleculeFiltersCustomFilterSmartsCatalogFilter: …` Filter molecules using a predefined SMARTS catalog of structural alerts. - `catalog: Literal["PAINS", "PAINS_A", "PAINS_B", 11 more]` Predefined SMARTS catalog to apply. PAINS, BRENK, ChEMBL, and NIH catalogs reject known problematic substructures. - `"PAINS"` - `"PAINS_A"` - `"PAINS_B"` - `"PAINS_C"` - `"BRENK"` - `"CHEMBL"` - `"CHEMBL_BMS"` - `"CHEMBL_Dundee"` - `"CHEMBL_Glaxo"` - `"CHEMBL_Inpharmatica"` - `"CHEMBL_LINT"` - `"CHEMBL_MLSMR"` - `"CHEMBL_SureChEMBL"` - `"NIH"` - `type: Literal["smarts_catalog_filter"]` - `"smarts_catalog_filter"` - `class MoleculeFiltersCustomFilterSmilesRegexFilter: …` Filter molecules by regex patterns on their SMILES representation. - `patterns: SequenceNotStr[str]` Regex patterns applied to SMILES strings. Molecules matching any pattern are rejected. - `type: Literal["smiles_regex_filter"]` - `"smiles_regex_filter"` - `workspace_id: Optional[str]` Target workspace ID (admin keys only; ignored for workspace keys) ### Returns - `class DesignEstimateCostResponse: …` Estimate response with monetary values encoded as decimal strings to preserve precision. - `breakdown: Breakdown` Cost breakdown for the billed application. - `application: Literal["structure_and_binding", "small_molecule_design", "small_molecule_library_screen", 3 more]` - `"structure_and_binding"` - `"small_molecule_design"` - `"small_molecule_library_screen"` - `"protein_design"` - `"protein_library_screen"` - `"adme"` - `cost_per_unit_usd: str` Estimated cost per displayed unit as a decimal string, rounded up to 4 decimal places. This may include token-size multipliers or generation overhead; estimated_cost_usd is the authoritative total. - `num_units: int` Number of units shown for the estimate. For structure-and-binding, this is the requested number of samples. For protein and small-molecule design/screen endpoints, this is the requested number of proteins or molecules. - `disclaimer: str` - `estimated_cost_usd: str` Estimated total cost as a decimal string ### Example ```python import os from boltz_api import Boltz client = Boltz( api_key=os.environ.get("BOLTZ_API_KEY"), # This is the default and can be omitted ) response = client.small_molecule.design.estimate_cost( num_molecules=10, target={ "entities": [{ "chain_ids": ["string"], "type": "protein", "value": "value", }] }, ) print(response.breakdown) ```