Protein Binder Design

Protein binder design workflow - generate protein binders.

BinderScores dataclass

BinderScores(
    iptm: float | None = None,
    design_ptm: float | None = None,
    quality_score: float | None = None,
    bb_rmsd: float | None = None,
    loop: float | None = None,
    helix: float | None = None,
    sheet: float | None = None,
    liability_score: float | None = None,
    liability_num_violations: int | None = None,
    liability_high_severity_violations: int | None = None,
    min_interaction_pae: float | None = None,
    delta_sasa_refolded: float | None = None,
    plip_hbonds_refolded: int | None = None,
    plip_saltbridge_refolded: int | None = None,
    num_tokens: int | None = None,
    design_hydrophobicity: float | None = None,
    num_filters_passed: int | None = None,
)

Scores for a generated protein binder design.

Parameters:

Name	Type	Description	Default
iptm	float | None	Interface predicted TM-score (0-1, higher is better).	None
design_ptm	float | None	Predicted TM-score for the designed binder (0-1).	None
quality_score	float | None	Overall quality score (0-1, higher is better).	None
bb_rmsd	float | None	Backbone RMSD compared to initial structure (Angstrom).	None
loop	float | None	Fraction of residues in loop conformation.	None
helix	float | None	Fraction of residues in helix conformation.	None
sheet	float | None	Fraction of residues in sheet conformation.	None
liability_score	float | None	Liability score (lower is better).	None
liability_num_violations	int | None	Number of liability violations.	None
liability_high_severity_violations	int | None	Number of high-severity liability violations.	None
min_interaction_pae	float | None	Minimum predicted aligned error at the interface.	None
delta_sasa_refolded	float | None	Change in solvent-accessible surface area upon binding (A^2).	None
plip_hbonds_refolded	int | None	Number of hydrogen bonds at the interface.	None
plip_saltbridge_refolded	int | None	Number of salt bridges at the interface.	None
num_tokens	int | None	Number of tokens in the design.	None
design_hydrophobicity	float | None	Hydrophobicity of the designed binder.	None
num_filters_passed	int | None	Number of quality filters passed.	None

ProteinBinder dataclass

ProteinBinder(
    bound_structure_uuid: str | None = None,
    sequence: str | None = None,
    scores: BinderScores | None = None,
)

Generated protein binder design.

Parameters:

Name	Type	Description	Default
bound_structure_uuid	str | None	UUID of the bound structure (binder + target complex).	None
sequence	str | None	Amino acid sequence of the designed binder.	None
scores	BinderScores | None	Detailed scores for the binder design.	None

iptm property

iptm: float | None

Interface predicted TM-score (0-1, higher is better).

quality_score property

quality_score: float | None

Overall quality score (0-1, higher is better).

ProteinBinderDesignResult dataclass

ProteinBinderDesignResult(
    workflow_data: dict[str, Any],
    workflow_type: str,
    workflow_uuid: str,
    complete: bool = True,
)

Bases: WorkflowResult

Result from a protein-binder-design workflow.

generated_binders property

generated_binders: list[ProteinBinder]

Generated protein binder designs, sorted by quality score.

messages property

messages: list[Message]

Any messages or warnings from the workflow.

submit_protein_binder_design_workflow

submit_protein_binder_design_workflow(
    binder_design_input: dict[str, Any],
    protocol: BinderProtocol
    | str = BinderProtocol.PROTEIN_ANYTHING,
    num_designs: int = 10,
    budget: int = 2,
    name: str = "Protein Binder Design Workflow",
    folder_uuid: str | None = None,
    folder: Folder | None = None,
    max_credits: int | None = None,
    webhook_url: str | None = None,
    is_draft: bool = False,
) -> Workflow

Submits a protein-binder-design workflow to the API.

Parameters:

Name	Type	Description	Default
binder_design_input	dict[str, Any]	Input specification for the binder design (BoltzGenInput format).	required
protocol	BinderProtocol | str	Design protocol to use. Options: - PROTEIN_ANYTHING: Design a protein binder - PEPTIDE_ANYTHING: Design a peptide binder - PROTEIN_SMALL_MOLECULE: Design a protein that binds a small molecule - NANOBODY_ANYTHING: Design a nanobody binder	PROTEIN_ANYTHING
num_designs	int	Number of designs to generate.	10
budget	int	Number of designs to return in the final diversity-optimized set.	2
name	str	Name of the workflow.	'Protein Binder Design Workflow'
folder_uuid	str | None	UUID of the folder to place the workflow in.	None
folder	Folder | None	Folder object to store the workflow in.	None
max_credits	int | None	Maximum number of credits to use for the workflow.	None
webhook_url	str | None	URL that Rowan will POST to when the workflow completes.	None
is_draft	bool	If True, submit the workflow as a draft without starting execution.	False

Returns:

Type	Description
Workflow	Workflow object representing the submitted workflow.

Raises:

Type	Description
ValueError	If protocol is not a valid BinderProtocol, or if no protein_entities sequence contains a designable region.
requests.HTTPError	if the request to the API fails.