starling.inference.constraints.RgConstraint

class RgConstraint

Bases: Constraint

Methods

__init__	Create constraint for radius of gyration (Rg).
apply	Apply the constraint to the given latents.
bell_shaped_schedule	Bell-shaped schedule for time-dependent guidance strength.
compute_loss	Compute loss based on deviation from target Rg.
cosine_weight	Cosine schedule for time-dependent guidance strength.
get_adaptive_clip_threshold	Get an adaptive clipping threshold that follows a cosine schedule.
get_time_scale	Get the time-dependent scaling factor.
initialize	Called by the sampler to set model parameters.
should_apply_guidance	Check if guidance should be applied at the current timestep.

__init__(target, tolerance=0.0, force_constant=2.0, **kwargs)

Create constraint for radius of gyration (Rg).

Parameters:

• target (float) – Target Rg value in Angstroms

• tolerance (float, default=0.0) – Allowed deviation from target before penalty applies

• force_constant (float, default=2.0) – Force constant for the harmonic potential

• **kwargs – Additional parameters passed to parent Constraint class

compute_loss(distance_maps: Tensor) → Tuple[Tensor, Tensor]

Compute loss based on deviation from target Rg.

Parameters:

distance_maps (torch.Tensor) – Pre-computed distance maps from the latents

Returns:

Per-batch loss and mean loss

Return type:

Tuple[torch.Tensor, torch.Tensor]