Article

To Predict is to Design: Unlocking Generative Capabilities in All-Atom Structure Predictors via Geometric Score Distillation

2025-12-26

Abstract excerpt

Current protein binder design largely relies on a decoupled paradigm: generating backbones via unconditioned diffusion followed by sequence filling or refilling with inverse folding models. This separation prevents the design process from accessing the holistic validation metrics of structure predictors during generation, wasting rich physical priors. While recent works like BindCraft have successfully inverted Al...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ff45bfc1-97b5-5a40-ad0e-3509166dea87
DOI: 10.64898/2025.12.23.696242

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

To Predict is to Design: Unlocking Generative Capabilities in All-Atom Structure Predictors via Geometric Score DistillationDOI 10.64898/2025.12.23.696242Read

Generative AI for Drug Discovery and Protein Design: The Next Frontier in AI-Driven Molecular ScienceSemantic proximity Read

ProChoreo: <i>de novo</i> Binder Design from Conformational Ensembles with Generative Deep LearningSemantic proximity Read

Modeling the structure-conditioned sequence landscape for large-scale protein design with TriFlowSemantic proximity Read

Generative Drug Design in a Loop with dtSFMSemantic proximity Read

De novo design of high-affinity protein binders to bioactive helical peptidesSemantic proximity Read

Programming Biomolecular Interactions with All-Atom Generative ModelSemantic proximity Read

RareFold: Structure Prediction and Design of Proteins with Noncanonical Amino AcidsSemantic proximity Read

DrugHIVE: Target-specific spatial drug design and optimization with a hierarchical generative modelSemantic proximity Read

Aiki-GeNano: Multi-Stage Preference Optimization for Generative Design of Developable NanobodiesSemantic proximity Read

Automated and modular protein binder design with BinderFlowSemantic proximity Read

Illuminating protein space with a programmable generative modelSemantic proximity Read

Advancing Ligand Binding Affinity Prediction with Cartesian Tensor-Based Deep LearningSemantic proximity Read