Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· 0 citations· 48 references
TL;DR
LinkerBridge is proposed, an equivariant framework that unifies biochemical semantics with physical constraints through two innovations: a Contextual Interaction-Aware Representation module that internalizes pre-existing bio-chemical semantics and a Differentiable Physical Guidance mechanism derived from Van der Waals potentials to steer generation away from collision zones.
Abstract
3D molecular linker design is a critical task in structure-based drug discovery, which requires the precise synthesis of chemical bridges to connect fragments within the constrained environment of a protein binding pocket. Existing methods often suffer from environmental blindness, treating the inter-fragment space as a vacuum and yielding candidates with poor binding affinity or severe steric clashes. To address this, we propose LinkerBridge, an equivariant framework that unifies biochemical semantics with physical constraints through two innovations: a Contextual Interaction-Aware Representation module that internalizes pre-existing biochemical semantics, and a Differentiable Physical Guidance mechanism derived from Van der Waals potentials to steer generation away from collision zones. Extensive evaluations on ZINC, GEOM, and BindingMOAD benchmarks, as well as Hsp90 and JNK3 case studies, demonstrate that LinkerBridge significantly outperforms state-of-the-art methods in real-world drug discovery.
Analysis of protein–ligand cocrystal structures with 131 431 modifiable positions shows that approximately 22% of positions can accommodate linkers without significant geometric restriction.
The central theme, conformational analysis, links on-target potency via pre-organization of the bioactive conformation with physics-based physicochemical property prediction with physics-based physicochemical property prediction, highlighting neutral polarity as a key determinant of permeability and exposure.
Metal-organic frameworks (MOFs) with precisely modified pore environments are essential for applications in catalysis, gas capture, and gas sensing. However, creating these highly selective sites through straightforward synthetic routes remains a challenge. Herein, we present a design strategy for UiO-type MOFs that en...
Tobias Hennig, Erik Rohloff, Verena Drewes et al.· Angewandte Chemie· 0 citations
Boltz2ESI is introduced, an end-to-end framework that predicts enzyme–substrate interactions by leveraging structural knowledge learned by a biomolecular foundation model and consistently outperforms state-of-the-art sequence-based and rigid-docking approaches.
Xi-Wei Cheng, Seonghwan Seo, C. Huh et al.· bioRxiv· 0 citations
EvoBind-multimer is presented, a deep learning framework for the de novo design of molecular glues directly from protein sequences that generates small macrocyclic peptides that bridge user-defined protein pairs without requiring prior interface knowledge or existing ligands.
Andrä Brunner, Krzysztof Wierbiłowicz, Diandra Daumiller et al.· bioRxiv· 0 citations
Scaffold-Guided Structure Refinement is presented, leveraging information on known binders within ligand series targeting a specific protein, based on the observation that shared molecular scaffolds among binders exhibit conserved binding modes.
J. Pletzer-Zelgert, Matthias Rarey, Bernd Kuhn· Journal of Medicinal Chemist...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.