Скачать или смотреть ConGLUDe: Bridging the Gap in AI Drug Discovery (2601.09693)

Paper: Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design (2601.09693)
Published: 14 Jan 2026.

Learn more on Emergent Mind: https://www.emergentmind.com/papers/2...
arXiv: https://arxiv.org/abs/2601.09693
Sign up for our free trending papers email digest: https://www.emergentmind.com/subscribe
Follow us on X: https://x.com/EmergentMind
Join our Discord:   / discord  

This video details ConGLUDe, a groundbreaking framework that unifies the precision of structure-based design with the scale of ligand-based bioactivity data. We examine how its pocket-agnostic, two-tower architecture uses contrastive learning and virtual nodes to predict binding sites dynamically, eliminating the need for manual pocket definition. The discussion covers the model's comprehensive three-axis loss function, its ability to generalize effectively to novel molecular structures, and its state-of-the-art performance in zero-shot virtual screening tasks compared to traditional methods.