LDDM: 3D generative model designs novel drug hits validated by X-ray across 5 targets
mmbronstein · x · 2026-09-19
- A team from EPFL, UCSF and partners (Igashov, Bronstein, Correia et al.) released LDDM, a unified 3D generative model for synthesizable structure-based drug design (SBDD), on bioRxiv.
- Key results: experimentally validated across 5 targets, designing novel hits with structural accuracy confirmed by X-ray crystallography — beyond purely computational validation common in generative drug design.
- Preprint: doi 10.64898/2026.09.15.751537.
Related event: Large Drug Discovery Model Released with X-ray Validation(4 posts)→
More from Research
- Meta's Atomic Creator Tokens beat Semantic IDs: +19.8pt Recall@15 and 2.7x lower latency — _reachsumit · 2026-11-04
- HiGenTrans transfers LLM knowledge into generative recommenders at input, representation and decision levels — _reachsumit · 2026-11-04
- SA-OPSD distills self-teacher knowledge at beam-search pruning boundaries for generative recommendation — _reachsumit · 2026-11-04
- MV-Thinker: Multi-View Thinking with Adaptive Generation for Generative Recommendation — _reachsumit · 2026-11-04
- ByteDance details USDB storage system: 85.8% lower write latency for recommender sequences — _reachsumit · 2026-11-04
- Kuaishou's UAGR injects utility signals into semantic codes and decoding for generative recommendation — _reachsumit · 2026-11-04