Large Drug Discovery Model LDDM debuts with X-ray-validated novel hits across 5 targets
IAmSamFin · x · 2026-09-20
igashov and colleagues released LDDM, a generative structure-based drug discovery (SBDD) framework, alongside a preprint. The team reports experimental validation across 5 targets, successfully designing novel, experimentally confirmed hits whose structural accuracy was verified by X-ray crystallography. ML researcher Rebecca Neeser, who came from drug discovery, noted that critiquing generative molecules became noticeably harder with this model — a major step forward.
Related event: LDDM: New Large Drug Discovery Model Validated by X-ray Structures(2 posts)→
More from Research
- LangChain's Jev-as-a-Judge: cheap, fast semantic verifiers for agent evals — multiply_matrix · 2026-09-20
- Spotify reframes recommender systems for the agentic web in weekly IR papers roundup — _reachsumit · 2026-09-20
- Microsoft researcher points out BERT was already called an LLM back in 2019 — JFPuget · 2026-09-20
- OpenAI's Navier-Stokes claim under fire: did Codex lift two mathematicians' approach? — ExamImmediate8956 · 2026-09-20
- Have we seen an acceleration in discoveries? Cyber spikes, math rises, algorithms flat — soumitrashukla9 · 2026-09-20
- TovanaEngine: a local world model trained on 50K+ real SWE-bench coding-agent runs — Decent-Ad9950 · 2026-09-20