Biomni AI digests 803 COVID Moonshot compounds, returns Markush core and 50-molecule catalogue
matteo_aldeghi · x · 2026-11-17
- Matteo Aldeghi of the FutureHouse science team ran chemistry in Biomni Lab, feeding it 803 public COVID Moonshot compounds to decide which series to pursue.
- Biomni clustered them into 3 candidate series, flagged potency, synthetic accessibility and oral risk, and built a SAR across 18 traceable comparisons.
- For the chosen series it returned a Markush core plus a 50-molecule catalogue (30 potency-push / 20 SAR-exploration); the reasoning is traceable so chemists can audit it rather than trust a ranking.
More from Research
- BrickFlow uses SE(3) flow models to reconstruct buildable LEGO assemblies from images — Peter Kulits · 2026-11-17
- Meta-model writes weight updates from one paragraph, beating LoRA on many benchmarks — gdm3000 · 2026-11-17
- SPARE preprint: 2.55x faster decoding for linear attention on a 1.3B model — krishnan · 2026-11-17
- Study estimates ~12% of philosophy published today may be AI-generated — leland_mcinnes · 2026-11-17
- Berkeley EECS & Statistics open all-rank faculty search in AI for Physical Sciences — berkeley_ai · 2026-11-17
- Origami as physical reservoir computing: powering robotic crawling in Scientific Reports — cephaloform · 2026-11-17