Microsoft team's retroChimera in Nature: ensembling diverse models for chemist-aligned retrosynthesis
marwinsegler · x · 2026-09-22
Marwin Segler's team published retroChimera, a retrosynthesis planning model, in Nature:
- Chemical synthesis remains a critical bottleneck in small-molecule drug discovery; AI synthesis planning can propose better routes and make generative molecular design tractable.
- The core idea is ensembling models with diverse inductive biases, aligning predictions with chemists' actual judgments.
- The paper shows deep learning models can now learn from much less data, the ensemble framework improves robustness, and fine-tuning on pharma ELN (electronic lab notebook) data is feasible.
- Authors include Microsoft researchers (e.g., Christopher Bishop) and GSK medicinal chemists; extensive analyses are in the paper, with model code and weights on GitHub.
Related event: Microsoft's retroChimera Hits Nature and Goes Open Source(5 posts)→
More from Research
- 50+ NeurIPS 2025 papers found containing AI hallucinations that slipped past peer review — CSProfKGD · 2026-11-12
- Indie researcher pauses RNN training over environment bugs, shifts to FunSearch-style tasks — cephaloform · 2026-11-12
- Self-supervised visual similarity partially explains word generalization in humans and machines — Patricio M. Vera · 2026-11-12
- P2Echo: one text-prompted model segments multi-view echocardiography with high accuracy and low cost — UBC-V · 2026-11-12
- I Fixed Alamo Drafthouse's Search With Query Logs Alone: +18.4% MRR, No Model Training — CShorten30 · 2026-11-12
- NYU lab open-sources Outerloop: autonomous research agents that open PRs only when benchmarks improve — mengyer · 2026-11-12