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.
More from Research
- HyperFrames and Google DeepMind Launch Code2Video Bench for Agentic Video Tasks — aftahi_ai · 2026-09-22
- Researcher proposes strict ICLR reforms: 3-paper cap, 10-page limit, reproducibility required — A_K_Nain · 2026-09-22
- Jev reportedly does tensor logic under the hood: differentiable IF args, no wasted gen tokens — StewartalsopIII · 2026-09-22
- Microsoft's BI-Bench: Frontier LLMs Score Under 50% on End-to-End Business Intelligence — MicrosoftResearch · 2026-09-22
- What Is RLCD? Fudan Researcher Explains the Method Behind Jev — SinclairWang1 · 2026-09-22
- Is synthetic-cell SpudCell the enabling tech for mirror life? Researchers weigh in — NikoMcCarty · 2026-09-22