ETH Zurich and Roche use active learning to predict reactions in data-scarce drug discovery
jiqizhixin · x · 2026-10-21
ETH Zurich and Roche Innovation Center published a closed-loop active-learning framework in Nature Computational Science (Oct 9, 2026) for predicting C–H borylation in drug discovery.
- Problem: when a candidate drug has multiple similar C–H bonds, predicting whether and where borylation occurs is hard, and high-throughput experiments are too costly to generate diverse training data
- Method: combines active learning with geometric deep learning — an XGBoost ensemble on ECFP4 fingerprints first predicts substrate borylation, with closed-loop experiments iteratively adding high-value data
- Open-access paper; a concrete AI-for-Science advance in pharmaceutical reaction prediction
More from Research
- Paper asks 'How long is the coast of a neuron?' — resolution shapes neural computation — neurovium · 2026-10-21
- OpenAI scales thousands of AI agents to find new leads in biological data — truecakesnake · 2026-10-21
- EAU: Co-evolving user simulator, environment, and RL setup for training LLM agents — UAlberta · 2026-10-21
- Meta's Self-Credit: Dense Rewards from Sparse RLVR via Intra-group Rescaling — meta · 2026-10-21
- New paper: game-theoretic limits of being helpful yet harmless when an AI assistant doesn't know who it's talking to — conitzer · 2026-10-21
- CS1: a 4B clinical decision model trained on 12.4M questions beats open rivals — AI4Pathology · 2026-10-21