AstraZeneca is building an AI-and-robotics biologics lab to speed drug discovery
MIT Tech Review AI · rss · 2026-07-23
AstraZeneca says AI is now embedded across biologics R&D, with a build-measure-learn loop that ranks candidate molecules computationally and sends only the best ones to the lab.
- The company is building a “lab of the future” in Kendall Square, where AI, robotics, and instruments will form a closed-loop discovery system.
- Its proprietary multimodal datasets include molecular structures, binding measurements, safety profiles, and manufacturing outcomes, which it uses to fine-tune frontier models.
- AstraZeneca also points to virtual clinical trial-like systems — advanced cell models and micro-scale organ models — to improve safety prediction for de novo biologic design.
- The long-term goal is AI-generated proteins designed from scratch into clinical candidates, but the company says the field still needs better standardized data, benchmarks, and hybrid ML-biology talent.
- Sapra argues the hardest open problem is safety prediction for molecules generated computationally.
More from Companies & People
- Anthropic files S-1 with SEC, formally kicking off its IPO process — firstadopter · 2026-10-26
- LangChain and Tavily to co-host NYC event on production agents using live web data, Nov 12 — LangChain · 2026-10-26
- Google DeepMind opens 6-month Paris student researcher role on discrete diffusion for 2027 — qberthet · 2026-10-26
- Deep Learning Course Adds Mechanistic Interpretability Lecture This Winter — CSProfKGD · 2026-10-26
- CS professor: don't hide your AI use from future employers, lead with it — lemire · 2026-10-26
- Ex-DOGE cyber researchers breach Anthropic systems with AI agents in under 12 hours — ScottNover · 2026-10-26