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
- Lightning AI says it will show its full stack at Ai4 in Las Vegas — LightningAI · 2026-07-23
- Princeton’s Northeast Robotics Colloquium opens papers, demos and Rising Stars — tomssilver · 2026-07-23
- Post-quantum security starts with knowing where your cryptography lives — moniquejmorrow · 2026-07-23
- Gary Marcus says a new Substack post adds context to the OpenAI–Hugging Face incident — GaryMarcus · 2026-07-23
- Delaware is trying to get ahead of AI-run companies before they become real — bloomberglaw · 2026-07-23
- OpenAI Codex community hackathon draws a full room of builders and judges — paw_lean · 2026-07-23