Artificial intelligence is compressing drug discovery timelines and opening up previously untreatable disease targets, according to a deep dive from MIT Technology Review published July 23 in partnership with AstraZeneca.
The feature details how AI has become core infrastructure in pharmaceutical R&D, particularly for biologic medicines made from engineered proteins. AstraZeneca’s biologics engineering team uses a build-measure-learn loop where AI generates candidate molecules computationally and predicts which designs are most likely to succeed. Lab resources are then focused only on the top-ranked candidates, creating tighter feedback cycles with fewer dead ends.
Puja Sapra, senior vice president and head of R&D biologics engineering at AstraZeneca, said the company’s proprietary multimodal datasets covering molecular structures, binding measurements, safety profiles, and manufacturing outcomes serve as a key differentiator. McKinsey estimates that generative AI combined with other computational tools could slash drug discovery timelines by as much as 50%.
The article highlights AstraZeneca’s lab of the future facility in Kendall Square, Cambridge, where AI and robotic automation form a continuous closed-loop discovery system. Scientists remain central to the process, providing oversight and strategic direction, while automated high-throughput systems eventually aim to make and evaluate thousands of molecular interactions weekly.
The approach is also enabling entirely new classes of medicines that can hit multiple disease targets simultaneously or deliver therapeutic payloads to specific cells. Sapra described this as making the drugging of previously impossible targets a practical reality rather than a theoretical ambition.
