MIT Technology Review is reporting that artificial intelligence is rapidly transforming the pharmaceutical industry, particularly in the development of biologic medicines. The publication, through its custom content arm Insights, highlighted how AI is accelerating the traditionally expensive and failure-prone process of drug discovery.
AstraZeneca, a major pharmaceutical company, is actively integrating AI into its research and development infrastructure. Puja Sapra, senior vice president and head of R&D biologics engineering and oncology targeted discovery at AstraZeneca, said that "everything we do, whether it’s design, make, test, or analyze, is now computationally enhanced." She explained that AI generates and prioritizes candidate molecules, allowing scientists to focus lab resources on the most promising designs, which shortens cycle times and increases productivity.
The report noted that AI is also enabling the discovery of entirely new classes of medicines, such as multi-specific biologics that can target multiple disease pathways simultaneously. McKinsey estimates that generative AI, combined with other computational tools, could reduce drug discovery timelines by up to 50%.
AstraZeneca is leveraging its proprietary, multimodal datasets, which Sapra called a "data moat," to fine-tune frontier AI models. The company is also building a "lab of the future" facility in Kendall Square, Cambridge, Massachusetts, designed as a continuous, closed-loop discovery system where AI and robotic automation will execute experiments and generate data that feeds directly back into the models.
The ultimate vision for AI in biologic drug discovery is "de novo" design, where AI generates entirely new protein sequences from scratch, predicting their structure, safety, behavior in the body and manufacturability. Sapra believes this will become a reality, though challenges remain in standardizing training data, establishing robust evaluation benchmarks, and accurately predicting safety through methods like virtual clinical trials.
The publication emphasized that human talent remains central to this transformation. Scientists will collaborate with AI systems, providing oversight and strategic direction, while engineers design transparent and explainable systems. This human-AI collaboration aims to develop potentially life-changing treatments for many diseases.
Full Article: How AI helps scientists design the next generation of medicines