Advancing cutting-edge AI capabilities

From X-rays to digital health records, medicine is inherently multimodal. Our Gemini models were built from the ground up for multimodality, enabling them to reason across complex information—from medical images to the lengthy context of a patient’s entire health history. This sophisticated understanding helps clinicians and researchers find key insights within complex patient data, unlocking new possibilities for care and discovery.

AlphaFold, an AI model from Google DeepMind, is revolutionizing our understanding of proteins, the building blocks of life. By rapidly predicting their complex 3D shapes, AlphaFold is supporting scientists to accelerate research in diverse fields, from developing new malaria vaccines to deepening the understanding of tuberculosis. Isomorphic Labs has expanded on AlphaFold in combination with their other cutting edge proprietary technology—applying this frontier AI technology to tackle drug discovery challenges including small molecules, biologics, and other modalities—with an ambition to one day solve all disease with the help of AI.

Mobile and wearable devices are another promising area where generative AI models could provide personalized insights for both healthcare and wellness. That’s why we developed our foundational Large Sensor Model (LSM), training it on the largest dataset of its kind to decode signals like heart rate and activity levels with remarkable accuracy. LSM is a versatile foundation model that is capable of many downstream health tasks. Building on this foundation, our Personal Health Large Language Model (PH-LLM)—a version of the Gemini model fine-tuned for health— can interpret sensor data and generate insights and recommendations about an individual’s sleep and fitness patterns.