4. AI Co-Scientist

At the core of our work lies research, encompassing both incremental updates that build upon years of progress and groundbreaking developments that transform the industry and our partners’ workflows. To aid biomedical researchers in creating innovative hypotheses and research plans, we have introduced an AI co-scientist, a novel system built on Gemini 2.0. This AI co-scientist enables researchers to parse vast volumes of scientific literature and generate high-quality, novel hypotheses. For example, suppose researchers aim to better comprehend the spread of a disease-causing microbe. By specifying this research goal using natural language, the AI co-scientist will propose testable hypotheses, including a summary of relevant published literature and a possible experimental approach.

Although not intended to automate the scientific process, this collaborative tool is designed to assist experts in discovering new ideas and accelerating their work. We are currently collaborating with partners, including Imperial College London, Houston Methodist, and Stanford University, and are eager to observe how researchers worldwide utilize this tool. While still in its early stages, the enthusiasm is palpable – we have received significant interest in our upcoming trusted tester program.

5. TxGemma

The development of therapeutic drugs from concept to approved use is a lengthy and expensive process, prompting us to work with the broader research community to identify new methods for making this development more efficient.

Today, we announced TxGemma, a collection of Gemma-based open models that we hope will enhance the efficiency of AI-powered drug discovery. TxGemma is capable of understanding regular text and the structures of different therapeutic entities, such as small molecules, chemicals, and proteins. This enables researchers to ask TxGemma questions to help predict important properties of potential new therapies, including their safety and efficacy.

Later this month, we will make TxGemma available to the community to build upon and improve through Health AI Developer Foundations.

6. Treatment Options for Pediatric Oncology

In collaboration with Google, the Princess Máxima Center for pediatric oncology in the Netherlands is developing an AI tool called Capricorn. It utilizes Gemini models to help physicians accelerate the identification of personalized cancer treatments by combining vast public medical data and de-identified patient data.

Based on its analysis, Capricorn rapidly generates summaries of treatment options and relevant medical publications, allowing physicians to engage in more in-depth discussions on how to achieve the best possible health outcomes for their pediatric patients. With AI, physicians have more time to dedicate to what matters most: patient care.