4. AI-CO-scientist
Research is at the heart of our work, whether it is step -by -step updates that are based on many years of progress, or cutting -edge developments that change industry and how our partners work. To help biomedical researchers create new hypotheses and research plans, we recently launched an AI-CO scientist, a new system built on Gemini 2.0. AI-CO scientist helps researchers analyze large quantities of scientific literature and create high quality hypotheses. For example, let’s say that researchers will better understand the spread of a disease -causing microbe. They can specify this research goals using natural language, and the AI-CO scientist will suggest testable hypotheses, including a summary of relevant published literature and a possible experimental approach.
While not intended to automate the scientific process, this collaborative tool is designed to help experts reveal new ideas and speed up their work. We are already working with partners, including Imperial College London, Houston Methodist and Stanford University, and are eager to see how scientists around the world use this tool. And while it is in the early days, the enthusiasm is ready – we have received considerable interest in our upcoming trusted tester program.
5. TXGEMMA
The development of therapeutic drugs from concept to approved use is a long and expensive process, so we work with the wider research community to find new ways to make this development more efficient.
Today we announced TXGEMMA, a collection of Gemma-based open models that we hope will help improve the effectiveness of AI-driven drug discovery. TXGEMMA is able to understand regular text and structures of different therapeutic devices, such as small molecules, chemicals and proteins. This means that researchers can ask TXGEMMA questions to help predict important features of potential new therapies such as how safe or effective they can be.
Later this month, we will make this available to society to build on and improve through health developer foundations.
6. Treatment options for pediatric oncology
Using Google, the Princess Máxima Center for Pediatric Oncology in the Netherlands develops an AI tool called Capricorn. It uses gemini models to help doctors accelerate the identification of personalized cancer treatments by combining huge public medical data and de-identified patient data.
Based on its analysis, Capricorn Generates quickly summarizes treatment options and relevant medical publication, which allows doctors to have more in -depth discussions on how to achieve the best possible health results for their pediatric patients. With AI, doctors have more time to dedicate what is most important: patient care.