Over five years, the consortium will focus on addressing data gaps through strategic data generation and building high-quality AI-ready genomic datasets. These datasets will power the next generation of AI models for biological discovery.

The partnership aims to make biology more predictive by developing a framework that will support the generation of AI-ready biological datasets specifically designed to train advanced machine learning models. The collaboration seeks to accelerate scientific discovery and unlock deeper biological and biomedical insights.

The organisations will establish a broader consortium focused on generating the biological data required to advance AI in biology and welcome additional collaborators who share their goals.

The initiative builds on an existing relationship between the Sanger Institute and Google DeepMind, including previous research collaborations, a joint AI in genomics fellowship, and shared efforts to strengthen global AI capability and capacity in research, including in lower and middle income countries.

AI is creating unprecedented opportunities to extract insight from genomic and molecular data. While AI is already being used in genomics, opportunities remain to develop models and datasets for underexplored areas of the life sciences. The datasets that the consortium will generate will provide a foundation for training and evaluating AI models capable of making more accurate predictions about biological processes.

Researchers at the Sanger Institute are already applying AI-powered approaches across genomics, from extracting insights from large-scale datasets, integrating information from genes, RNA and proteins, to designing and interpreting experiments.

Dr Julia Wilson, Chief Innovation and Impact Officer at the Wellcome Sanger Institute, said: “By combining Sanger’s expertise in generating world-leading datasets with Google DeepMind’s leadership in artificial intelligence, we have an opportunity to accelerate the generation of biological data specifically designed to power the development of foundational AI models. Through this consortium, we aim to create resources that will be shared widely with the community to enable transformative scientific discoveries and deliver broad impact across the life sciences.”

Dr Pushmeet Kohli, Vice President of AI for Science at Google DeepMind, said: “Together with the Sanger Institute, we aim to build the data backbone needed to decode the complexities of biological processes. Through this work, we seek to establish data scaling laws that could inform future data generation and bring the scientific community closer to a virtual cell, accelerating discovery and unlocking entirely new frontiers for researchers worldwide.”

Anna Koivuniemi, Head of the Google DeepMind Impact Accelerator, said: “Addressing the most significant challenges in biology will require collaboration across disciplines, sectors and institutions. We are excited to partner with the Sanger Institute in order to strengthen AI in genomics opportunities and ensure this data can help to accelerate breakthroughs that benefit humanity.”

Leslie Yeh, Director of Google.org Scientific Progress, said: “Over the past decade, we’ve seen how deep learning can transform our understanding of complex biological challenges. With this new consortium, Google.org is supporting the open-access data foundations needed to fuel the next generation of biological AI models. By accelerating the integration of large-scale genomic datasets, we aim to support the global research community in achieving life-saving scientific breakthroughs.”

Image Credits: James Forshall/Wellcome Sanger Institute