NVIDIA today officially launched Cambridge-1, the United Kingdom’s most powerful supercomputer, which will enable top scientists and healthcare experts to use the powerful combination of AI and simulation to accelerate the digital biology revolution and bolster the country’s world-leading life sciences industry.
Dedicated to advancing healthcare, Cambridge-1 represents a $100 million investment by NVIDIA. Its first projects with AstraZeneca, GSK, Guy’s and St Thomas’ NHS Foundation Trust, King’s College London and Oxford Nanopore Technologies include developing a deeper understanding of brain diseases like dementia, using AI to design new drugs and improving the accuracy of finding disease-causing variations in human genomes.
Cambridge-1 brings together decades of NVIDIA’s work in accelerated computing, AI and life sciences, where NVIDIA Clara™ and AI frameworks are optimized to take advantage of the entire system for large-scale research. An NVIDIA DGX SuperPOD™ supercomputing cluster, it ranks among the world’s top 50 fastest computers and is powered by 100 percent renewable energy.
“Cambridge-1 will empower world-leading researchers in business and academia with the ability to perform their life’s work on the U.K.’s most powerful supercomputer, unlocking clues to disease and treatments at a scale and speed previously impossible in the U.K.,” said Jensen Huang, founder and CEO of NVIDIA. “The discoveries developed on Cambridge-1 will take shape in the U.K., but the impact will be global, driving groundbreaking research that has the potential to benefit millions around the world.”
Cambridge-1 builds on the U.K.’s status as a global leader in life sciences, technology and AI by providing advanced infrastructure for current and future generations to carry out groundbreaking research within the country.
According to a report by Frontier Economics, an economics consulting firm, Cambridge-1 has the potential to create an estimated value of £600 million (about $825 million) over the next 10 years.
AstraZeneca: Transforming Drug Discovery with AI
NVIDIA is collaborating with AstraZeneca to fuel faster drug discoveries by creating a transformer-based generative AI model for chemical structures. Transformer-based neural network architectures, which have become available only in the last several years, allow researchers to leverage massive datasets using self-supervised training methods, avoiding the need for manually labeled examples during pre-training.
The MegaMolBART drug discovery model is being used in reaction prediction, molecular optimization and de novo molecular generation and will optimize the drug development process. It is based on AstraZeneca’s MolBART transformer model and is being trained on the ZINC chemical compound database — using NVIDIA’s Megatron framework to enable massively scaled-out training on supercomputing infrastructure. This open-source model will be available to researchers and developers in the NVIDIA NGC™ software catalog.
NVIDIA and AstraZeneca have a separate project on Cambridge-1 focused on the use of AI in digital pathology. In digital pathology, significant time and money are spent annotating whole slide images of tissue samples, to aid the search for new insights. By using unsupervised AI algorithms trained on thousands of images, it is possible to remove the process of annotating while simultaneously finding potential imaging features that correlate with drug response.
“Training AI algorithms on whole slide images is challenging in part due to the size of the images,” said Lindsay Edwards, vice president of Data Science and AI, Respiratory and Immunology, BioPharmaceuticals R&D at AstraZeneca. “Working with NVIDIA on Cambridge-1 enables us to scale our current work and develop new methodologies advancing the use of AI in digital pathology.”