Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More
Cerebras Systems has teamed with Mayo Clinic to create an AI genomic foundation model that predicts the best medical treatments for people with reheumatoid arthritis.
It could also be useful in predicting the best treatment for people with cancer and cardiovascular disease, said Andrew Feldman, CEO of Cerebras Systems, in an interview with GamesBeat.
Mayo Clinic, in collaboration with Cerebras Systems, announced significant progress in developing artificial intelligence tools to advance patient care, today at the JP Morgan Healthcare Conference in San Francisco.
As part of Mayo Clinic’s commitment to transforming healthcare, the institution has led the development of a world-class genomic foundation model, designed to support physicians and patients.
Like Nvidia and other semiconductor companies, Cerebras if focused on AI supercomputing. But its approach is much different from Nvidia’s, which relies on individual AI processors. Cerebras Systems designs an entire wafer — with many chips on a single wafer of silicon — that collectively solve big AI problems and other computing tasks with much lower power consumption. Feldman said it took tens of such systems to compute the genomic foundation model over months of time. Still, that was far less time, effort, power and cost than traditional computing solutions, he said. PitchBook recently predicted that Cerebras would have an IPO in 2025.
Building on Mayo Clinic’s leadership in precision medicine, the model is designed to improve diagnostics and personalize treatment selection, with an initial focus on Rheumatoid Arthritis (RA). RA treatment presents a significant clinical challenge, often requiring multiple attempts to find effective medications for individual patients.
Traditional approaches examining single genetic markers have shown limited success in predicting treatment response.
The joint team’s genomic model was trained by mixing publicly available human reference genome data with Mayo’s comprehensive patient exome data. The human reference genome is a digital DNA sequence representing a composite, “idealized” version of the human genome. It serves as a standard framework against which individual human genomes can be compared, enabling researchers to identify genetic variations.
In contrast to models trained exclusively on human reference genome, Mayo’s genomic foundation model demonstrates significantly better results on genomic variant classification because it was trained on data sourced from 500 Mayo Clinic patients. As more patient data is incorporated into training, the team expects continuous improvement in model quality.
The team designed new benchmarks to evaluate the model’s clinically relevant capabilities, such as detecting specific medical conditions from DNA data, addressing a gap in publicly available benchmarks, which focus primarily on identifying structural elements like regulatory or functional regions.
The Mayo Clinic Genomic Foundation Model demonstrates state-of-the-art accuracy in several key areas: 68-100% accuracy in RA benchmarks, 96% accuracy in cancer predisposing prediction, and 83% accuracy in cardiovascular phenotype prediction. These capabilities align to Mayo Clinic’s vision of delivering world leading healthcare through AI technology. More testing will need to be done to verify the results, Feldman said.
“Mayo Clinic is committed to using the most advanced AI technology to train models that will fundamentally transform healthcare,” Matthew Callstrom, Mayo Clinic’s medical director for strategy and chair of radiology, in a statement. “Our collaboration with Cerebras enabled us to create a state-of-the-art AI model for genomics. In less than a year, we’ve developed promising AI tools that will help our physicians make more informed decisions based on genomic data.”
“Mayo’s genomic foundation model sets a new bar for genomic models, excelling not only in standard tasks like predicting functional and regulatory properties of DNA but also enabling discoveries of complex correlations between genetic variants and medical conditions,” said Natalia Vassilieva, field CTO at Cerebras Systems, in a statement. “Unlike current approaches focused on single-variant associations, this model enables the discovery of connections where collections of variants contribute to a particular condition.”
The rapid development of these models – typically a multi-year endeavor – was accelerated by training Mayo Clinic’s custom models on the Cerebras AI platform. The Mayo Genomic Foundation Model represents significant steps toward enhancing clinical decision support and advancing precision medicine.
Cerebras’ flagship product is the CS-3, a system powered by the Wafer-Scale Engine-3.
Advancing AI for chest X-rays
Separately, Mayo Clinic today unveiled separate groundbreaking collaborations with Microsoft Research and with Cerebras Systems in the field of generative artificial intelligence (AI), designed to personalize patient care, significantly accelerate diagnostic time and improve accuracy.
Announced during the J.P. Morgan Healthcare Conference, the projects focus on developing and testing foundation models customized for various applications, leveraging the power of multimodal radiology images and data (including CT scans and MRIs) with Microsoft Research and genomic sequencing data with Cerebras.
The innovations have the potential to transform how clinicians approach diagnosis and treatment, ultimately leading to better patient outcomes.
Foundation AI models are large, pre-trained models capable of adapting to and carrying out many tasks with minimal extra training. They learn from massive datasets, acquiring general knowledge that can be used across diverse applications. This adaptability makes them efficient and versatile building blocks for numerous AI systems.
Mayo Clinic and Microsoft Research are collaboratively developing foundation models that integrate text and images. For this use case, Mayo and Microsoft Research are working together to explore the use of generative AI in radiology using Microsoft Research’s AI technology and Mayo Clinic’s X-ray data.
Empowering clinicians with instant access to the information they need is at the heart of this research project. Mayo Clinic aims to develop a model that can automatically generate reports, evaluate tube and line placement in chest X-rays, and detect changes from prior images. This proof-of-concept model seeks to improve clinician workflow and patient care by providing a more efficient and comprehensive analysis of radiographic images.
The Mayo Clinic has 76,000 people and they see huge numbers of patients a year.
“We set about on a partnership to bring AI technology to healthcare. This allowed us to to combine sort of their domain expertise, their remarkable data, with our AI expertise and our compute,” Feldman said.
He said that large language models predict words, but genomic models predict nucleotides. When a nucleotide is flipped in a mutation or transcription error, it could be the cause of a disease or could predict the onset of a disease.
Existing models can only ask whether the flipping of a single nucleotide predicts a disease. But Cerebras looks at the flipping of more than one nucleotide and comes up with a more accurate model.
“What we’re using it for, together with Mayo Clinic, is to predict which drug will work for a specific patient,” Feldman said.
It’s a billion-parameter foundation model, or 10 times larger than AlphaFold, and it was trained on a trillion tokens. That makes it more accurate, Feldman said.
Too often, patients have to go through a trial-and-error process to figure out which drug will work. But with this model, Feldman believes that it can predict which drug will work on a specific person. The first target is rheumatoid arthritis, which afflicts 1.3 million Americans.
“While it’s still early, what we have been able to show was that we were able to predict with impressive accuracy which drug would work for a given patient,” he said.
On arthritis, the prediction accuracy was 87%. The data must still be published and peer reviewed.
