SAN FRANCISCO, Sept. 13, 2022 (GLOBE NEWSWIRE) -- Researchers at University of California San Diego and University of California San Francisco have been selected to lead components of the National Institutes of Health (NIH) Common Fund’s Bridge to Artificial Intelligence (Bridge2AI) program. Over the next four years, Bridge2AI will award $130 million to accelerate the widespread use of AI in biomedical research and health care.
Physicians and scientists have long recognized the potential of AI to help understand and treat disease, but its use in clinical and research settings remains limited. This is, in part, because AI tools cannot always be easily or appropriately applied to new datasets that were not organized for this type of analysis. Furthermore, most AI algorithms function as “black boxes” — when they reach a conclusion about something, no one knows exactly how or why that decision was made.
To address these issues, Bridge2AI will fund four Data Generation Projects to create comprehensive AI-ready datasets that will lay the groundwork for new, interpretable and trustworthy AI technologies. The four multi-site projects will be unified by the Bridge Center, an executive hub that oversees the integration, dissemination and evaluation of all Bridge2AI activities.
Trey Ideker, professor at UC San Diego School of Medicine, will serve as principal investigator for one of the Data Generation Projects and will work closely with Nevan Krogan, professor in the Department of Cellular & Molecular Pharmacology in the School of Medicine, senior investigator at Gladstone Institutes, and Director of the Quantitative Biosciences Institute; Andrej Sali, Professor in the Department of Bioengineering and Therapeutic Sciences at UCSF; Emma Lundberg, Professor of Bioengineering and Pathology at Stanford University; and Prashant Mali, Professor of Bioengineering at UC San Diego.
Cell Maps for AI
Ideker, Krogan and collaborators are expected to receive nearly $20 million in the next four years to launch Cell Maps for AI, a research project designed to usher in a new era of precision medicine. The team envisions a future in which an AI algorithm could analyze a patient’s genome and decipher which disease they have, what stage they are in and which treatments are most likely to help. Importantly, they say the algorithm must be interpretable, such that a physician could point to the molecular and cellular pathways that inform its decisions.
“Once we understand the underlying biology, attacking the disease becomes so much more straightforward,” Krogan said. “We’re perfectly positioned to build this bridge from the genome to the clinic for a whole range of diseases.”
“It’s not enough for an algorithm to just take a complex set of mutations and decide what drug to give a patient if we don’t know why it’s making that choice,” said Ideker. “We may now have enough human genomes sequenced to power precision medicine, but what we don’t have yet is a clear map of cellular biology to interpret the data with.”
To address this, the project aims to map the structure and function of a human cell in its entirety, starting with the most basic cell type: the stem cell. The researchers will obtain induced pluripotent stem cells from a variety of genetic backgrounds and combine microscopy, biochemistry and computational tools to study their biology at multiple scales. The final product will be a comprehensive model of the cell, from genes and proteins to entire organelles and how they all work together. Once the stem cell has been modeled, they plan to use the same approach to model other cells, such as those that are dividing, differentiating or in various disease states.
Their goal is to eventually have a library of cell maps across many demographic and disease contexts, which can be used to train AI algorithms to make informed and interpretable decisions about human health.
“The fact that we have nearly a decade of experience working together and generating cell maps for various disease states such as cancer, infectious diseases and psychiatric disorders gives us a head start. Armed with complete maps of how genes and proteins interact in human cells, we see how dozens of seemingly unrelated genes and proteins involved in a disease are in fact all part of the same interconnected biological pathway,” said Krogan.
“With Bridge2AI, we are not only generating unprecedented datasets, but also developing a system to do this work in an organized and ethical way, which will set the field up for future success,” Ideker said.
UCSF is expected to receive close to $4.5 million to work on specific data acquisition and tool development modules and activities. The Krogan lab will map the physical interactions of key chromatin modifiers involved in cancer, neuropsychiatric, and cardiac disorders to identify thousands of protein-protein interactions and provide an unprecedented wealth of mapping data to allow the construction of visible machine learning models with biomedical applications.
“I could not be more excited to join forces with Trey Ideker, Emma Lundberg, Nevan Krogan and others to develop and apply modeling methods that will bridge the gap between structural biology and systems biology. The project will provide us with an opportunity to learn about how best to combine statistical Bayesian modeling and machine learning, and to demonstrate the advantages of the resulting integrative modeling approach in the context of cancer biology,” said Andrej Sali.
An additional complementary lead PI, Emma Lundberg at Stanford University will map the spatial subcellular organization of key chromatin modifiers and metabolic enzymes involved in diseases using high throughput imaging to provide insights into the epigenetic regulation of cell identity as well as a comprehensive catalog of image data to inform AI/ML research.
“Working with this very specific group of people enables the data we generate from imaging to be that much more precise. Using modern microscopy, we can generate such big data sets, while AI-assisted analysis makes us well equipped to efficiently and accurately analyze them,” said Emma Lundberg.
“There’s great value in looking at the big picture,” Krogan said. “It makes these analyses exponentially more powerful. Ultimately, our goal is to apply artificial intelligence to these maps, so they can predict a patient’s prognosis and the best combination of drugs to treat them.”
“Generating high-quality ethically sourced datasets is crucial for enabling the use of next-generation AI technologies that transform how we do research,” said Lawrence A. Tabak, DDS, PhD, who is performing the duties of the Director of NIH. “The solutions to long-standing challenges in human health are at our fingertips, and now is the time to connect researchers and AI technologies to tackle our most difficult research questions and ultimately help improve human health.”
Additional researchers are from the University of Alabama, University of Alabama at Birmingham, University of Montreal, Simon Fraser University, University of South Florida, University of Texas at Austin, University of Virginia and Yale University. Bridge Center collaborators include faculty at the Broad Institute, Vanderbilt University and University of Texas Health.
The Cell Maps for AI project is supported by National Institutes of Health award OT2-OD032742.
Media Contact:
Nicole Mlynaryk, 858-249-0419, npmlynaryk@health.ucsd.edu
Alexa Rocourt, 415-514-9816, alexa.rocourt@ucsf.edu
Rachel Britt, 301-435-0968, cfcomms@nih.gov
