A total of five national laboratories are now a part of the Accelerating Therapeutics for Opportunities in Medicine (ATOM) consortium, assisting public-private efforts to develop an artificial intelligence(AI)-driven drug discovery platform.
The latest labs to join this week were the U.S. Department of Energy’s Argonne, Brookhaven, and Oak Ridge national laboratories. They join the Frederick National Laboratory (FNL) for Cancer Research and the Lawrence Livermore National Laboratory. Together, their end goal is a speed drug discovery and reduce risk, making a more patient-centric model along the way. The platform they seek will pair various data types with high-performance computing (HPC), advanced experimental technologies, and AI.
“Bringing the experience and expertise from three additional DOE national laboratories to ATOM’s current partners, including the Frederick National Laboratory for Cancer Research (FNL), sponsored by the National Cancer Institute, reinforces ATOM as a valuable national resource to create powerful new capabilities for the cancer research community, building collaborations and driving advances in translational research to develop treatments more quickly,” Eric Stahlberg, director of the Biomedical Informatics and Data Science group at FNL and co-lead of the ATOM consortium, said.
Each lab brings its own specific expertise to the table. Argonne has experience in high-performance computing and computer science, which will be used to perform advanced simulations and further groundbreaking machine learning analytics. Brookhaven will bring knowledge of creating scalable HPC foundations that can effectively pair machine learning with complex, nonlinear, and uncertain aspects common to cancer drug therapy research.
Lastly, Oak Ridge represents the largest DOE science and energy lab with experience in using modeling and simulation on supercomputers, data-intensive science, and biological systems research to accelerate scientific discovery. This experience will be tapped to examine the complex interactions between candidate molecules and the human body. It could also be a good test of the lab’s exascale-class supercomputer, Frontier, which is a national first, scheduled to come online later this year.
“Tightly coupling these quantitative systems pharmacology models with the larger AI workflow is what sets ATOM apart from other AI-driven drug discovery methods,” Marti Head, director of the ORNL-University of Tennessee Joint Institute for Biological Sciences, said. “By integrating high-performance computing, simulation, and big data with chemistry and biology at scale, we can think about drug discovery in one coherent, networked piece and get drugs to patients faster with a greater probability of success. Thinking about the challenges we’ve all been struggling with since the start of the COVID-19 pandemic in March of 2020 is a perfect example of why having these drug discovery tools that can operate holistically and help us move faster is so important for the world.”
The ultimate goal is to pool these resources to cut the drug discovery timeline from five years to less than a year.