AI Predicts Cancer: Genomics Model Simulates Tumors
Unlocking Cancer’s Secrets: New Computational Framework Revolutionizes Biological Research
Baltimore, MD – A groundbreaking computational framework, developed by researchers at the University of Maryland School of Medicine (UMSOM), is poised to revolutionize how scientists understand and combat complex diseases like cancer.This innovative approach, detailed in a recent study, allows for the creation of refined, predictive models of biological systems, effectively transforming laboratory experiments and clinical trials into virtual simulations.
the research, spearheaded by the Institute for Genome Sciences (IGS) at UMSOM, leverages new spatial genomics technology to provide unprecedented insights into the intricate communication networks between cancer cells and their surrounding habitat. Specifically, the team utilized this technology to meticulously track the growth and progression of pancreatic tumors, from their initial development to invasive stages, using real patient tissue.This allowed for a detailed understanding of how cancerous cells, such as fibroblasts, interact with tumor cells.
“What makes these models so exciting to me as someone who studies immunology is that they can be informed, initialized, and built upon using both laboratory and human genomics data,” explained Dr. Johnson, a key researcher on the project. “Immune cells are amazing and follow rules of behavior that can be programmed into one of these models. So, for instance, we can take data and treat it as a snapshot of what the human immune system is doing, and this framework gives us a sandbox to freely investigate our hypotheses of what’s happening there over time without extra costs or risk to patients.”
Elana J. Fertig, PhD, Director of IGS and a lead author on the study, drew a parallel between this biological modeling and her previous work in weather prediction. ”Ever since my transitioning from my training in weather prediction at the University of Maryland, College Park into computation, I have believed that we coudl apply the same principles to work across biological systems to make predictive models in cancer,” she stated. “I am struck by how many rules of biology we don’t yet know. Adapting this approach to genomics technologies gives us a virtual cell laboratory in which we can conduct experiments to test the implications of cellular rules entirely in silico.”
Dr. Fertig described the research as a “tapestry of team science,” with crucial validation of the computational models provided by clinical collaborators at Johns Hopkins University and Oregon health Sciences University. The project received vital funding from the National Foundation for Cancer Research.
In a move to accelerate scientific progress, the newly developed computational “grammar” is open source, ensuring its accessibility to the global scientific community. “By making this tool accessible to the scientific community, we are providing a path forward to standardize such models and make them generally accepted,” commented Dr. Bergman. To underscore the broad applicability of this framework, researchers led by Genevieve Stein-O’Brien, PhD, of Johns Hopkins School of Medicine, successfully applied the approach to a neuroscience example, simulating the intricate process of brain layer formation during development.
Mark T. Gladwin, MD, Vice President for Medical Affairs at the University of Maryland, Baltimore, and UMSOM Dean, highlighted the transformative potential of this work. “With this work from IGS, we have a new framework for biological research since researchers can now create computerized simulations of their bench experiments and clinical trials and even start predicting the effects of therapies on patients,” he said. ”This has significant applications to enable digital twins and virtual clinical trials in cancer and beyond. We look forward to future work extending this computational modeling of cancer to the clinic.”
The senior authors of the study, including paul Macklin, PhD, of Indiana University, Genevieve Stein-O’Brien, and Dr. Fertig, are actively working to disseminate this software and enhance its integration with genomics data for automated model formulation. This ongoing effort is supported by the National Cancer Institute (NCI) Informatics Technology in cancer Research Consortium. Further validation and applications of the software to breast and pancreatic cancer are also supported by numerous NCI grants, the Jayne Koskinas Ted Giovanis Foundation, the National Foundation for Cancer Research, the Cigarette Restitution Fund Program from the State of Maryland, and the Lustgarten Foundation.