Mysteries surround the complex information encoded within human genomes and cells. Deciphering the intricate language that governs cell structure, function and communication could vastly improve the understanding of human health and disease. 

Carnegie Mellon University's new Center for AI-Driven Biomedical Research (AI4BIO) aims to unlock these mysteries by developing and applying novel artificial intelligence and machine learning methods. These tools seek to illuminate fundamental aspects of gene regulation, cellular function, tissue development and disease progression. AI4BIO will tackle the challenges of applying the latest AI advancements to biomedicine, enabling research to fully incorporate new technologies and tools.

"AI-driven biomedical research holds tremendous potential for addressing intractable problems related to cellular mechanisms and for advancing our understanding of some of the most devastating, incurable diseases," said Jian Ma, the Ray and Stephanie Lane Professor of Computational Biology and director of AI4BIO. "CMU has the talent and creativity to rise to these challenges."

Based in the Ray and Stephanie Lane Computational Biology Department within CMU's School of Computer Science (SCS), AI4BIO will forge new connections across CMU and beyond and establish new frontiers in medicine, advancing treatments for cancer, Alzheimer's and other diseases.

"Advances in AI are transforming scientific inquiry, with the potential for groundbreaking discoveries that could shape the future of medicine," said Martial Hebert, dean of the School of Computer Science. "This initiative positions the School of Computer Science to play a critical role in the development of AI tools and will impact the biomedical research conducted across CMU."

AI4BIO has established its inaugural leadership group, including Ma; Russell Schwartz, head of the Lane Computational Biology Department; Carl Kingsford, the Herbert A. Simon Professor of Computer Science; and Kathryn Roeder, the UPMC Professor of Statistics and Life Sciences.

CMU, SCS and the Lane Computational Biology Department are among the foremost places in the world for developing new computational solutions and tools for the vast amounts of data available about the human body. AI4BIO will build on collaborative opportunities through CMU's automated science and engineering initiative and the new Richard King Mellon Hall of Sciences, which will bring researchers in SCS and the Mellon College of Science together in the same building to chart the future of science.

AI4BIO will leverage recent breakthroughs, such as large language models (LLMs), to develop new models that learn from the wealth of data generated through single-cell genomics, high-resolution imaging and high-precision genome engineering. These models will help scientists interpret genomes, cells and tissues, capturing their spatial and temporal dynamics and guiding the next iterations of experimentation.

"One of the grand challenges in biomedicine is our limited understanding of cellular structure and function. AI4BIO will develop multiscale AI modeling frameworks for a cohesive understanding of genomes, cells and tissues at different scales," Ma said. "This new paradigm is expected to illuminate fundamental aspects of normal development and disease progression."

AI4BIO will build on the Lane Computational Biology Department's long-standing leadership in AI-driven biomedical research and on several earlier large-scale initiatives at CMU, and expand the university's leadership in AI-driven biomedicine. The center will bring together existing CMU faculty to pursue team-based research projects and provide resources to recruit new faculty and cultivate novel research directions. AI4BIO is also seeking partners outside academia to explore shared interests and develop AI solutions to propel biomedical research on multiple fronts.

To learn more about AI4BIO and how to get involved, visit the center's webpage.