Mapping brain aging at the cellular level using machine learning

In a comprehensive Genome Press interview, Stanford University researcher Eric San reveals how machine learning is revolutionizing the understanding of brain aging at unprecedented cellular resolution. Dr. Sun, who will establish an independent laboratory at MIT's Bioengineering School and Ragon Institute in 2026, represents a new generation of computational scientists transforming aging research through innovative machine learning approaches.

Groundbreaking discoveries in cell aging mechanisms

Dr. Sun's groundbreaking work focuses on the development of a “spatial aging clock,” a sophisticated machine learning model that can measure biological age at the individual cellular level. This represents a quantum leap from traditional aging studies, which typically examines tissue or organs as a whole unit. His recent natural publication (2025) shows how these computational tools can identify specific cell types that dramatically affect cell-neighboring senescence trajectories.

“I've always been fascinated by the biology of aging,” explains Dr. San in an interview. “Why do wrinkles develop when you get older? Why do they become difficult to learn and forget? Why do they seem to be experiencing aging, even though they live considerably longer than other animals?” These basic questions fostered his early interest in aging studies after discovering Cynthia Kenyon's work, which dramatically extended the lifespan of C. elegans in his elementary school days.

An innovative computational framework for aging research

The approach of researchers at Stanford University represents a fundamental change in the way scientists study aging. While traditional methods often provide extensive snapshots of the aging process, Dr. Sun's spatial aging clock can accurately identify which cells are aging faster or slower within complex tissue environments. This granularity understanding opens up new possibilities for targeted interventions. Can researchers ultimately identify and correct “bad actors” in specific cells that accelerate the aging of brain tissue? Is it possible to enhance cellular activity that promotes youthful functioning of neighbors?

Dr. Sun's research methodology combines spatial transcriptomics with single cell analysis to create a detailed map of how aging progresses through brain tissue. His machine learning models reveal complex intercellular communication networks that determine whether adjacent cells rapidly age or maintain youthful properties, rather than simply identifying aged cells.

From mathematical foundations to biological discoveries

This path to breakthrough reflects Dr. Sun's unique multidisciplinary background. Growing up in Pueblo, Colorado, he spent countless hours in the public library. At first, he was fascinated with dinosaurs and space exploration before being drawn to mathematics. “Mathematics has been my favorite subject throughout high school,” he points out.

This mathematical foundation proved important when Dr. Sun began developing computational models when he studied chemistry, physics and applied mathematics in his undergraduate year at Harvard University. His projects ranged from simulations of chromosome evolution to building mathematical models of aging and using machine learning to predict age from multi-omic data. These experiences have established his calculation expertise that enables the development of innovative spatial aging clocks.

Impact on dementia and neurodegenerative studies

The practical applications of Dr. Sun's work go far beyond basic science. His computational framework can change the way researchers approach age-related diseases, particularly dementia and other neurodegenerative conditions. By identifying specific cellular mechanisms that promote brain aging, scientists may develop more accurate therapeutic targets. What if we could design treatments to enhance rejuvenation signals from beneficial cells while suppressing the senescent effects of problematic cell populations?

Dr. San's work also raises interesting questions about the nature of aging itself. If individual cells can influence the trajectory of neighbors' aging, how can environmental factors or therapeutic interventions exploit these cellular communication networks? Is understanding these mechanisms likely to lead to treatments that not only slow aging, but actually reverse it in certain brain regions?

Building the next generation of aging researchers

Beyond his contributions to research, Dr. Sun emphasizes the importance of mentoring future scientists. “Outside of my research, I am excited to set up my lab and mentor students and postdoctoral researchers,” he said. “I want to support and nurture the next generation of scientists both in the field of aging research and beyond.”

His commitment to scientific instruction reflects broader concerns about supporting young researchers through the inevitable challenges of scientific discovery. Dr. Sun says that despite the scientific community being “very common than the former”, the scientific community often emphasizes success over failure, and in many cases a series of failures is the catalyst for the discovery and success of the final research.”

Future directions in computational aging research

Looking ahead, Dr. Sun plans to extend the spatial aging clock framework to other organizations and develop it as a standard tool for the aging research community. His lab focuses on building large-scale AI models to predict the effects of multi-scale biological perturbations and enable high-throughput calculation screens for potentially rejuvenating interventions.

Researchers' long-term visions include transforming computational discoveries into effective therapeutics. His work suggests a future where aging studies go beyond explaining what happens during aging, and control exactly how it occurs. Can his spatial aging clock ultimately lead to individual anti-aging treatments tailored to the individual's specific cell aging patterns?

Dr. Sun's work also highlights the evolving relationship between artificial intelligence and biological discoveries. His spatial aging clock shows how machine learning not only analyzes complex biological data, but also generates entirely new insights into basic life processes. As computational power continues to progress, what other biological mysteries could be brought to similar AI-driven approaches?

Dr. Eric Sang's Genome Press interview is part of a larger series called Innovators & Ideas, which highlights the people behind today's most influential scientific breakthroughs. Each interview in the series offers a blend of cutting-edge research and personal reflection, providing readers with a comprehensive view of scientists who shape the future. By focusing on professional achievements and personal insights, this interview style brings rich stories that attract and educate readers. This format provides an ideal starting point for profiles exploring the impact of scientists on the field, and also touches on the broader human themes. For more information about research leaders and rising stars featured in Innovators and Ideas – Genome Press interview series, visit the publication's website https://genomicpress.kglmeridian.com/.