AI Helps CMU Study Alzheimer’s Impact on Brain Cells

Alzheimer’s disease, a leading cause of dementia, has long been associated with amyloid-beta plaques and tau tangles in the brain. However, recent research from Carnegie Mellon University has uncovered a new dimension: the reorganization of DNA within brain cells, which might influence genetic expression and disease progression.

Published in the journal Science, the study highlights the work of Jian Ma, the Ray and Stephanie Lane Professor of Computational Biology. Ma emphasizes the importance of examining not just individual genes but the entire genome’s 3D structure to better understand Alzheimer’s disease.

Exploring Cellular Changes in Alzheimer’s Disease

The research team analyzed postmortem brain tissue from Alzheimer’s patients and healthy individuals, focusing on the prefrontal cortex. Using GAGE-seq, a tool for examining single-cell structures, they discovered unexpected interactions between different DNA regions within affected brain cells.

In Alzheimer’s-affected brain cells, DNA is organized differently, with normally separate regions becoming more mixed together. These changes in DNA organization were linked to lower gene activity and changes in how brain cells function.

Collaborating with the University of Pittsburgh School of Medicine, Carnegie Mellon University spearheaded the study. Hansruedi Mathys, assistant professor of neurobiology at Pitt, remarked, “Our study represents a major advance in understanding what goes wrong in Alzheimer’s disease.”

AI and the Link Between DNA Structure and Gene Activity

To delve deeper into how DNA reorganization influences gene activity, researchers developed Hicformer, an AI model that merges DNA sequences with cellular structures to predict gene behavior. This tool serves as a computational environment to explore how genome folding affects gene activity.

Yang Zhang, a project scientist at the Ray and Stefanie Lane Computational Biology Department at CMU, noted, “Measuring gene activity and genome folding in the same cell allows us to directly connect chromosome structure with disease-related gene programs.”

The study’s findings underscore the significance of 3D genome organization in Alzheimer’s biology, potentially paving the way for future research to pinpoint structural changes that may lead to new therapeutic targets. This work was supported by the National Institutes of Health and involved a team of researchers from various institutions, including the Broad Institute of MIT and Harvard, UCLA, and the University of Washington.