Researchers at the University of Texas at Arlington (UTA) have received a $1.96 million grant from the National Eye Institute (NEI) to develop artificial intelligence-powered computational tools designed to identify biological regulators involved in maintaining ocular health and driving eye disease.
The four-year project, led by Xinlei (Sherry) Wang, the Jenkins Garrett Professor of statistics and data science in UTA’s Department of Mathematics, aims to improve understanding of the molecular mechanisms underlying eye diseases and identify potential targets for future diagnostics and therapies.
“The eye contains many specialized tissues and cell types that work together to make vision possible,” said Wang. “Understanding the complex relationship between tissue-specific transcriptional regulators and visual function is a cornerstone of vision research.”
Working alongside Lin Xu, assistant professor at UT Southwestern Medical Center, Wang’s team will combine expertise in Bayesian statistics, bioinformatics, single-cell sequencing, omics data analysis, and ocular biology to develop two complementary computational tools.
The first will use scalable algorithms to analyze large genomic datasets and identify transcriptional regulators associated with ocular health and disease. The researchers aim to ensure the tool can efficiently process increasingly large volumes of biological data.
The second tool will address the cellular complexity of ocular tissues by computationally separating signals from different cell types within whole-tissue samples. This approach could allow researchers to investigate cell-specific regulatory activity without conducting costly single-cell experiments for every regulator.
“When researchers analyze a whole tissue sample, the signals are mixed together,” Wang explained. “Our second tool will computationally separate those mixed signals to reveal how a regulator may behave in particular cell types without requiring very expensive single-cell experiments for every regulator.”
By integrating tissue-level and cell-type-specific analyses, the researchers hope to identify regulatory pathways that warrant further investigation, potentially accelerating the discovery of disease mechanisms and therapeutic targets.
The project builds on Wang’s broader research into AI-driven statistical methods for investigating complex diseases, including a separate collaboration exploring AI and Bayesian learning to accelerate drug design.
“Together, these two tools will let us study the eye at two levels: the overall tissue level and the individual cell-type level within it,” Wang said. “The long-term goal is to improve understanding of eye disease mechanisms and help the field identify promising directions for future diagnostics and targeted therapies.”
Source: University of Texas at Arlington.
