Case Western Reserve University’s new AI tool expands genetic research across multiple ancestries
Uncovers disease risk factors long missed by current methods
Most genetic research used in modern medicine has been conducted on people of European descent—leaving those of other ancestries receiving medical advice based on research that doesn’t apply to them.
For patients from a non-European background, research used to estimate the contribution of risk factors leading to heart disease, cancer or diabetes may be inaccurate.
But researchers at Case Western Reserve University are using artificial intelligence (AI) to identify both shared and ancestry-specific disease risk factors standard approaches often miss.
The goal: more accuracy that potentially saves lives.
Their work, recently published in Genome Biology and funded by the National Institutes of Health, uses transfer learning, a form of AI that allows a computer system to take knowledge learned from one situation and apply it to a different but related situation.
Postdoctoral fellow Yihe Yang and Professor Xiaofeng Zhu, at Case Western Reserve University School of Medicine, have developed the new AI-driven method to study genetics. Called MRBEE-TL and available now, it uses knowledge and data from large European ancestries to help analyze smaller, more varied populations.
“Current methods for analyzing genetic data have a significant limitation; they analyze each group separately,” Zhu said. “With this new method, doctors will be able to offer better targeted treatments, reducing health disparities that have persisted for generations.”
MRBEE-TL combines data from multiple ancestry groups, using AI to account for and correct any biases that can arise when combining data from different populations. Most importantly, it uncovers disease risk factors specific to certain ancestry groups—factors that standard methods miss.
“This is a highly important and impactful study because it addresses a major blind spot in genetic research,” said Zhenghe John Wang, chair of the Department of Genetics and Genome Sciences at the School of Medicine. “By enabling powerful and reliable analysis across diverse ancestries, this method helps ensure that discoveries about disease risks are not limited to a single population, laying critical groundwork for more unbiased and accurate precision medicine for everyone.”
The researchers are now working on using MRBEE-TL to analyze risk factors for major diseases like heart disease, Alzheimer’s, diabetes and cancer, hoping to uncover ancestry-specific risk factors that have previously gone undetected.
