Article content
- A new machine learning tool called T1GRS pinpoints people at high risk of developing type 1 diabetes by analyzing the complex interactions between many different genes.
- Although T1GRS was built using data from people of European descent, it also accurately predicts risk for people outside of Europe.
- Four genetic subtypes of type 1 diabetes have emerged, each with different onset patterns and complications, which may aid in personalized treatment of the condition.
In people with type 1 diabetes (T1D), the immune system shuts down the body’s ability to produce insulin, a hormone responsible for regulating blood sugar levels and supplying glucose to cells to produce energy. As a result, they become dependent on external sources of hormones for the rest of their lives. Predicting who will develop T1D remains difficult because existing genetic risk scores are primarily limited to individuals with known high-risk mutations.
Now, researchers at the University of California, San Diego have developed a machine learning model called T1GRS. This model analyzes complex interactions between many different genes and calculates more accurate genetic risk scores for broader populations. This study demonstrated that this tool can be used to identify children and adults at high risk for T1D earlier than current methods, allowing preventive measures to be taken before the disease fully develops. This study was published in Nature Genetics on April 30, 2026.
Prediction of genetic risk
Researchers scoured a genomic dataset of more than 20,000 people with T1D of European descent (along with nearly 800,000 people without autoimmune disease) to examine genetic variations associated with the disease. They identified known risk variants at 79 genetic loci (the physical locations of genes on chromosomes) and 13 loci involved in gene regulation, immune function, and blood sugar control that had not previously been associated with symptoms.
The research team also mapped specific genetic variations in the major histocompatibility complex (MHC), the region on chromosome 6 that contains the strongest known genetic association with T1D. By analyzing data from more than 29,000 people, we discovered several novel variants associated with T1D that affect immune function and gene activation.
“There is a ‘block’ of collaborative genetic information in the MHC that is highly enriched in patients with type 1 diabetes,” said co-author Emily Griffin, Ph.D., a postdoctoral fellow in the lab of Kyle J. Galton, Ph.D., associate professor of pediatrics at the University of California, San Diego School of Medicine. “Having them doesn’t mean you’ll get diabetes, but it does mean you’re very unlikely to get diabetes if you don’t have them.”
