New AI algorithm could improve autoimmune disease prognosis and treatment

A new cutting-edge artificial intelligence (AI) algorithm could lead to better — and earlier — predictions and new treatments for autoimmune diseases, in which the immune system mistakenly attacks the body's own healthy cells and tissues. Attacks. Algorithms dig into the genetic code to more accurately model conditions for how genes associated with specific autoimmune diseases are expressed and regulated and identify additional risk genes.

The work, developed by a team led by Penn State College of Medicine researchers, improves on existing methods and identifies 26 percent more novel gene-trait associations, the researchers said. He published his work today. Nature Communications.

“We all carry some DNA mutations, and we need to know how one of these changes can affect the expression of genes associated with disease so that we can predict disease risk sooner. This is especially important for autoimmune disease,” said distinguished professor Dajiang Liu. , vice chair for research, and director of Artificial Intelligence and Biomedical Informatics at Penn State College of Medicine and co-senior author of the study.

“If an AI algorithm can more accurately predict disease risk, it means we can intervene earlier.”

Genetics often emphasizes the development of disease. Mutations in DNA can affect gene expression, or the process by which information in DNA is converted into functional products such as proteins. How much or how little a gene is expressed can affect disease risk.

Genome-wide association studies (GWAS), a popular approach in human genetics research, can pinpoint regions of the genome associated with a particular disease or trait but not identify specific genes influencing disease risk. could do It's like sharing your location with a friend with the exact location settings on your smartphone—the city may be clear, but the address is fuzzy.

Current methods are also limited in their analysis of particles. Gene expression can be specific to certain cell types. If the analysis does not distinguish between different cell types, the results may ignore true causal relationships between genetic variation and gene expression.

The research team's method, dubbed EXPRESSO for expression prediction with only abstract data, applies a more advanced artificial intelligence algorithm and data from single-cell expression quantitative trait loci. Analyzes, a type of data that links genetic variants to the genes they regulate.

It also integrates 3D genomic data and epigenetics—which measures how genes can be altered by the environment to affect disease—into its modeling. The team applied EXPRESSO to GWAS datasets for 14 autoimmune diseases, including lupus, Crohn's disease, ulcerative colitis and rheumatoid arthritis.

“With this new method, we were able to identify many risk genes for autoimmune disease that actually have cell type-specific effects, meaning that their effects are limited to a particular cell. in one type and not in another,” said Bebo Jiang, assistant professor. Penn State College of Medicine and senior author of the study.

The team then used this information to identify potential treatments for the autoimmune disease. Currently, there are no good long-term treatment options, he said.

“Most treatments are designed to relieve symptoms, not cure the disease. It's a dilemma knowing that an autoimmune disease requires long-term treatment, but current treatments often have such side effects. However, studies co-senior author Laura Carell, a professor of genomics and molecular biology at Penn State College of Medicine, said that AI is an important tool for the development of novel treatments. offer a promising path.

The team's work pointed to drug combinations that could reverse gene expression in cell types associated with autoimmune disease, such as vitamin K for ulcerative colitis and metformin, which is commonly associated with type 2 diabetes. Recommended for type 1 diabetes. These drugs, already approved by the Food and Drug Administration as safe and effective for treating other diseases, could potentially be repurposed.

The research team is working with collaborators to validate their findings in a laboratory setting and, ultimately, clinical trials.

Leda Wang, a doctoral student in the biostatistics program, and Chicharat Khonsarirakskol, who earned a doctorate in bioinformatics and genomics in 2022 and received his medical degree from Penn State in May, co-led the study. Other Penn State College of Medicine authors on the paper include: Havel Marcus, who is pursuing a doctorate and medical degree; Dai Chen, doctoral candidate; Fan Zhang, graduate student; and Fang Chen, postdoctoral scholar. Xiaowei Zhan, associate professor at UT Southwestern Medical Center, also contributed to this paper.