Cleveland Clinic researchers are utilizing AI to investigate the connection between the gut microbiome and Alzheimer’s disease. It has been observed in previous studies that changes in gut bacteria occur as Alzheimer’s disease progresses. The study describes a computational approach to identifying the interaction between bacterial metabolites and cell receptors, and their contribution to Alzheimer’s disease.The gut bacteria of individuals with Alzheimer’s disease undergo changes as the disease progresses. A recent study published in Cell Reports presents a computational approach for determining how bacterial metabolites, which are byproducts, interact with cell receptors and contribute to the development of Alzheimer’s disease. Feixiong Cheng, PhD, the first director of the Cleveland Clinic Genome Center, collaborated closely with the Luo Ruvo Center for Brain Health and the Center for Microbiome and Human Health (CMHH) on this study. The research ranks metabolites and receptors based on their likelihood of interaction and their potential influence on Alzheimer’s disease.Alzheimer’s disease is a condition that has been extensively studied in relation to metabolites. The information gathered from these studies is considered one of the most thorough guides to understanding diseases associated with metabolites. When bacteria break down the food we consume, they release metabolites into our bodies. These metabolites then have an impact on our cells and can either aid or harm our health by influencing cellular processes. Metabolites have been linked not only to Alzheimer’s disease, but also to heart disease, infertility, various types of cancer, autoimmune disorders, and allergies. Finding ways to prevent harmful interactions between metabolites and our cells could potentially help in the battle against these diseases. As a result, researchers are actively working on developing drugs that can target and mitigate these interactions.
Some researchers are trying to stop metabolites from binding to receptors on the surface of cells. This is not easy because there is so much information needed to find the right receptor.
Dr. Cheng, a member of the Genomic Medicine Staff, said, “Gut metabolites are important for many processes in our bodies, and each process has a specific receptor. The problem is that there are thousands of receptors and metabolites, so it’s been difficult and expensive to figure out which metabolite goes with which receptor. That’s why we decided to use AI.” Dr. Cheng’s team wanted to see if well-known methods would work.The human body contains gut metabolites with established safety profiles that could potentially be used for preventing or treating complex diseases such as Alzheimer’s. Yunguang Qiu, PhD, a postdoctoral fellow in the Cheng Lab, led a team including J. Mark Brown, PhD, James Leverenz, MD, and neuropsychologist Jessica Caldwell, PhD, ABPP/CN. Leverenz is the Director of Cleveland Clinic Luo Ruvo Center for Brain Healthand and the Cleveland Alzheimer’s Disease Research Center, while Caldwell is the Director of the Women’s Alzheimer’s Movement Prevention Center at Cleveland Clinic Nevada.
The research team utilized machine learning, a form of AI, to examine over 1.09 million potential metabolite-receptor pairs and forecast the probability of each interaction contributing to Alzheimer’s disease.
The analyses involved:
- genetic and proteomic data from human and preclinical Alzheimer’s disease studies
- various receptor (protein structures) and metabolite shapes
- the impact of different metabolites on patient-derived brain cells
The team scrutinized the metabolite-receptor pairs with the highest likelihood of influencing Alzheimer’s disease.
Alzheimer’s disease can be detected by examining brain cells from patients. A protective metabolite known as agmatine, which is believed to protect brain cells from inflammation and associated damage, was the focus of the study. The research revealed that agmatine is most likely to interact with a receptor called CA3R in Alzheimer’s disease.
When Alzheimer’s-affected neurons were treated with agmatine, the levels of CA3R were reduced, indicating that the metabolite and receptor have an influence on each other. Furthermore, the treated neurons showed lower levels of phosphorylated tau proteins, which are a marker for Alzheimer’s disease.
Dr. Cheng explained that these experiments demonstrate how his team’s AI algorithm.Algorithms have the potential to open up new areas of research into various diseases in addition to Alzheimer’s. “We concentrated on Alzheimer’s disease, but the interactions between metabolites and receptors are relevant to nearly every disease involving gut microbes,” he explained. “We aim to establish a foundation for advancing the entire field of metabolite-related diseases and human health with our techniques.” Dr. Cheng and his team are now working on refining and utilizing these AI technologies to explore the connections between genetic and environmental factors (such as diet and gut metabolites) in relation to human health and diseases, including Alzheimer’s and other conditions.The study was supported by the National Institute of Neurological Disorders and Stroke and the National Institute on Aging under the National Institutes of Health. Yunguang Qiu, a postdoctoral fellow at the Cheng Lab, was the first author of the study.
