A new machine learning tool called “Evolutionary Action Machine Learning” (EAML) has identified sex-specific genes that contribute to Alzheimer’s disease. The tool was developed by researchers at the Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital and the Baylor College of Medicine. EAML uses an advanced computational predictive feature called the “evolutionary action (EA) score” to find genetic factors that influence Alzheimer’s risk separately in males and females. By using this approach, the researchers were able to identify 98 genes associated with Alzheimer’s, several of which were found to affect different disease progression in men and women.
The sex-separated study identified 157 Alzheimer’s-associated genes in males and 127 in females, and revealed that biological pathways may have a significant impact on Alzheimer’s development in one of the sexes more than in the other. For example, they found that female-specific EAML candidates are involved in a module related to cell cycle and DNA quality control, with links to the BRCA1 gene, which is associated with breast cancer. The study’s findings could guide future therapeutic strategies and clinical trials and open up potential therapeutic avenues gained by targeting these genes.
By using EAML, researchers can analyze functional impacts of non-synonymous coding variants to estimate their deleterious effect on biological processes using the evolutionary action score, and potentially provide an efficient means of identifying genes involved in sex-specific differences in Alzheimer’s. The authors suggest that this breakthrough could pave the way for sex-specific analyses in future disease-gene association studies, enabling personalized treatments tailored to each individual’s genetic makeup.
