Decoding Alzheimer’s Disease Genomes With Deep Learning

This research aims to unravel the genetic and molecular mechanisms of Alzheimer’s disease using machine learning that predicts the impact of genetic mutations on biological functions.

Dr. Naito’s research aims to unravel the genetic complexities of Alzheimer’s disease. This project has two primary objectives: to develop a pipeline to predict the impact of genetic mutations on RNA processing in brain cells by state-of-the-art machine-learning technologies and to investigate how genetic mutations have an impact on individuals with Alzheimer’s via RNA processing by applying this pipeline to huge genomic data. A better understanding of genetic associations of Alzheimer’s will help in developing new treatments and identifying biomarkers.

This research introduces several innovative aspects to the study of Alzheimer’s disease and beyond. We will develop a computational pipeline to characterize genetic mutations with our novel prediction score tailored for brain cell types. This approach allows for a nuanced understanding of the functional impact of genetic variants associated with the pathogenesis of Alzheimer’s disease, leveraging unprecedentedly large-scale whole-genome sequencing data. Furthermore, our method to predict a variant’s effect in brain cell types is directly applicable to studies of other neurological diseases.

Once our study is complete, we will gain a deeper understanding of Alzheimer’s disease pathogenesis from a genetic perspective. This will aid in identifying key molecules associated with Alzheimer’s disease, leading to the development of novel therapeutics and biomarkers. In our research field, our developed pipeline will contribute to elucidating genetic mechanisms not only of Alzheimer’s disease but also of other relevant neurological diseases.