3D genome-selected microRNAs to improve Alzheimer's disease prediction

Keyi Li; Runqiu Chi; Liangjie Liu; Mofan Feng; Kai Su; Xia Li; Guang He; Yi Shi

doi:10.3389/fneur.2023.1059492

3D genome-selected microRNAs to improve Alzheimer's disease prediction

Front Neurol. 2023 Feb 13:14:1059492. doi: 10.3389/fneur.2023.1059492. eCollection 2023.

Authors

Keyi Li^{1

2}, Runqiu Chi^{1

2}, Liangjie Liu^{1

2}, Mofan Feng^{1

2}, Kai Su^{1

2}, Xia Li³, Guang He^{1

2}, Yi Shi^{1

2}

Affiliations

¹ Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Bio-X Institutes, Shanghai Jiao Tong University, Shanghai, China.
² Shanghai Key Laboratory of Psychotic Disorders, Brain Science and Technology Research Center, Shanghai Jiao Tong University, Shanghai, China.
³ Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

Abstract

Introduction: Alzheimer's disease (AD) is a type of neurodegenerative disease that has no effective treatment in its late stage, making the early prediction of AD critical. There have been an increase in the number of studies indicating that miRNAs play an important role in neurodegenerative diseases including Alzheimer's disease via epigenetic modifications including DNA methylation. Therefore, miRNAs may serve as excellent biomarkers in early AD prediction.

Methods: Considering that the non-coding RNAs' activity may be linked to their corresponding DNA loci in the 3D genome, we collected the existing AD-related miRNAs combined with 3D genomic data in this study. We investigated three machine learning models in this work under leave-one-out cross-validation (LOOCV): support vector classification (SVC), support vector regression (SVR), and knearest neighbors (KNNs).

Results: The prediction results of different models demonstrated the effectiveness of incorporating 3D genome information into the AD prediction models.

Discussion: With the assistance of the 3D genome, we were able to train more accurate models by selecting fewer but more discriminatory miRNAs, as witnessed by several ML models. These interesting findings indicate that the 3D genome has great potential to play an important role in future AD research.

Keywords: 3D genome; Alzheimer's disease; biomarkers; machine learning; microRNA.

Grants and funding

This project was supported by the Key Research and Development Plan of the Ministry of Science and Technology (2022YFE0125300), the National Key Research and Development Program (2016YFC0906400), the Innovation Funding in Shanghai (20JC1418600 and 18JC1413100), the National Natural Science Foundation of China (82071262 and 81671326), the Natural Science Foundation of Shanghai (20ZR1427200 and 20511101900), the Shanghai Municipal Science and Technology Major Project (2017SHZDZX01), the Shanghai Key Laboratory of Psychotic Disorders (13DZ2260500), the Shanghai Leading Academic Discipline Project (B205), and the Shanghai Jiao Tong University STAR Grant (YG2023ZD26, YG2022ZD024, and YG2022QN111).