Title
Age Prediction by DNA Methylation in Neural Networks
Document Type
Article
Publication Date
6-2022
Abstract
Aging is traditionally thought to be caused by complex and interacting factors such as DNA methylation. The traditional formula of DNA methylation aging is based on linear models and little work has explored the effectiveness of neural networks, which can learn non-linear relationships. DNA methylation data typically consists of hundreds of thousands of feature space and a much less number of biological samples. This leads to overfitting and a poor generalization of neural networks. We propose Correlation Pre-Filtered Neural Network (CPFNN) that uses Spearman Correlation to pre-filter the input features before feeding them into neural networks. We compare CPFNN with the statistical regressions (i.e., Horvath's and Hannum's formulas), the neural networks with LASSO regularization and elastic net regularization, and the Dropout Neural Networks. CPFNN outperforms these models by at least 1 year in term of Mean Absolute Error (MAE), with a MAE of 2.7 years. We also test for association between the epigenetic age with Schizophrenia and Down Syndrome (p=0.024p=0.024 and p<0.001p
Identifier
PMID: 34048347
DOI
10.1109/TCBB.2021.3084596
Publisher
Institute of Electrical and Electronics Engineers Inc.
ISSN
15455963
Repository Citation
Li, L., Zhang, C., Liu, S., Guan, H., Zhang, Y. (2022). Age prediction by DNA methylation in neural networks. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19(3), 1393-1402. https://doi.org/10.1109/TCBB.2021.3084596
Publication Information
IEEE/ACM Transactions on Computational Biology and Bioinformatics