ABSTRACT
Recent research efforts have shown compelling evidence of DNA methylation alterations in aging and age-related disease. The traditional formula of DNA methylation aging suffers from multiple hypothesis testing due to the interacting, high dimensional, and non-linear nature of the data. Neural network analyses have shown effectiveness on biological age prediction for its ability in learning interacting and nonlinear relationships. However, the high dimensionality of DNA methylation data often results in overfitting and poor generalization in neural networks. To solve this problem, we developed a neural network model that selects input features based on their correlations with biological age. We compared it with the traditional statistical regressions and other dimension reduction models in neural networks, such as neural networks with LASSO and elastic net regularizations and the dropout neural networks. The results showed that our model decreased the age prediction error to 2.7 years, outperforming all other models. In addition, we studied age acceleration in two age-related diseases (Down Syndrome and Schizophrenia). Our model is able to confirm age acceleration in Down Syndrome with a much smaller variance comparing to existing studies and find extrinsic epigenetic age acceleration (EEAA) in Schizophrenia, which is a weak pattern that other models couldn't detect. Our research is one of the first to adapt neural network algorithms in biological aging prediction. It can be applied to a wide range of high-dimensional biomarker data, and ultimately improve understanding of the aging process and benefit public health.
- Horvath, S. (2012) DNA methylation age of human tissues and cell types, Genome Biology, 14.Google Scholar
- Hannum, G., et al. (2012) Genome-wide methylation profiles reveal quantitative views of human aging rates, molecular cell, 49.Google Scholar
- Levine, E.M, et al. (2018) An epigenetic biomarker of aging for lifespan and health span, Aging, 10.Google Scholar
- Aliferi, A., et al. (2018) DNA methylation-based age prediction using massively parallel sequencing data and multiple machine learning models, Forensic Science International: Genetics, 37.Google ScholarCross Ref
Index Terms
- The genetics of human aging: predicting age and age-related diseases by deep mining high dimensional biomarker data
Recommendations
Structure and expression of dna methyltransferase genes from apomictic and sexual Boechera species
Display Omitted The structure of the DNMTs genes in apomict and sexual Boechera species are highly similar to A. thaliana orthologs.While the expression levels of MET1 and CMT3 do not differ much, DRM2 upregulated in developing seeds of apomictic ...
Prediction of methylation status on DNA sequences and identification of its important DNA sequence features
BEBI'08: Proceedings of the 1st WSEAS international conference on Biomedical electronics and biomedical informaticsIn mammals, cytosines of most CpG dinucleotides in their genomes except gene promoters are subject to modification by methyl group (methylation). A number of genes in a mammal are regulated developmental-specifically or tissue-specifically by the ...
Genome-wide DNA-binding specificity of PIL5, an Arabidopsis basic Helix-Loop-Helix (bHLH) transcription factor
PIL5 is a member of the basic Helix-Loop-Helix (bHLH) transcription factor superfamily. We previously showed that PIL5 binds to the G-box (CACGTG) motif with high affinity. However, since there are many randomly matched G-box motifs throughout the ...
Comments