Several age predictors based on DNA methylation, dubbed epigenetic clocks, have been created in recent years, with the vast majority based on regularized linear regression. This study explores the improvement in the performance and interpretation of epigenetic clocks using deep learning. First, we gathered 142 publicly available data sets from several human tissues to develop AltumAge, a neural network framework that is a highly accurate and precise age predictor. Compared to ElasticNet, AltumAge performs better for within-data set and cross-data set age prediction, being particularly more generalizable in older ages and new tissue types. We then used deep learning interpretation methods to learn which methylation sites contributed to the final model predictions. We observe that while most important CpG sites are linearly related to age, some highly-interacting CpG sites can influence the relevance of such relationships. Using chromatin annotations, we show that the CpG sites with the highest contribution to the model predictions were related to gene regulatory regions in the genome, including proximity to CTCF binding sites. We also found age-related KEGG pathways for genes containing these CpG sites. Lastly, we performed downstream analyses of AltumAge to explore its applicability and compare its age acceleration with Horvath’s 2013 model. We show that our neural network approach predicts higher age acceleration for tumors, for cells that exhibit age-related changes in vitro, such as immune and mitochondrial dysfunction, and for samples from patients with multiple sclerosis, type 2 diabetes, and HIV, among other conditions. Altogether, our neural network approach provides significant improvement and flexibility compared to current epigenetic clocks for both performance and model interpretability.

近年来已经创建了几种基于 DNA 甲基化的年龄预测因子，称为表观遗传时钟，其中绝大多数基于正则化线性回归。本研究探讨了使用深度学习改进表观遗传时钟的性能和解释。首先，我们从几个人体组织中收集了 142 个公开可用的数据集来开发 AltumAge，这是一个高度准确和精确的年龄预测器的神经网络框架。与 ElasticNet 相比，AltumAge 在数据集内和跨数据集的年龄预测方面表现更好，尤其适用于老年人和新组织类型。然后，我们使用深度学习解释方法来了解哪些甲基化位点有助于最终模型预测。我们观察到，虽然最重要的 CpG 位点与年龄呈线性关系，但 一些高度交互的 CpG 站点会影响这种关系的相关性。使用染色质注释，我们表明对模型预测贡献最大的 CpG 位点与基因组中的基因调控区域有关，包括与 CTCF 结合位点的接近程度。我们还发现了包含这些 CpG 位点的基因与年龄相关的 KEGG 通路。最后，我们对 AltumAge 进行了下游分析，以探索其适用性，并将其年龄加速与 Horvath 的 2013 模型进行比较。我们表明，我们的神经网络方法可以预测肿瘤、在体外表现出与年龄相关的变化（例如免疫和线粒体功能障碍）的细胞以及来自多发性硬化症、2 型糖尿病和 HIV 等患者的样本的更高年龄加速。条件。共，