Multi-task deep autoencoder to predict Alzheimer's disease progression using temporal DNA methylation data in peripheral blood.
Multi-task deep autoencoder to predict Alzheimer's disease progression using temporal DNA methylation data in peripheral blood.
复制标题
DOI：
10.1016/j.csbj.2022.10.016
复制
发表时间：
2022
影响因子：
6
通讯作者：
Zhao, Fengdi
中科院分区：
文献类型：
--
作者：
Chen, Li;Saykin, Andrew J.;Yao, Bing;Zhao, Fengdi
诊断阿尔茨海默病（AD）的传统方法，如脑成像和脑脊液是侵入性的和昂贵的。由于生物标志物具有非侵入性和易于获取的特性，因此希望通过利用从外周组织获得的生物标志物开发有用的诊断工具。然而，使用外周血中的DNA甲基化数据预测AD进展的能力很少为人所知。在纵向研究中，考虑复杂和高维的DNA甲基化数据，开发有效的预测模型也是具有挑战性的。在这里，我们开发了两个多任务深度自动编码器，它们基于卷积自动编码器和长短期记忆自动编码器，通过联合最小化重构误差和最大化预测精度来学习压缩特征表示。通过对从阿尔茨海默病神经成像计划中收集的外周血纵向DNA甲基化数据进行基准测试，我们证明了所提出的多任务深度自动编码器在预测AD进展和重建时间DNA甲基化谱方面优于最先进的机器学习方法。此外，所提出的多任务深度自动编码器可以仅使用历史DNA甲基化数据准确地预测AD进展，并且通过包括所有时间DNA甲基化数据来进一步提高性能。可用性：：https://github.com/lichen-lab/MTAE.
Traditional approaches for diagnosing Alzheimer’s disease (AD) such as brain imaging and cerebrospinal fluid are invasive and expensive. It is desirable to develop a useful diagnostic tool by exploiting biomarkers obtained from peripheral tissues due to their noninvasive and easily accessible characteristics. However, the capacity of using DNA methylation data in peripheral blood for predicting AD progression is rarely known. It is also challenging to develop an efficient prediction model considering the complex and high-dimensional DNA methylation data in a longitudinal study. Here, we develop two multi-task deep autoencoders, which are based on the convolutional autoencoder and long short-term memory autoencoder to learn the compressed feature representation by jointly minimizing the reconstruction error and maximizing the prediction accuracy. By benchmarking on longitudinal DNA methylation data collected from the peripheral blood in Alzheimer’s Disease Neuroimaging Initiative, we demonstrate that the proposed multi-task deep autoencoders outperform state-of-the-art machine learning approaches for both predicting AD progression and reconstructing the temporal DNA methylation profiles. In addition, the proposed multi-task deep autoencoders can predict AD progression accurately using only the historical DNA methylation data and the performance is further improved by including all temporal DNA methylation data. Availability:: https://github.com/lichen-lab/MTAE.
登录
查看更多内容
影响因子：
3
作者：
Sanchez-Mut JV;Gräff J
通讯作者：
Gräff J
影响因子：
3.7
作者：
Bahado-Singh RO;Vishweswaraiah S;Aydas B;Yilmaz A;Metpally RP;Carey DJ;Crist RC;Berrettini WH;Wilson GD;Imam K;Maddens M;Bisgin H;Graham SF;Radhakrishna U
通讯作者：
Radhakrishna U
影响因子：
4.6
作者：
Lee, Garam;Nho, Kwangsik;Fargher, Kristin
通讯作者：
Fargher, Kristin
DOI：
10.1016/j.compmedimag.2019.01.005
发表时间：
2019-04-01
影响因子：
5.7
作者：
Cui, Ruoxuan;Liu, Manhua
通讯作者：
Liu, Manhua
影响因子：
5.7
作者：
Li QS;Vasanthakumar A;Davis JW;Idler KB;Nho K;Waring JF;Saykin AJ;Alzheimer’s Disease Neuroimaging Initiative (ADNI)
通讯作者：
Alzheimer’s Disease Neuroimaging Initiative (ADNI)