Improving the Classification of Alzheimer's Disease Using Hybrid Gene Selection Pipeline and Deep Learning.

Improving the Classification of Alzheimer's Disease Using Hybrid Gene Selection Pipeline and Deep Learning.
复制标题

DOI:
10.3389/fgene.2021.784814
复制
发表时间:
2021
影响因子:
3.7
通讯作者:
Chang CY
Chang CY
中科院分区:
生物学3区
文献类型:
--
作者:
Mahendran N;Vincent PMDR;Srinivasan K;Chang CY

文献摘要

参考文献

被引文献

相似文献

阿尔茨海默氏症是一种进行性、不可逆转的神经退行性脑部疾病。即使症状很明显,也需要数年时间才能注意到、解码和揭示阿尔茨海默病。然而,成像技术等技术的进步有助于早期诊断。尽管如此,有时结果还是不准确,从而延误了治疗。因此,近年来的研究重点是鉴定区分基因型和表型特征的分子生物标志物。然而,基因表达数据集生成的特征非常庞大,有 1,000 个甚至超过 10,000 个。为了克服这种维数灾难,引入了特征选择技术。我们设计了一个基因选择管道,结合了过滤器、包装器和无监督方法来选择相关基因。我们结合了最小冗余和最大相关性(mRmR)、基于包装的粒子群优化(WPSO)和自动编码器来选择相关特征。我们使用了基因表达综合库中的 GSE5281 阿尔茨海默病数据集。在选择相关基因后,我们实施了一个改进的深度信念网络 (IDBN),其具有简单的停止标准。我们使用贝叶斯优化技术来调整改进的深度置信网络中的超参数。表格结果表明,拟议的管道显示出有希望的结果。
Alzheimer’s is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer’s. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate, which delays the treatment. Thus, the research in recent times focused on identifying the molecular biomarkers that differentiate the genotype and phenotype characteristics. However, the gene expression dataset’s generated features are huge, 1,000 or even more than 10,000. To overcome such a curse of dimensionality, feature selection techniques are introduced. We designed a gene selection pipeline combining a filter, wrapper, and unsupervised method to select the relevant genes. We combined the minimum Redundancy and maximum Relevance (mRmR), Wrapper-based Particle Swarm Optimization (WPSO), and Auto encoder to select the relevant features. We used the GSE5281 Alzheimer’s dataset from the Gene Expression Omnibus We implemented an Improved Deep Belief Network (IDBN) with simple stopping criteria after choosing the relevant genes. We used a Bayesian Optimization technique to tune the hyperparameters in the Improved Deep Belief Network. The tabulated results show that the proposed pipeline shows promising results.
DOI: 10.3233/jad-170490
发表时间: 2018
期刊: Journal of Alzheimer's disease : JAD
影响因子: --
作者:
Huber CM;Yee C;May T;Dhanala A;Mitchell CS
通讯作者: Mitchell CS
DOI: 10.1007/s10278-019-00265-5
发表时间: 2020-07-29
影响因子: 4.4
作者:
Bin Tufail, Ahsan;Ma, Yong-Kui;Zhang, Qiu-Na
通讯作者: Zhang, Qiu-Na
DOI: 10.1007/s10115-010-0288-x
发表时间: 2011-03-01
影响因子: 2.7
作者:
El Akadi, Ali;Amine, Aouatif;Aboutajdine, Driss
通讯作者: Aboutajdine, Driss
DOI: 10.1186/s12883-017-1010-3
发表时间: 2018-01-10
期刊: BMC neurology
影响因子: 2.6
作者:
Huang X;Liu H;Li X;Guan L;Li J;Tellier LCAM;Yang H;Wang J;Zhang J
通讯作者: Zhang J
DOI: 10.2174/1381612824666180607124038
发表时间: 2018
影响因子: 3.1
作者:
Carpenter KA;Huang X
通讯作者: Huang X