Latent-space embedding of expression data identifies gene signatures from sputum samples of asthmatic patients.

Latent-space embedding of expression data identifies gene signatures from sputum samples of asthmatic patients.
复制标题

DOI:
10.1186/s12859-020-03785-y
复制
发表时间:
2020-10-15
期刊:
影响因子:
3
通讯作者:
Gerstein M
Gerstein M
中科院分区:
生物学4区
文献类型:
--
作者:
Lou S;Li T;Spakowicz D;Yan X;Chupp GL;Gerstein M

文献摘要

参考文献

被引文献

相似文献

哮喘的发病机制是一个涉及多基因、多途径的复杂过程。从哮喘数据集中识别生物标记物,特别是那些包括不同亚群的生物标记物,是具有挑战性的。潜在地,自动编码器为这样的任务提供了理想的框架,因为它们可以以无监督的方式将复杂的、噪声的高维基因表达数据嵌入到低维潜在空间中,使我们能够从表达数据中提取区分特征。在这里,我们开发了一个框架,结合去噪自动编码器和监督学习分类器来识别与哮喘严重程度相关的基因特征。使用具有50个隐藏单元的训练自动编码器,我们发现低维嵌入上的层次聚类与先前定义的和临床相关的患者聚类很好地对应。此外,每个隐藏的单位都有来自每个基因的贡献,对这些贡献的路径分析表明,隐藏的单位在已知的哮喘相关途径中显著丰富。然后,我们使用对隐藏单位贡献最大的基因来开发一个二级随机森林分类器,用于直接预测哮喘的严重程度。来自该分类器的特征重要性度量基于与严重性相关的50个关键基因来识别特征。此外,通过支持向量机回归,我们可以使用这些关键基因成功地估计患者的FEV1/FVC比率。我们发现,去噪自动编码器框架可以从哮喘患者的基因表达中提取与功能基因组和患者集群相对应的有意义的模式。
The pathogenesis of asthma is a complex process involving multiple genes and pathways. Identifying biomarkers from asthma datasets, especially those that include heterogeneous subpopulations, is challenging. Potentially, autoencoders provide ideal frameworks for such tasks as they can embed complex, noisy high-dimensional gene expression data into a low-dimensional latent space in an unsupervised fashion, enabling us to extract distinguishing features from expression data. Here, we developed a framework combining a denoising autoencoder and a supervised learning classifier to identify gene signatures related to asthma severity. Using the trained autoencoder with 50 hidden units, we found that hierarchical clustering on the low-dimensional embedding corresponds well with previously defined and clinically relevant clusters of patients. Moreover, each hidden unit has contributions from each of the genes, and pathway analysis of these contributions shows that the hidden units are significantly enriched in known asthma-related pathways. We then used genes that contribute most to the hidden units to develop a secondary random-forest classifier for directly predicting asthma severity. The feature importance metric from this classifier identified a signature based on 50 key genes, which are associated with severity. Furthermore, we can use these key genes to successfully estimate FEV1/FVC ratios across patients, via support-vector-machine regression. We found that the denoising autoencoder framework can extract meaningful patterns corresponding to functional gene groups and patient clusters from the gene expression of asthma patients.
DOI: 10.1093/nar/gkv007
发表时间: 2015-04-20
影响因子: 14.9
作者:
Ritchie ME;Phipson B;Wu D;Hu Y;Law CW;Shi W;Smyth GK
通讯作者: Smyth GK
DOI: 10.1111/j.1440-1843.2006.00784.x
发表时间: 2006-01-01
期刊: RESPIROLOGY
影响因子: 6.9
作者:
Simpson, JL;Scott, R;Gibson, PG
通讯作者: Gibson, PG
DOI: 10.1513/annalsats.201703-259oc
发表时间: 2018-03-01
影响因子: 8.3
作者:
Nurmagambetov, Tursynbek;Kuwahara, Robin;Garbe, Paul
通讯作者: Garbe, Paul
DOI: 10.1164/rccm.201408-1440oc
发表时间: 2015-05-15
影响因子: 24.7
作者:
Yan, Xiting;Chu, Jen-Hwa;Chupp, Geoffrey L.
通讯作者: Chupp, Geoffrey L.
基于距离相关性从基因表达数据中推断出非线性基因调节网络。
DOI: 10.1371/journal.pone.0087446
发表时间: 2014
期刊: PloS one
影响因子: 3.7
作者:
Guo X;Zhang Y;Hu W;Tan H;Wang X
通讯作者: Wang X