Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.
Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.
复制标题
DOI：
10.1371/journal.pcbi.1006076
复制
发表时间：
2018-04
影响因子：
4.3
通讯作者：
Garmire LX
中科院分区：
文献类型：
--
作者：
Ching T;Zhu X;Garmire LX
人工神经网络（ANN）是一种由许多简单的神经计算元件互连而成的计算体系结构，已应用于成像分析和诊断等生物医学领域。我们已经开发了一个新的人工神经网络框架，称为Cox-nnet，从高通量转录组学数据预测患者预后。在10个TCGA RNA-Seq数据集中，Cox-nnet实现了与其他方法相同或更好的预测准确性，包括Cox比例风险回归（LASSO，岭和mimimax凹罚），随机森林生存和CoxBoost。Cox-nnet还揭示了更丰富的生物学信息，在途径和基因水平。隐藏层节点的输出为生存敏感降维提供了另一种方法。总之，我们已经开发出一种新的方法，用于高通量数据的准确和有效的预后预测，具有功能生物学的见解。源代码可以在https://github.com/lanagarmire/cox-nnet上免费获得。越来越多的应用高通量转录组学数据来预测患者预后需要现代计算方法。随着人工神经网络的重新流行，我们提出了一个改进的神经网络模型是否可以用于预测患者的生存，作为传统方法的替代方法，如考克斯比例风险（Cox-PH）方法与LASSO或岭惩罚。为此，我们开发了一个神经网络扩展的考克斯回归模型，称为Cox-nnet。它被优化用于从高通量基因表达数据进行生存预测，具有与其他常规方法相当或更好的性能。更重要的是，Cox-nnet通过分析Cox-nnet中隐藏层节点所表示的特征，在通路和基因水平上揭示了更丰富的生物信息。此外，我们建议使用隐藏节点的功能作为一种新的方法，在生存数据分析降维。
Artificial neural networks (ANN) are computing architectures with many interconnections of simple neural-inspired computing elements, and have been applied to biomedical fields such as imaging analysis and diagnosis. We have developed a new ANN framework called Cox-nnet to predict patient prognosis from high throughput transcriptomics data. In 10 TCGA RNA-Seq data sets, Cox-nnet achieves the same or better predictive accuracy compared to other methods, including Cox-proportional hazards regression (with LASSO, ridge, and mimimax concave penalty), Random Forests Survival and CoxBoost. Cox-nnet also reveals richer biological information, at both the pathway and gene levels. The outputs from the hidden layer node provide an alternative approach for survival-sensitive dimension reduction. In summary, we have developed a new method for accurate and efficient prognosis prediction on high throughput data, with functional biological insights. The source code is freely available at https://github.com/lanagarmire/cox-nnet. The increasing application of high-througput transcriptomics data to predict patient prognosis demands modern computational methods. With the re-gaining popularity of artificial neural networks, we asked if a refined neural network model could be used to predict patient survival, as an alternative to the conventional methods, such as Cox proportional hazards (Cox-PH) methods with LASSO or ridge penalization. To this end, we have developed a neural network extension of the Cox regression model, called Cox-nnet. It is optimized for survival prediction from high throughput gene expression data, with comparable or better performance than other conventional methods. More importantly, Cox-nnet reveals much richer biological information, at both the pathway and gene levels, by analyzing features represented in the hidden layer nodes in Cox-nnet. Additionally, we propose to use hidden node features as a new approach for dimension reduction during survival data analysis.
登录
查看更多内容
DOI：
10.1214/10-aoas388
发表时间：
2011-01-01
期刊：
The annals of applied statistics
影响因子：
--
作者：
Breheny P;Huang J
通讯作者：
Huang J
影响因子：
12.3
作者：
Huang S;Chong N;Lewis NE;Jia W;Xie G;Garmire LX
通讯作者：
Garmire LX
影响因子：
1.7
作者：
Koziol, James A.;Jia, Zhenyu
通讯作者：
Jia, Zhenyu
影响因子：
2
作者：
FARAGGI, D;SIMON, R
通讯作者：
SIMON, R
影响因子：
4.7
作者：
Cork, Sarah M.;Van Meir, Erwin G.
通讯作者：
Van Meir, Erwin G.