当前位置: X-MOL 学术Evol. Bioinf. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Predicting Self-Interacting Proteins Using a Recurrent Neural Network and Protein Evolutionary Information
Evolutionary Bioinformatics ( IF 1.7 ) Pub Date : 2020-05-28 , DOI: 10.1177/1176934320924674
Ji-Yong An 1 , Yong Zhou 1 , Zi-Ji Yan 1 , Yu-Jun Zhao 1
Affiliation  

Self-interacting proteins (SIPs) play crucial roles in biological activities of organisms. Many high-throughput methods can be used to identify SIPs. However, these methods are both time-consuming and expensive. How to develop effective computational approaches for identifying SIPs is a challenging task. In the article, we present a novel computational method called RRN-SIFT, which combines the recurrent neural network (RNN) with scale invariant feature transform (SIFT) to predict SIPs based on protein evolutionary information. The main advantage of the proposed RNN-SIFT model is that it uses SIFT for extracting key feature by exploring the evolutionary information embedded in Position-Specific Iterated BLAST–constructed position-specific scoring matrix and employs an RNN classifier to perform classification based on extracted features. Extensive experiments show that the RRN-SIFT obtained average accuracy of 94.34% and 97.12% on the yeast and human dataset, respectively. We also compared our performance with the back propagation neural network (BPNN), the state-of-the-art support vector machine (SVM), and other existing methods. By comparing with experimental results, the performance of RNN-SIFT is significantly better than that of the BPNN, SVM, and other previous methods in the domain. Therefore, we conclude that the proposed RNN-SIFT model is a useful tool for predicting SIPs, as well to solve other bioinformatics tasks. To facilitate widely studies and encourage future proteomics research, a freely available web server called RNN-SIFT-SIPs was developed at http://219.219.62.123:8888/RNNSIFT/ including the source code and the SIP datasets.



中文翻译:

使用递归神经网络和蛋白质进化信息预测自我相互作用的蛋白质

自相互作用蛋白(SIP)在生物体的生物活性中起着至关重要的作用。许多高通量方法可用于识别SIP。但是,这些方法既费时又昂贵。如何开发有效的计算方法来识别SIP是一项艰巨的任务。在本文中,我们提出了一种称为RRN-SIFT的新型计算方法,该方法将递归神经网络(RNN)与尺度不变特征变换(SIFT)结合起来,可以基于蛋白质进化信息预测SIP。提出的RNN-SIFT模型的主要优点是,它利用SIFT通过探索嵌入在特定于位置的迭代BLAST构造的特定位置评分矩阵中的进化信息来提取关键特征,并使用RNN分类器基于提取的特征进行分类。酵母人类数据集。我们还将性能与反向传播神经网络(BPNN),最新的支持向量机(SVM)和其他现有方法进行了比较。通过与实验结果进行比较,RNN-SIFT的性能明显优于该领域的BPNN,SVM和其他先前方法。因此,我们得出的结论是,提出的RNN-SIFT模型是预测SIP的有用工具,也可以解决其他生物信息学任务。为了促进广泛的研究并鼓励未来的蛋白质组学研究,在http://219.219.62.123:8888/RNNSIFT/上开发了可免费获得的名为RNN-SIFT-SIP的Web服务器,其中包括源代码和SIP数据集。

更新日期:2020-06-30
down
wechat
bug