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.

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。酵母和人类数据集。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。