College of Computer Science and Technology, Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China.
Int J Mol Sci. 2019 Mar 1;20(5):1070. doi: 10.3390/ijms20051070.
Non-coding RNAs (ncRNAs) play crucial roles in multiple fundamental biological processes, such as post-transcriptional gene regulation, and are implicated in many complex human diseases. Mostly ncRNAs function by interacting with corresponding RNA-binding proteins. The research on ncRNA⁻protein interaction is the key to understanding the function of ncRNA. However, the biological experiment techniques for identifying RNA⁻protein interactions (RPIs) are currently still expensive and time-consuming. Due to the complex molecular mechanism of ncRNA⁻protein interaction and the lack of conservation for ncRNA, especially for long ncRNA (lncRNA), the prediction of ncRNA⁻protein interaction is still a challenge. Deep learning-based models have become the state-of-the-art in a range of biological sequence analysis problems due to their strong power of feature learning. In this study, we proposed a hierarchical deep learning framework RPITER to predict RNA⁻protein interaction. For sequence coding, we improved the conjoint triad feature (CTF) coding method by complementing more primary sequence information and adding sequence structure information. For model design, RPITER employed two basic neural network architectures of convolution neural network (CNN) and stacked auto-encoder (SAE). Comprehensive experiments were performed on five benchmark datasets from PDB and NPInter databases to analyze and compare the performances of different sequence coding methods and prediction models. We found that CNN and SAE deep learning architectures have powerful fitting abilities for the -mer features of RNA and protein sequence. The improved CTF coding method showed performance gain compared with the original CTF method. Moreover, our designed RPITER performed well in predicting RNA⁻protein interaction (RPI) and could outperform most of the previous methods. On five widely used RPI datasets, RPI369, RPI488, RPI1807, RPI2241 and NPInter, RPITER obtained A U C of 0.821, 0.911, 0.990, 0.957 and 0.985, respectively. The proposed RPITER could be a complementary method for predicting RPI and constructing RPI network, which would help push forward the related biological research on ncRNAs and lncRNAs.
非编码 RNA（ncRNA）在多种基本生物过程中发挥着关键作用，例如转录后基因调控，并与许多复杂的人类疾病有关。大多数 ncRNA 通过与相应的 RNA 结合蛋白相互作用发挥作用。ncRNA-蛋白质相互作用的研究是理解 ncRNA 功能的关键。然而，目前用于鉴定 RNA-蛋白质相互作用（RPI）的生物学实验技术仍然昂贵且耗时。由于 ncRNA-蛋白质相互作用的复杂分子机制以及 ncRNA，特别是长 ncRNA（lncRNA）缺乏保守性，因此 ncRNA-蛋白质相互作用的预测仍然是一个挑战。基于深度学习的模型由于其强大的特征学习能力，已成为一系列生物序列分析问题的最新技术。在这项研究中，我们提出了一个层次化的深度学习框架 RPITER 来预测 RNA-蛋白质相互作用。对于序列编码，我们通过补充更多的原始序列信息并添加序列结构信息，改进了联合三联体特征（CTF）编码方法。对于模型设计，RPITER 采用卷积神经网络（CNN）和堆叠自动编码器（SAE）两种基本神经网络架构。我们在来自 PDB 和 NPInter 数据库的五个基准数据集上进行了综合实验，以分析和比较不同序列编码方法和预测模型的性能。我们发现 CNN 和 SAE 深度学习架构对 RNA 和蛋白质序列的-mer 特征具有强大的拟合能力。改进的 CTF 编码方法与原始 CTF 方法相比表现出性能提升。此外，我们设计的 RPITER 在预测 RNA-蛋白质相互作用（RPI）方面表现出色，并且可以优于大多数先前的方法。在五个广泛使用的 RPI 数据集 RPI369、RPI488、RPI1807、RPI2241 和 NPInter 上，RPITER 分别获得了 0.821、0.911、0.990、0.957 和 0.985 的 AUC。所提出的 RPITER 可以作为预测 RPI 和构建 RPI 网络的补充方法，这将有助于推动有关 ncRNA 和 lncRNA 的相关生物学研究。
