DM-RPIs: Predicting ncRNA-protein interactions using stacked ensembling strategy. (December 2019)

• Record Type: Journal Article
• Authors: Cheng, Shuping; Zhang, Lu; Tan, Jianjun; Gong, Weikang; Li, Chunhua; Zhang, Xiaoyi
• Is Part Of: Computational biology and chemistry. Volume 83(2019)
• Publication Date: 2019-12
• Subjects: ncRNA-protein interactions -- Deep Stacking Auto-encoders Networks (DSANs) -- Support Vector Machine (SVM) -- Random Forest (RF) -- Convolution Neural Network (CNN) -- Stacked integrate; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2019.107088
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: We proposed a computational method, DM-RPIs (Deep Mining RNA-Protein Interactions), to identify ncRNA-protein interactions. The method used the Deep Stacking Autoencoders Networks (DSANs) model to preproccess the raw data firstly, then three mainstream learning algorithms of Support Vector Machine (SVM), Random Forest (RF) and Convolution Neural Network (CNN), were trained as three individual predictors. At last the three individual predictors were stacked integrated together. DM-RPIs performed well for predicting ncRNA-protein interactions with an accuracy of 0.851, precision of 0.852, sensitivity of 0.873, specificity of 0.826 and MCC of 0.701 on RPI2241 dataset, respectively. Abstract: ncRNA-protein interactions (ncRPIs) play an important role in a number of cellular processes, such as post-transcriptional modification, transcriptional regulation, disease progression and development. Since experimental methods are expensive and time-consuming to identify the ncRPIs, we proposed a computational method, Deep Mining ncRNA-Protein Interactions (DM-RPIs), for identifying the ncRPIs. In order to descending dimension and excavating hidden information from k-mer frequency of RNA and protein sequences, using the Deep Stacking Auto-encoders Networks (DSANs) model refined the raw data. Three common machine learning algorithms, Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN), were separately trained as individual predictors and then the three individual predictors were integrated together using stacked ensembling strategy. Based on the RPI2241 dataset, DM-RPI obtains an accuracy of 0.851, precision of 0.852, sensitivity of 0.873, specificity of 0.826, and MCC of 0.701, which is promising and pioneering for the prediction of ncRPIs.