Predicting lncRNA-protein interactions through deep learning framework employing multiple features and random forest algorithm

Abstract

RNA-protein interaction (RPI) is crucial to the life processes of diverse organisms. Various researchers have identified RPI through long-term and high-cost biological experiments. Although numerous machine learning and deep learning-based methods for predicting RPI currently exist, their robustness and generalizability have significant room for improvement. This study proposes LPI-MFF, an RPI prediction model based on multi-source information fusion, to address these issues. The LPI-MFF employed protein-protein interactions features, sequence features, secondary structure features, and physical and chemical properties as the information sources with the corresponding coding scheme, followed by the random forest algorithm for feature screening. Finally, all information was combined and a classification method based on convolutional neural networks is used. The experimental results of fivefold cross-validation demonstrated that the accuracy of LPI-MFF on RPI1807 and NPInter was 97.60% and 97.67%, respectively. In addition, the accuracy rate on the independent test set RPI1168 was 84.9%, and the accuracy rate on the Mus musculus dataset was 90.91%. Accordingly, LPI-MFF demonstrated greater robustness and generalization than other prevalent RPI prediction methods.

Keywords: Features fusion; LncRNA–protein interactions; Multiple features; Random forest algorithm.

Fig. 1

The flowchart of LPI-MFF

Fig. 2

The ROC curve of different feature combinations on RPI1807

Fig. 3

The ROC curve of different feature combinations on RPI1807

Fig. 4

The ROC curves with different feature selection algorithms on RPI1807, and the PR curves with different feature selection algorithms on RPI1807

Fig. 5

LIME analysis of LPI-MFF

Fig. 6

SHAP analysis of LPI-MFF

Fig. 7

Prediction of RPI in Mus musculus dataset by LPI-MFF