Prediction of LncRNA-Protein Interactions Based on Multi-kernel Fusion and Graph Auto-Encoders.

With the increasing amount of recognized lncRNAs, people are paying much more attention than before mining their potential function of them, which performs biological functions by interacting with proteins. However, facing the huge amount of biological data, it is obvious that biological experiments only in vitro and in vivo are time-consuming and insufficient. To this end, this study proposed a framework for LncRNA-Protein Interactions prediction based on Multi-kernel fusion and Graph Auto-Encoders (LPI-MGAE). First, three feature kernels should be constructed in lncRNA and protein space, respectively. Secondly, three feature kernels are fused separately using the average weighted strategy. Then, the embedding of the feature kernels can be extracted with a graph auto-encoder consisting of two-layer graph convolutional networks. Finally, a regularized least squares classifier can be used to derive the final prediction results. 5-fold cross-validation shows that LPI-MGAE obtains successful outcomes on both Dataset1 and Dataset2, with an AUPR of 19.37%–34.67% higher on Dataset1 compared to the baseline methods. Simultaneously, LPI-MGAE also has achieved 0.1%–15.76% higher AUC and 16.54%–63.55% higher AUPR on Dataset2.