A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Pan Wang; Guiyang Zhang; Zu-Guo Yu; Guohua Huang

doi:10.3389/fgene.2021.752732

A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Front Genet. 2021 Oct 26:12:752732. doi: 10.3389/fgene.2021.752732. eCollection 2021.

Authors

Pan Wang¹, Guiyang Zhang¹, Zu-Guo Yu², Guohua Huang¹

Affiliations

¹ School of Electrical Engineering, Shaoyang University, Shaoyang, China.
² Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering, Xiangtan University, Xiangtan, China.

Abstract

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.

Keywords: deep learning; extreme gradient boosting; machine learning; protein functions; protein-protein interaction.