Feature Integration and Feature Augmentation for Predicting GPCR-Drug Interaction

Abstract

Accurately predicting the interaction between G-protein-coupled receptors (GPCR) and drugs is of great significance for understanding protein functions and drug discovery and has become a hot spot in current research. To improve the accuracy of GPCR-drug interaction prediction, this paper proposes a new GPCR-Drug interaction prediction method based on multi-feature integration and feature augmentation from deep random forest: First, the sequence features of GPCR from amino acid composition and protein evolution are extracted respectively, and the characteristics of the drug molecule from the molecular fingerprint perspective are formulated; then, the extracted multiple features are combined to obtain the feature representation of the GPCR-Drug pair; finally, based on the proposed GPCR-Drug feature representation method, we use deep random forest to generate augmented features and construct cascaded predictions model. The cross-validation and independent test results on the standard data set verify the effectiveness and greater explainability of the proposed method.