Using a stacked ensemble learning framework to predict modulators of protein-protein interactions

Mengyao Gao, Lingling Zhao, Zitong Zhang, Junjie Wang, Chunyu Wang

Abstract: Highlights•SELPPI is the first stacked model to predict protein–protein interactions modulators.•SELPPI improves the accuracy for PPIM prediction and outperforms all existing models.•SELPPI makes full use of 6 tree-based ML models and 7 groups of descriptor features.•Ensemble learning and optimal features play significant roles in enhancing efficiency.