초록 열기/닫기 버튼

The drug discovery and optimization of candidate compounds are key initial stages in drug development. Predicting the affinity between drugs and proteins, known as drug-target binding affinity (DTA), is a significant problem in the fields of biochemistry, structural biology, and artificial intelligence. In this study, we propose the utilization of ensemble learning with convolutional neural networks (CNNs) using quadratic programming (QP) to improve prediction accuracy. Additionally, we suggest incorporating self-supervised and semi-supervised learning with data augmentation. Experimental results using the Davis dataset demonstrated that the proposed self-supervised learning model outperformed other learning methods in predicting DTA across all four metrics, including mean squared error (MSE).