SSLDTI: A novel method for drug-target interaction prediction based on self-supervised learning

Zhixian Liu, Qingfeng Chen, Wei Lan, Huihui Lu, Shichao Zhang

Abstract: Highlights•We propose a novel drug-target interaction prediction method, which improves prediction accuracy.•It uses contrastive learning and self-prediction to extract local and global features from sparse heterogeneous graph.•It introduces a positive sample compensation coefficient to the objective function to reduce the impact of class imbalance.