KRN-DTI: Towards accurate drug-target interaction prediction with Kolmogorov-Arnold and residual networks

Abstract

Predicting drug-target interactions (DTIs) accurately is essential in the field of drug discovery. Recently, artificial intelligence (AI) technologies, especially graph convolutional networks (GCNs), have been developed to tackle this challenge. However, as the number of GCN layers increases, models may lose critical information due to excessive smoothing. Moreover, these methods often lack interpretability and are dependent on specific datasets, which limits their generalizability. Consequently, this study introduces a novel method, KRN-DTI, which employs interpretable GCN technology to predict DTIs based on a drug-target heterogeneous network. The method uses GCN technology to identify potential DTIs by leveraging known interactions and dynamically adjusting the weights, thereby enhancing the model's interpretability. Additionally, residual connection technology is employed to integrate GNN outputs, mitigating the over-smoothing issue. Furthermore, the model's interpretability is enhanced by adaptively adjusting weights using Kolmogorov–Arnold Networks (KAN) and attention mechanisms. Experimental results show that KRN-DTI outperforms several advanced computational methods on the benchmark dataset. Case studies further highlight the effectiveness of KRN-DTI in predicting potential DTIs, showcasing its potential for real-world applications in drug discovery. Our code and data are publicly accessible at: https://github.com/lizhen5000/KRN-DTI.git.