Drug repositioning based on residual attention network and free multiscale adversarial training

• Published in: BMC bioinformatics Vol. 25; no. 1; pp. 261 - 21
• Main Authors: Li, Guanghui, Li, Shuwen, Liang, Cheng, Xiao, Qiu, Luo, Jiawei
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 08.08.2024; BioMed Central; BMC
• Subjects: Adversarial training; Algorithms; Collaboration; Computational Biology - methods; Cost analysis; Deep learning; Disease; Drug development; Drug discovery; Drug Repositioning - methods; Drug-disease association; Drugs; Graph attention network; Graph autoencoder; Humans; Information processing; Machine learning; Methods; MicroRNAs; Multilayers; Neighborhoods; Networks; Neural networks; Neural Networks, Computer; Nodes; Pathogenesis; Pharmaceutical research; Predictions; Proteins; Residual network; Semantics; Technology application; Training; China; Graph autoencoder; Adversarial training; Graph attention network; Residual network; Drug-disease association
• DOI: 10.1186/s12859-024-05893-5
• ISSN: 1471-2105

Conducting traditional wet experiments to guide drug development is an expensive, time-consuming and risky process. Analyzing drug function and repositioning plays a key role in identifying new therapeutic potential of approved drugs and discovering therapeutic approaches for untreated diseases. Exploring drug-disease associations has far-reaching implications for identifying disease pathogenesis and treatment. However, reliable detection of drug-disease relationships via traditional methods is costly and slow. Therefore, investigations into computational methods for predicting drug-disease associations are currently needed. This paper presents a novel drug-disease association prediction method, RAFGAE. First, RAFGAE integrates known associations between diseases and drugs into a bipartite network. Second, RAFGAE designs the Re_GAT framework, which includes multilayer graph attention networks (GATs) and two residual networks. The multilayer GATs are utilized for learning the node embeddings, which is achieved by aggregating information from multihop neighbors. The two residual networks are used to alleviate the deep network oversmoothing problem, and an attention mechanism is introduced to combine the node embeddings from different attention layers. Third, two graph autoencoders (GAEs) with collaborative training are constructed to simulate label propagation to predict potential associations. On this basis, free multiscale adversarial training (FMAT) is introduced. FMAT enhances node feature quality through small gradient adversarial perturbation iterations, improving the prediction performance. Finally, tenfold cross-validations on two benchmark datasets show that RAFGAE outperforms current methods. In addition, case studies have confirmed that RAFGAE can detect novel drug-disease associations. The comprehensive experimental results validate the utility and accuracy of RAFGAE. We believe that this method may serve as an excellent predictor for identifying unobserved disease-drug associations.