Computer methods and programs in biomedicine · 2026
Multi-view semi-supervised adversarial attention network for drug repurposing.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Fan Mengmeng, He Dakuo, Liu Qian, Liu Qing, Wang Feng, Li He, Wang Hao, Shan Siqi, Zhang Jinghao, Hou Yue
Аннотация
BACKGROUND AND OBJECTIVE: Drug repositioning represents an efficient strategy for uncovering new therapeutic indications for approved drugs. However, most existing prediction methods rely on similarity data and overlook biological and chemical information. In addition, data sparsity and randomly selected negative samples further limit predictive performance.
METHODS: We propose the Multi-view Semi-Supervised Adversarial Attention Network (M-SSAAN) for drug-disease association prediction. M-SSAAN combines structural and similarity embeddings to generate multi-view representations, and employs attention mechanisms along with semi-supervised adversarial learning to alleviate data sparsity and enhance robustness.
RESULTS: The effectiveness of M-SSAAN was evaluated through comparative experiments, ablation studies, and strategy analyses. In addition, case studies on ibuprofen indications and zero-shot predictions for lung cancer further demonstrate the model's ability to identify reliable drug-disease associations.
CONCLUSION: These results highlight the strong potential of M-SSAAN as a powerful and reliable tool for drug discovery.
METHODS: We propose the Multi-view Semi-Supervised Adversarial Attention Network (M-SSAAN) for drug-disease association prediction. M-SSAAN combines structural and similarity embeddings to generate multi-view representations, and employs attention mechanisms along with semi-supervised adversarial learning to alleviate data sparsity and enhance robustness.
RESULTS: The effectiveness of M-SSAAN was evaluated through comparative experiments, ablation studies, and strategy analyses. In addition, case studies on ibuprofen indications and zero-shot predictions for lung cancer further demonstrate the model's ability to identify reliable drug-disease associations.
CONCLUSION: These results highlight the strong potential of M-SSAAN as a powerful and reliable tool for drug discovery.