Artificial intelligence in antiviral drug discovery: Data resources, methods, and applications

Viral infectious diseases remain a major global health burden, underscoring the urgent need for efficient strategies to identify novel antiviral agents, particularly those with broad-spectrum activity and a high barrier to resistance. With the rapid accumulation of diverse biological and chemical data, artificial intelligence (AI) is increasingly being integrated into antiviral drug discovery to accelerate candidate identification and optimization. In this review, we summarize major data resources for AI-assisted antiviral research, including viral genome databases, viral protein databases, virus-host protein interaction databases, antiviral compound activity databases, compound structure databases, and viral mutation and drug resistance databases. We then review representative AI methods and applications across key tasks in antiviral drug discovery, including target-based drug discovery, phenotype-based drug discovery, and viral mutation and drug resistance prediction. We also summarize representative antiviral candidates from AI-assisted studies and their reported activities. Finally, we discuss current challenges and future opportunities in AI-assisted antiviral drug discovery. We believe that the continued advances in data resources and AI methodologies will accelerate the development of more effective antiviral agents.