Harnessing AI to fuse phenotypic signatures for drug target identification: progress in computational modeling

Computational models integrating large-scale gene expression profiles provide a powerful approach for predicting multi-target drug interactions (DTIs). Unlike traditional experimental and computational methods that often require detailed structural or target-specific information, gene expression-based models leverage reference transcriptional signatures. This enables functional inference of interactions without explicit structural data, offering a valuable strategy in data-limited scenarios. By incorporating phenotypic information, these models bridge phenotype screening and target prediction, establishing a novel paradigm for target identification. This review introduces and compares current target identification methods, emphasizing the unique advantages of gene expression profiling in DTI prediction. We also outline major public databases and their applications. As an effective hypothesis-generation tools, computational DTI models reduce experimental costs, enhance understanding of multi-target mechanisms, and accelerate drug discovery. We categorize and analyze three primary model types utilizing large-scale gene expression data: biological network-based, association-based, and multimodal integration approaches, discussing their respective strengths and limitations. Key challenges and future directions are also addressed, including data integration, algorithm optimization, and multi-omics fusion, to fully realize the potential of gene expression data in multi-target drug prediction. This review offers comprehensive guidance on advanced tools, databases, and methodologies, enabling novel research paths for unbiased multi-target exploration. By linking phenotype screening with computational analysis, this integrative approach is expected to advance precision medicine, especially in uncovering drug mechanisms in complex diseases, offering promising prospects.