Integrating multi-omics and artificial intelligence fuels advanced target identification and drug discovery

Target identification is pivotal for developing novel therapeutics in cancer and other diseases. Traditional experiment screening methods are constrained by low throughput and the complexity of biological systems. Multi-omics technologies offer a transformative solution by providing comprehensive, multi-dimensional insights into molecular mechanisms. However, the exponential growth of multi-omics data necessitates efficient computational algorithms for dimensionality reduction and unravel the intricate biological processes. Artificial intelligence (AI) has emerged as a powerful tool capable of analyzing complementary multi-modal data streams. The integration of multi-omics technologies and AI algorithms has revolutionized target identification and drug discovery. This review highlights prevalent omics techniques and their role in target identification and drug discovery, outlines key machine learning (ML) classifications, and describes the integration of multi-omics with AI. We explore the applications of AI-driven multi-omics in various stages of drug discovery, including target identification, target validation, lead optimization, as well as clinical evaluation, underscoring the transformative potential of this approach. Additionally, we discuss the challenges associated with this integrative strategy and future trends in the field. As the integration of multi-omics and AI continues to expand, we anticipate a paradigm shift in target identification and drug discovery, paving the way for more precise and effective therapies.