AI-Powered Oncology Drug Target Discovery and Validation: Integrating Population Genomics and Causal Inference

The identification of novel and druggable cancer targets remains one of the most resource-intensive steps in oncology drug development, with a majority of drug candidates failing in clinical trials due to a lack of robust target validation. Advances in artificial intelligence, population-scale genomics, and causal inference methods are now converging to change how targets are prioritized, moving the field away from purely correlative biomarker discovery toward genetically and causally supported target selection. Large-scale human genetic data lakes, GWAS repositories, and multi-omics datasets offer an unprecedented opportunity to systematically identify targets with a higher probability of clinical success, while AI and machine learning methods are accelerating the interpretation of this complexity at scale.The central challenge in oncology drug discovery lies in translating the growing volume of population-scale genetic and multi-omic data into validated, actionable drug targets. Traditional target discovery pipelines often struggle to distinguish causal drivers of cancer from mere disease associations, leading to costly downstream attrition. This Research Topic aims to bring together computational, translational, and industry perspectives on how AI, GWAS, and causal inference methods can be integrated across the full pipeline, from initial target identification through experimental and clinical validation, to improve the efficiency and success rate of oncology drug development.This Research Topic welcomes contributions that advance the application of AI and population genomics to oncology drug target discovery and validation. We are particularly interested in work that bridges computational prediction with experimental or clinical validation. We welcome Original Research, Review, Mini Review and Perspective articles on themes including, but not limited to:- AI and machine learning approaches for prioritizing novel cancer drug targets- Integration of GWAS and population-scale genomic data into target discovery pipelines- Causal inference methods for distinguishing driver targets from disease associations- Human genetic data lakes and their application to oncology drug discovery- Multi-omics data integration for target identification and validation- Functional genomics and experimental validation strategies (e.g., CRISPR screens) for AI-predicted targets- Translational and industry-academia collaborative approaches to target validation- Case studies of successful or failed target discovery informed by genetic evidencePlease note: manuscripts consisting solely of in silico predictions or computational analyses of public databases which are not accompanied by any form of experimental or clinical validation are out of scope for this Research Topic and will not be accepted as part of this collection. Topic editors: Shameer Khader, Ph.D, Kamlesh Yadav Source: https://www.frontiersin.org/research-topics/85280/ai-powered-oncology-drug-target-discovery-and-validation-integrating-population-genomics-and-causal-inference