Advances in the emerging field of epi-informatics in drug discovery: roads taken and future prospects.

Abstract

INTRODUCTION Epigenetic drug discovery remains a promising drug discovery strategy that has long been driven by advances in computational approaches. The subfield of epi-informatics, established more than a decade ago, continues to evolve rapidly as emerging machine learning methodologies reshape and expand its applications. AREAS COVERED The authors provide an updated overview of bioinformatics, chemoinformatics, and machine learning methodologies used to identify, design, and optimize compounds, primarily small-molecules, that modulate epigenetic processes with therapeutic potential. The discussion is based on a comprehensive literature analysis of peer-reviewed literature, encompassing 7,185 unique research articles published between 2000 up to 2025. The article also examines the epigenetic drug discovery landscape by analyzing the most extensively investigated epigenetic targets and emerging research trends. EXPERT OPINION Epi-informatics has evolved into a distinct interdisciplinary field integrating bioinformatics, chemoinformatics, and artificial intelligence to advance epigenetic drug discovery. Although rapid progress in multi-omics integration, molecular modeling, and generative artificial intelligence is accelerating the identification of drug candidates, future success will depend on high-quality, standardized data, interpretable machine learning models, and rigorous experimental validation that ensure reproducibility. Addressing these challenges will further advance epi-informatics in oncology research and an expanding range of complex diseases.