Multi-Omics and Multimodal Data Fusion in Drug Discovery: From Target Identification to Personalized Therapy

Introduction

Modern drug discovery faces systemic challenges in combating complex diseases, whose mechanisms involve interactive networks across genomic, transcriptomic, proteomic, metabolomic, and other molecular layers. Single-omics or conventional approaches often fail to capture this complexity comprehensively. This thematic issue explores strategies for integrating multi-omics data (including genomics, transcriptomics, proteomics, metabolomics, and epigenomics) with multimodal information such as chemical structures, bioactivity profiles, clinical phenotypes, imaging features, and real-world data. By leveraging advanced data fusion techniques​(e.g., graph neural networks, attention mechanisms, and knowledge graphs) and network pharmacology principles, we aim to revolutionize the entire drug discovery pipeline. Topics cover novel target identification, lead optimization, mechanism elucidation, drug repurposing, biomarker discovery, and personalized therapeutic strategies, ultimately providing powerful, data-driven methodologies to address complex diseases.

Keywords

Multi-Omics , multimodal fusion , drug discovery , complex disease , network pharmacology, personalized therapy

Sub-topics

ØMulti-Omics Data Integration and Interpretation Strategies

ØMultimodal Data Representation and Fusion: Trends and Challenges​

ØRecent Advances in AI-Powered Drug Discovery​

ØEfficacy and Safety Prediction in Drug Discovery​

ØNetwork Pharmacology and Systems Pharmacology Applications

​ØProgress and Trends in Personalized Medicine for Complex Diseases (e.g., Cancer)