Streamlining GWAS Interpretation with AI-Powered Exploration Tools
About the poster
Genome-Wide Association Studies (GWAS) have become a cornerstone for identifying genetic variants that influence disease susceptibility and drug response. A notable example of high value provided by these studies is the successful repurposing of ustekinumab and risankizumab for Crohn’s disease treatment. Despite multiple successes, the complexity, scale and difficulty in interpretation of GWAS data often present significant challenges for researchers aiming to translate genetic discoveries into therapeutic applications.
To address this, we showcase AI-powered solution designed to streamline the exploration and functional characterization of GWAS studies. It empowers researchers to interactively explore genetic data and uncover associations more efficiently. By leveraging LLM that is further enhanced with distilled knowledge gathered from over twenty large sources, Our solution enables rapid identification of meaningful genetic variants, prioritization of targets, and hypothesis generation in drug discovery and disease research.
With its user-friendly an intuitive no-code interface it allows biologists, clinicians, and researchers without coding experience to quickly analyze and interpret complex associations in genomic data, reducing the time and resources typically expended for this process. This efficiency and the comprehensive knowledge-based evidence support provided by the system enables faster decision-making in drug repurposing, supports novel therapeutic discoveries, and helps researchers make data-driven insights for better patient stratification in clinical settings.
This poster was originally presented during the BioIT 2025 Conference.
