AuraGenome: An LLM-Powered Framework for On-the-Fly Reusable and Scalable Circular Genome Visualizations

TL;DR

AuraGenome is an innovative LLM-powered framework that simplifies and accelerates the creation of complex, multi-layered circular genome visualizations through a semantic-driven multi-agent workflow and interactive visual analytics.

Contribution

It introduces a novel LLM-driven multi-agent system for automated, customizable, and scalable circular genome visualization, reducing manual effort and enhancing usability.

Findings

Effective in generating tailored visualizations in case studies

Reduces time and errors compared to manual scripting

Received positive feedback in user study

Abstract

Circular genome visualizations are essential for exploring structural variants and gene regulation. However, existing tools often require complex scripting and manual configuration, making the process time-consuming, error-prone, and difficult to learn. To address these challenges, we introduce AuraGenome, an LLM-powered framework for rapid, reusable, and scalable generation of multi-layered circular genome visualizations. AuraGenome combines a semantic-driven multi-agent workflow with an interactive visual analytics system. The workflow employs seven specialized LLM-driven agents, each assigned distinct roles such as intent recognition, layout planning, and code generation, to transform raw genomic data into tailored visualizations. The system supports multiple coordinated views tailored for genomic data, offering ring, radial, and chord-based layouts to represent multi-layered circular genome visualizations. In addition to enabling interactions and configuration reuse, the system supports real-time refinement and high-quality report export. We validate its effectiveness through two case studies and a comprehensive user study. AuraGenome is available at: https://github.com/Darius18/AuraGenome.