IntelliCircos: A Data-driven and AI-powered Authoring Tool for Circos Plots

2025-03-31

AI Summary

To address the labor-intensive, expert-dependent nature of manual Circos plot construction in genomic analysis, this paper introduces the first AI-driven interactive Circos visualization tool. Methodologically: (1) we curate the first large-scale domain-specific dataset comprising 4,396 manually annotated Circos plots; (2) we design a domain-aware large language model (LLM) recommendation framework that integrates track-pattern mining, fine-tuning, and context-sensitive prompt engineering to support ideation, automatic configuration suggestions, and Python code generation; and (3) we develop a human-in-the-loop interactive interface. A user study with eight bioinformaticians demonstrates a 57% average reduction in plotting time and significantly improved design satisfaction, validating the tool’s advantages in efficiency, usability, and domain expertise.

Technology Category

• Humans and AI: Other Foundations of Human Computation & AI
• Machine Learning: Probabilistic Circuits and Graphical Models
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Genomics data is essential in biological and medical domains, and bioinformatics analysts often manually create circos plots to analyze the data and extract valuable insights. However, creating circos plots is complex, as it requires careful design for multiple track attributes and positional relationships between them. Typically, analysts often seek inspiration from existing circos plots, and they have to iteratively adjust and refine the plot to achieve a satisfactory final design, making the process both tedious and time-intensive. To address these challenges, we propose IntelliCircos, an AI-powered interactive authoring tool that streamlines the process from initial visual design to the final implementation of circos plots. Specifically, we build a new dataset containing 4396 circos plots with corresponding annotations and configurations, which are extracted and labeled from published papers. With the dataset, we further identify track combination patterns, and utilize Large Language Model (LLM) to provide domain-specific design recommendations and configuration references to navigate the design of circos plots. We conduct a user study with 8 bioinformatics analysts to evaluate IntelliCircos, and the results demonstrate its usability and effectiveness in authoring circos plots.

Problem

• Simplifying complex manual creation of circos plots
• Reducing tedious iterative design adjustments for genomics data
• Providing AI-driven design recommendations for circos plots

Innovation

• AI-powered interactive authoring tool
• Dataset with 4396 annotated circos plots
• LLM for design recommendations and configurations