BioMaster: Multi-agent system for automated bioinformatics analysis workflow

BioMaster: мультиагентная система для автоматизированного рабочего процесса биоинформатического анализа
Yanlin Zhang, Xu Yang, Houcheng Su, Junning Feng, Yawen Lu, Yucheng Xu, Jinming Yang, Haojie Lu, Jixin Yang, Sirui Xie, Weicai Long, Chengrui Wang, Yusen Hou, Tingyu Zhu
2026-07-07

RNA-seq analysisbioinformatics workflow automationmulti-agent systemretrieval-augmented generationsingle-cell analysis
The growing volume and complexity of biological data have made bioinformatics workflows increasingly labor-intensive, error-prone, and difficult to scale. Large language model-based agents offer potential for automation but often fail in complex, multi-step analyses because of limited robustness. We present BioMaster, a multi-agent framework that integrates workflow planning, execution, error recovery, and output validation. BioMaster incorporates a dual retrieval-augmented design to leverage domain knowledge for tool selection, parameterization, and adaptation across tasks. A dedicated debug agent supports real-time error detection and correction, while memory optimization enables long, multi-stage workflows. In benchmarking across 49 bioinformatics tasks spanning 102 tools, BioMaster completed substantially more workflows than did existing automated systems, particularly in complex, interdependent pipelines. BioMaster supports both proprietary and open-source language models, enabling flexible deployment across different computational settings.
1
BioMaster applies input/output validation and workflow-optimized memory management to detect errors early and support reliable long, multi-step pipelines.
2
BioMaster is a multi-agent framework that decomposes complex bioinformatics workflows into specialized, role-based tasks with execution and validation.
3
Experiments covering RNA-seq, ChIP-seq, single-cell analysis, and Hi-C processing show that BioMaster outperforms existing methods in accuracy, efficiency, and scalability.
4
The framework uses retrieval-augmented generation to dynamically acquire domain-specific knowledge, improving adaptation to new tools and niche bioinformatics analyses.
5
The system targets major limitations of LLM-based workflow automation, including error propagation, limited adaptability, and weak generalization to specialized bioinformatics tasks.

complex bioinformatics analysis workflows

automated workflow execution and coordination, including task decomposition, domain-knowledge retrieval, validation, error control, and long-workflow scalability

Publication Details
Publication Date
2026-07-07
Journal
Publisher
ISSN
Cited by
34
Access Type
Author Information
Authors
Yanlin Zhang
Xu Yang
Houcheng Su
Junning Feng
Yawen Lu
Yucheng Xu
Jinming Yang
Haojie Lu
Jixin Yang
Sirui Xie
Weicai Long
Chengrui Wang
Yusen Hou
Tingyu Zhu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%