BioMaster: Multi-agent system for automated bioinformatics analysis workflow
BioMaster: мультиагентная система для автоматизированного рабочего процесса биоинформатического анализа
2026-07-07
SCID: 54.1/d29ga6nz
Discuss with AI
RNA-seq analysisbioinformatics workflow automationmulti-agent systemretrieval-augmented generationsingle-cell analysis
Figures from the paper
Abstract (AI)
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.
Key Findings
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.
Research Object
complex bioinformatics analysis workflows
Research Subject
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
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai16
SciPy 1.0: fundamental algorithms for scientific computing in Python2020
Array programming with NumPy2020
The Genome Analysis Toolkit: A MapReduce framework for analyzing next-generation DNA sequencing data2010
phyloseq: An R Package for Reproducible Interactive Analysis and Graphics of Microbiome Census Data2013
A Survey of Large Language Models2026
An integrated map of genetic variation from 1,092 human genomes2012
Massively parallel digital transcriptional profiling of single cells2017
Population Structure and Eigenanalysis2006
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks2020
The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2018 update2018
Lost in the Middle: How Language Models Use Long Contexts2024
Generative Agents: Interactive Simulacra of Human Behavior2023
Formation of Chromosomal Domains by Loop Extrusion2016
The Oxford Nanopore MinION: delivery of nanopore sequencing to the genomics community2016
iDEP: an integrated web application for differential expression and pathway analysis of RNA-Seq data2018
Augmenting large language models with chemistry tools2024