An AI Agent for Fully Automated Multi‐Omic Analyses

Abstract With the fast‐growing and evolving omics data, the demand for streamlined and adaptable tools to handle bioinformatics analysis continues to grow. In response to this need, Automated Bioinformatics Analysis (AutoBA) is introduced, an autonomous AI agent designed explicitly for fully automat...

Full description

Saved in:
Bibliographic Details
Main Authors: Juexiao Zhou, Bin Zhang, Guowei Li, Xiuying Chen, Haoyang Li, Xiaopeng Xu, Siyuan Chen, Wenjia He, Chencheng Xu, Liwei Liu, Xin Gao
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202407094
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846151505367793664
author Juexiao Zhou
Bin Zhang
Guowei Li
Xiuying Chen
Haoyang Li
Xiaopeng Xu
Siyuan Chen
Wenjia He
Chencheng Xu
Liwei Liu
Xin Gao
author_facet Juexiao Zhou
Bin Zhang
Guowei Li
Xiuying Chen
Haoyang Li
Xiaopeng Xu
Siyuan Chen
Wenjia He
Chencheng Xu
Liwei Liu
Xin Gao
author_sort Juexiao Zhou
collection DOAJ
description Abstract With the fast‐growing and evolving omics data, the demand for streamlined and adaptable tools to handle bioinformatics analysis continues to grow. In response to this need, Automated Bioinformatics Analysis (AutoBA) is introduced, an autonomous AI agent designed explicitly for fully automated multi‐omic analyses based on large language models (LLMs). AutoBA simplifies the analytical process by requiring minimal user input while delivering detailed step‐by‐step plans for various bioinformatics tasks. AutoBA's unique capacity to self‐design analysis processes based on input data variations further underscores its versatility. Compared with online bioinformatic services, AutoBA offers multiple LLM backends, with options for both online and local usage, prioritizing data security and user privacy. In comparison to ChatGPT and open‐source LLMs, an automated code repair (ACR) mechanism in AutoBA is designed to improve its stability in automated end‐to‐end bioinformatics analysis tasks. Moreover, different from the predefined pipeline, AutoBA has adaptability in sync with emerging bioinformatics tools. Overall, AutoBA represents an advanced and convenient tool, offering robustness and adaptability for conventional multi‐omic analyses.
format Article
id doaj-art-ee72c6f9d6f34f2399c301e1acfd5f1f
institution Kabale University
issn 2198-3844
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj-art-ee72c6f9d6f34f2399c301e1acfd5f1f2024-11-27T11:21:53ZengWileyAdvanced Science2198-38442024-11-011144n/an/a10.1002/advs.202407094An AI Agent for Fully Automated Multi‐Omic AnalysesJuexiao Zhou0Bin Zhang1Guowei Li2Xiuying Chen3Haoyang Li4Xiaopeng Xu5Siyuan Chen6Wenjia He7Chencheng Xu8Liwei Liu9Xin Gao10Computer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaLaboratory of Health Intelligence Huawei Technologies Co., Ltd Shenzhen 210000 ChinaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaAdvanced Computing and Storage Laboratory Central Research Institute 2012 Laboratories, Huawei Technologies Co., Ltd Nanjing Jiangsu 210000 ChinaComputer Science Program Computer, Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955‐6900 Kingdom of Saudi ArabiaAbstract With the fast‐growing and evolving omics data, the demand for streamlined and adaptable tools to handle bioinformatics analysis continues to grow. In response to this need, Automated Bioinformatics Analysis (AutoBA) is introduced, an autonomous AI agent designed explicitly for fully automated multi‐omic analyses based on large language models (LLMs). AutoBA simplifies the analytical process by requiring minimal user input while delivering detailed step‐by‐step plans for various bioinformatics tasks. AutoBA's unique capacity to self‐design analysis processes based on input data variations further underscores its versatility. Compared with online bioinformatic services, AutoBA offers multiple LLM backends, with options for both online and local usage, prioritizing data security and user privacy. In comparison to ChatGPT and open‐source LLMs, an automated code repair (ACR) mechanism in AutoBA is designed to improve its stability in automated end‐to‐end bioinformatics analysis tasks. Moreover, different from the predefined pipeline, AutoBA has adaptability in sync with emerging bioinformatics tools. Overall, AutoBA represents an advanced and convenient tool, offering robustness and adaptability for conventional multi‐omic analyses.https://doi.org/10.1002/advs.202407094agentbioinformaticslarge language modelomics analysis
spellingShingle Juexiao Zhou
Bin Zhang
Guowei Li
Xiuying Chen
Haoyang Li
Xiaopeng Xu
Siyuan Chen
Wenjia He
Chencheng Xu
Liwei Liu
Xin Gao
An AI Agent for Fully Automated Multi‐Omic Analyses
Advanced Science
agent
bioinformatics
large language model
omics analysis
title An AI Agent for Fully Automated Multi‐Omic Analyses
title_full An AI Agent for Fully Automated Multi‐Omic Analyses
title_fullStr An AI Agent for Fully Automated Multi‐Omic Analyses
title_full_unstemmed An AI Agent for Fully Automated Multi‐Omic Analyses
title_short An AI Agent for Fully Automated Multi‐Omic Analyses
title_sort ai agent for fully automated multi omic analyses
topic agent
bioinformatics
large language model
omics analysis
url https://doi.org/10.1002/advs.202407094
work_keys_str_mv AT juexiaozhou anaiagentforfullyautomatedmultiomicanalyses
AT binzhang anaiagentforfullyautomatedmultiomicanalyses
AT guoweili anaiagentforfullyautomatedmultiomicanalyses
AT xiuyingchen anaiagentforfullyautomatedmultiomicanalyses
AT haoyangli anaiagentforfullyautomatedmultiomicanalyses
AT xiaopengxu anaiagentforfullyautomatedmultiomicanalyses
AT siyuanchen anaiagentforfullyautomatedmultiomicanalyses
AT wenjiahe anaiagentforfullyautomatedmultiomicanalyses
AT chenchengxu anaiagentforfullyautomatedmultiomicanalyses
AT liweiliu anaiagentforfullyautomatedmultiomicanalyses
AT xingao anaiagentforfullyautomatedmultiomicanalyses
AT juexiaozhou aiagentforfullyautomatedmultiomicanalyses
AT binzhang aiagentforfullyautomatedmultiomicanalyses
AT guoweili aiagentforfullyautomatedmultiomicanalyses
AT xiuyingchen aiagentforfullyautomatedmultiomicanalyses
AT haoyangli aiagentforfullyautomatedmultiomicanalyses
AT xiaopengxu aiagentforfullyautomatedmultiomicanalyses
AT siyuanchen aiagentforfullyautomatedmultiomicanalyses
AT wenjiahe aiagentforfullyautomatedmultiomicanalyses
AT chenchengxu aiagentforfullyautomatedmultiomicanalyses
AT liweiliu aiagentforfullyautomatedmultiomicanalyses
AT xingao aiagentforfullyautomatedmultiomicanalyses