{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T23:59:33Z","timestamp":1788479973667,"version":"build-2803163510"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P20GM104320"],"award-info":[{"award-number":["P20GM104320"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P20GM103434"],"award-info":[{"award-number":["P20GM103434"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54GM104942"],"award-info":[{"award-number":["U54GM104942"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2125872"],"award-info":[{"award-number":["2125872"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Nebraska-Lincoln (UNL) Grand Challenge and Undergraduate Creative Activities and Research Experience"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The rapid evolution of bioinformatics tools and multi-step analytic procedure presents a challenge for building effective pipelines, particularly for researchers without extensive programming expertise. This study demonstrates that large language models (LLMs) hold strong potential for generating end-to-end bioinformatic pipelines through carefully crafted prompts, using a multi-step metaviral workflow as a representative example. Multiple LLMs were tested for their effectiveness, including OpenAI ChatGPT series, Anthropic Claude series, Google Gemini, Meta Llama, and DeepSeek.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our results show that ChatGPT-4, ChatGPT-5, Claude 4.5, and Gemini 2.5 consistently outperform other LLMs in generating complete bioinformatic pipelines, with statistically significant success rates. These models also handle tool substitutions effectively. Simple prompt engineering and the inclusion of official documentation further enhance performance, especially for newer bioinformatic tools. While capabilities vary, all LLMs tested show potential for both pipeline generation and updates with our designed prompts and strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>All prompts are available in the paper. The examples are available in GitHub https:\/\/github.com\/mpckkk\/pBio.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbaf308","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T13:08:48Z","timestamp":1764162528000},"source":"Crossref","is-referenced-by-count":2,"title":["Prompt-based bioinformatic pipeline generation for a multi-step metaviral workflow"],"prefix":"10.1093","volume":"6","author":[{"given":"Pengchong","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computing, University of Nebraska Lincoln , Lincoln, NE 68588,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoze","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computing, University of Nebraska Lincoln , Lincoln, NE 68588,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Immunology & Cell Biology, West Virginia University , Morgantown, WV 26505,","place":["United States"]},{"name":"Lane Department of Computer Science & Electrical Engineering, West Virginia University , Morgantown, WV 26506,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Immunology & Cell Biology, West Virginia University , Morgantown, WV 26505,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandi","family":"Sigmon","sequence":"additional","affiliation":[{"name":"Department of Plant Pathology, University of Nebraska-Lincoln , Lincoln, NE 68583,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karrie A","family":"Weber","sequence":"additional","affiliation":[{"name":"School of Biological Sciences, University of Nebraska-Lincoln , Lincoln, NE 68588,","place":["United States"]},{"name":"Department of Earth and Atmospheric Sciences, University of Nebraska-Lincoln , Lincoln, NE 68588,","place":["United States"]},{"name":"Daugherty Water for Food Institute, University of Nebraska System , Lincoln, NE 68588,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-6888","authenticated-orcid":false,"given":"Gangqing","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Immunology & Cell Biology, West Virginia University , Morgantown, WV 26505,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9974-8788","authenticated-orcid":false,"given":"Qiuming","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computing, University of Nebraska Lincoln , Lincoln, NE 68588,","place":["United States"]},{"name":"Nebraska Center for Virology, University of Nebraska-Lincoln , Lincoln, NE 68583,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"2026050508251768600_vbaf308-B1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026050508251768600_vbaf308-B2","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1038\/s41587-023-01953-y","article-title":"Identification of mobile genetic elements with geNomad","volume":"42","author":"Camargo","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2026050508251768600_vbaf308-B3","doi-asserted-by":"crossref","DOI":"10.3386\/w34255","volume-title":"How People Use ChatGPT","author":"Chatterji","year":"2025"},{"key":"2026050508251768600_vbaf308-B4","doi-asserted-by":"crossref","first-page":"btae589","DOI":"10.1093\/bioinformatics\/btae589","article-title":"Learning to explain is a good biomedical few-shot learner","volume":"40","author":"Chen","year":"2024","journal-title":"Bioinformatics"},{"key":"2026050508251768600_vbaf308-B5","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1038\/s41551-024-01284-6","article-title":"Simple and effective embedding model for single-cell biology built from ChatGPT","volume":"9","author":"Chen","year":"2025","journal-title":"Nat Biomed Eng"},{"key":"2026050508251768600_vbaf308-B6","doi-asserted-by":"crossref","first-page":"e1012901","DOI":"10.1371\/journal.pcbi.1012901","article-title":"Playbook workflow builder: interactive construction of bioinformatics workflows","volume":"21","author":"Clarke","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026050508251768600_vbaf308-B7","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1093\/bioinformatics\/bty630","article-title":"Simulating illumina metagenomic data with in silicoseq","volume":"35","author":"Gourl\u00e9","year":"2019","journal-title":"Bioinformatics"},{"key":"2026050508251768600_vbaf308-B8","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/s40168-020-00990-y","article-title":"VirSorter2: a multi-classifier, expert-guided approach to detect diverse DNA and RNA viruses","volume":"9","author":"Guo","year":"2021","journal-title":"Microbiome"},{"key":"2026050508251768600_vbaf308-B9","doi-asserted-by":"crossref","first-page":"e1999","DOI":"10.7717\/peerj-cs.1999","article-title":"A comparison of chain-of-thought reasoning strategies across datasets and models","volume":"10","author":"Hebenstreit","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"2026050508251768600_vbaf308-B10","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1038\/s41592-024-02235-4","article-title":"Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis","volume":"21","author":"Hou","year":"2024","journal-title":"Nat Methods"},{"key":"2026050508251768600_vbaf308-B11","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1038\/s41467-022-28581-5","article-title":"Genome binning of viral entities from bulk metagenomics data","volume":"13","author":"Johansen","year":"2022","journal-title":"Nat Commun"},{"key":"2026050508251768600_vbaf308-B12","doi-asserted-by":"crossref","first-page":"e83","DOI":"10.1093\/nar\/gkac341","article-title":"vRhyme enables binning of viral genomes from metagenomes","volume":"50","author":"Kieft","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026050508251768600_vbaf308-B13","author":"Lu"},{"key":"2026050508251768600_vbaf308-B14","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1038\/s41587-020-00774-7","article-title":"CheckV assesses the quality and completeness of metagenome-assembled viral genomes","volume":"39","author":"Nayfach","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2026050508251768600_vbaf308-B15","doi-asserted-by":"crossref","first-page":"e3002083","DOI":"10.1371\/journal.pbio.3002083","article-title":"iPHoP: an integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria","volume":"21","author":"Roux","year":"2023","journal-title":"PLoS Biol"},{"key":"2026050508251768600_vbaf308-B16","doi-asserted-by":"crossref","first-page":"giae030","DOI":"10.1093\/gigascience\/giae030","article-title":"A qualitative assessment of using ChatGPT as large language model for scientific workflow development","volume":"13","author":"S\u00e4nger","year":"2024","journal-title":"Gigascience"},{"key":"2026050508251768600_vbaf308-B17","first-page":"783","article-title":"Chain of thought strategy for smaller LLMs for medical reasoning","volume":"327","author":"Shah","year":"2025","journal-title":"Stud Health Technol Inform"},{"key":"2026050508251768600_vbaf308-B18","doi-asserted-by":"crossref","first-page":"105","DOI":"10.15302\/J-QB-023-0327","article-title":"Empowering beginners in bioinformatics with ChatGPT","volume":"11","author":"Shue","year":"2023","journal-title":"Quant Biol"},{"key":"2026050508251768600_vbaf308-B19","first-page":"972","article-title":"HealthPrompt: a zero-shot learning paradigm for clinical natural language processing","volume":"2022","author":"Sivarajkumar","year":"2022","journal-title":"AMIA Annu Symp Proc"},{"key":"2026050508251768600_vbaf308-B20","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1002\/jrsm.1749","article-title":"Zero- and few-shot prompting of generative large language models provides weak assessment of risk of bias in clinical trials","volume":"15","author":"\u0160uster","year":"2024","journal-title":"Res Synth Methods"},{"key":"2026050508251768600_vbaf308-B21","doi-asserted-by":"crossref","first-page":"i266","DOI":"10.1093\/bioinformatics\/btae230","article-title":"BioCoder: a benchmark for bioinformatics code generation with large language models","volume":"40","author":"Tang","year":"2024","journal-title":"Bioinformatics."},{"key":"2026050508251768600_vbaf308-B22","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1002\/qub2.67","article-title":"Bioinformatics and biomedical informatics with ChatGPT: year one review","volume":"12","author":"Wang","year":"2024","journal-title":"Quant Biol"},{"key":"2026050508251768600_vbaf308-B23","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei"},{"key":"2026050508251768600_vbaf308-B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with Kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"},{"key":"2026050508251768600_vbaf308-B25","doi-asserted-by":"crossref","first-page":"1687687","DOI":"10.3389\/fbinf.2025.1687687","article-title":"Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT","volume":"5","author":"Xu","year":"2025","journal-title":"Front Bioinform"},{"key":"2026050508251768600_vbaf308-B26","doi-asserted-by":"crossref","first-page":"204","DOI":"10.15302\/J-QB-023-0328","article-title":"ChatGPT opens a new door for bioinformatics","volume":"11","author":"Xu","year":"2023","journal-title":"Quant Biol"},{"key":"2026050508251768600_vbaf308-B27","doi-asserted-by":"crossref","first-page":"e2407094","DOI":"10.1002\/advs.202407094","article-title":"An AI agent for fully automated multi-omic analyses","volume":"11","author":"Zhou","year":"2024","journal-title":"Adv Sci (Weinh)"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/advance-article-pdf\/doi\/10.1093\/bioadv\/vbaf308\/65575901\/vbaf308.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbaf308\/68211714\/vbaf308.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbaf308\/68211714\/vbaf308.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:25:27Z","timestamp":1777983927000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbaf308\/8346364"}},"subtitle":[],"editor":[{"given":"Alex","family":"Bateman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbaf308","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2025,11,27]]},"article-number":"vbaf308"}}