{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T22:23:22Z","timestamp":1775600602625,"version":"3.50.1"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"8","funder":[{"name":"National Institutes of Health, National Eye Institute","award":["EY000184"],"award-info":[{"award-number":["EY000184"]}]},{"name":"National Institutes of Health, National Eye Institute","award":["R01 EY032482"],"award-info":[{"award-number":["R01 EY032482"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Single-cell RNA sequencing (scRNA-seq) data analysis often involves complex iterative workflow, requiring significant expertise and time. To navigate this complexity, we have developed SCassist, an R package that leverages the power of the large language models (LLM\u2019s) to guide and enhance scRNA-seq analysis. SCassist integrates LLM\u2019s into key workflow steps, to analyze user data and provide relevant recommendations for filtering, normalization and clustering parameters. It also provides LLM guided insightful interpretations of variable features and principal components, along with cell type annotations and enrichment analysis. SCassist provides intelligent assistance using popular LLM\u2019s like Google\u2019s Gemini, OpenAI\u2019s GPT and Meta\u2019s Llama3, making scRNA-seq analysis accessible to researchers at all levels.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The SCassist package, along with the detailed tutorials, is available at GitHub. https:\/\/github.com\/NIH-NEI\/SCassist.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf402","type":"journal-article","created":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T17:56:53Z","timestamp":1752343013000},"source":"Crossref","is-referenced-by-count":4,"title":["SCassist: an AI based workflow assistant for single-cell analysis"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2455-7172","authenticated-orcid":false,"given":"Vijayaraj","family":"Nagarajan","sequence":"first","affiliation":[{"name":"Laboratory of Immunology, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Guangpu","family":"Shi","sequence":"additional","affiliation":[{"name":"Laboratory of Immunology, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Samyuktha","family":"Arunkumar","sequence":"additional","affiliation":[{"name":"Laboratory of Immunology, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Chunhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Neuro-Immune Regulome Unit (Alumni), National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Jaanam","family":"Gopalakrishnan","sequence":"additional","affiliation":[{"name":"Neuro-Immune Regulome Unit, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Pulak R","family":"Nath","sequence":"additional","affiliation":[{"name":"Laboratory of Immunology (Alumni), National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Junseok","family":"Jang","sequence":"additional","affiliation":[{"name":"Laboratory of Immunology, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]},{"given":"Rachel R","family":"Caspi","sequence":"additional","affiliation":[{"name":"Laboratory of Immunology, National Eye Institute, NIH , Bethesda, MD 20892,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"key":"2025081213184000500_btaf402-B1","first-page":"1877","author":"Brown","year":"2020"},{"key":"2025081213184000500_btaf402-B2","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41467-023-35923-4","article-title":"Transformer for one stop interpretable cell type annotation","volume":"14","author":"Chen","year":"2023","journal-title":"Nat Commun"},{"key":"2025081213184000500_btaf402-B3","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2025081213184000500_btaf402-B4","doi-asserted-by":"publisher","author":"Devlin","DOI":"10.18653\/v1\/N19-1423"},{"key":"2025081213184000500_btaf402-B5","doi-asserted-by":"publisher","author":"Fang","year":"2024","DOI":"10.48550\/arXiv.2402.08303"},{"key":"2025081213184000500_btaf402-B6","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","article-title":"Large-scale foundation model on single-cell transcriptomics","volume":"21","author":"Hao","year":"2024","journal-title":"Nat Methods"},{"key":"2025081213184000500_btaf402-B7","doi-asserted-by":"crossref","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":"2025081213184000500_btaf402-B8","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2025081213184000500_btaf402-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bioinformatics\/btae075","article-title":"GeneGPT: augmenting large language models with domain tools for improved access to biomedical information","volume":"40","author":"Jin","year":"2024","journal-title":"Bioinformatics"},{"key":"2025081213184000500_btaf402-B10","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s13244-024-01660-5","article-title":"A novel reporting workflow for automated integration of artificial intelligence results into structured radiology reports","volume":"15","author":"Jorg","year":"2024","journal-title":"Insights Imaging"},{"key":"2025081213184000500_btaf402-B11","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2025081213184000500_btaf402-B12","first-page":"1","article-title":"A technique for the measurement of attitudes","volume":"140","author":"Likert","year":"1932","journal-title":"Arch Psychol"},{"key":"2025081213184000500_btaf402-B13","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1016\/j.immuni.2024.04.007","article-title":"A CTCF-binding site in the Mdm1-Il22-Ifng locus shapes cytokine expression profiles and plays a critical role in early Th1 cell fate specification","volume":"57","author":"Liu","year":"2024","journal-title":"Immunity"},{"key":"2025081213184000500_btaf402-B14","doi-asserted-by":"crossref","first-page":"6443","DOI":"10.1038\/s41467-024-50472-0","article-title":"Single-cell profiling identifies a CD8(bright) CD244(bright) natural killer cell subset that reflects disease activity in HLA-A29-positive birdshot chorioretinopathy","volume":"15","author":"Nath","year":"2024","journal-title":"Nat Commun"},{"key":"2025081213184000500_btaf402-B15","article-title":"Large-Scale cell representation learning via divide-and-conquer contrastive learning","author":"Nie","year":"2023"},{"key":"2025081213184000500_btaf402-B16","doi-asserted-by":"crossref","first-page":"420","DOI":"10.6026\/97320630001420","article-title":"GeneVenn\u2014a web application for comparing gene lists using Venn diagrams","volume":"1","author":"Pirooznia","year":"2007","journal-title":"Bioinformation"},{"key":"2025081213184000500_btaf402-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bioinformatics\/btae293","article-title":"scTPC: a novel semisupervised deep clustering model for scRNA-seq data","volume":"40","author":"Qiu","year":"2024","journal-title":"Bioinformatics"},{"key":"2025081213184000500_btaf402-B18","doi-asserted-by":"crossref","first-page":"106536","DOI":"10.1016\/j.isci.2023.106536","article-title":"Generative pretraining from large-scale transcriptomes for single-cell deciphering","volume":"26","author":"Shen","year":"2023","journal-title":"iScience"},{"key":"2025081213184000500_btaf402-B19","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1038\/s41592-024-02353-z","article-title":"Transformers in single-cell omics: a review and new perspectives","volume":"21","author":"Szalata","year":"2024","journal-title":"Nat Methods"},{"key":"2025081213184000500_btaf402-B20","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature"},{"key":"2025081213184000500_btaf402-B21","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"2025081213184000500_btaf402-B22","author":"Wen","year":"2023"},{"key":"2025081213184000500_btaf402-B23","author":"Xu","year":"2024"},{"key":"2025081213184000500_btaf402-B24","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1038\/s41422-024-01034-y","article-title":"GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model","volume":"34","author":"Yang","year":"2024","journal-title":"Cell Res"},{"key":"2025081213184000500_btaf402-B25","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","article-title":"scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","volume":"4","author":"Yang","year":"2022","journal-title":"Nat Mach Intell"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf402\/63735739\/btaf402.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/8\/btaf402\/63735739\/btaf402.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/8\/btaf402\/63735739\/btaf402.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T17:18:49Z","timestamp":1755019129000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf402\/8198067"}},"subtitle":[],"editor":[{"given":"Laura","family":"Cantini","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":25,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf402","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,8]]},"published":{"date-parts":[[2025,7,12]]},"article-number":"btaf402"}}