{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:07:09Z","timestamp":1780596429825,"version":"3.54.1"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":34,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54AG075936"],"award-info":[{"award-number":["U54AG075936"]}],"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":["R35GM154865"],"award-info":[{"award-number":["R35GM154865"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Data preprocessing is critical for single-cell omics analyses, but default pipelines often underperform on diverse datasets, especially from emerging platforms like spatial transcriptomics. We introduce Lense, a language-model-guided method that automatically selects optimal preprocessing by comparing plots that visualize low-dimensional representations across pipeline variants. Integrated with Seurat, Lense streamlines analysis and improves preprocessing robustness without requiring manual tuning.<\/jats:p>","DOI":"10.1093\/bib\/bbag288","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:05:42Z","timestamp":1778760342000},"source":"Crossref","is-referenced-by-count":0,"title":["Lense: optimizing data preprocessing in single-cell omics using large language models"],"prefix":"10.1093","volume":"27","author":[{"given":"Jingyun","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University School of Medicine , 2424 Erwin Road, Durham, NC, 27705 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University School of Medicine , 2424 Erwin Road, Durham, NC, 27705 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"2026060413251740700_ref1","doi-asserted-by":"crossref","first-page":"eabl4896","DOI":"10.1126\/science.abl4896","article-title":"The tabula sapiens: a multiple-organ, single-cell transcriptomic atlas of humans","volume":"376","author":"Tabula Sapiens Consortium","year":"2022","journal-title":"Science"},{"key":"2026060413251740700_ref2","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41586-019-1629-x","article-title":"The human body at cellular resolution: the NIH human biomolecular atlas program","volume":"574","author":"Consortium HuBMAP","year":"2019","journal-title":"Nature"},{"key":"2026060413251740700_ref3","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1016\/j.immuni.2019.09.013","article-title":"TCF-1-centered transcriptional network drives an effector versus exhausted CD8 t cell-fate decision","volume":"51","author":"Chen","year":"2019","journal-title":"Immunity"},{"key":"2026060413251740700_ref4","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41586-021-03752-4","article-title":"Transcriptional programs of neoantigen-specific TIL in anti-PD-1-treated lung cancers","volume":"596","author":"Caushi","year":"2021","journal-title":"Nature"},{"key":"2026060413251740700_ref5","doi-asserted-by":"publisher","first-page":"eabm5214","DOI":"10.1126\/science.abm5214","article-title":"Distinct myeloid-derived suppressor cell populations in human glioblastoma","volume":"387","author":"Jackson","year":"2025","journal-title":"Science"},{"key":"2026060413251740700_ref6","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"2026060413251740700_ref7","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13059-017-1382-0","article-title":"SCANPY: large-scale single-cell gene expression data analysis","volume":"19","author":"Wolf","year":"2018","journal-title":"Genome Biol"},{"key":"2026060413251740700_ref8","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1038\/s41592-025-02617-2","article-title":"Optimizing Xenium in situ data utility by quality assessment and best-practice analysis workflows","volume":"22","author":"Marco Salas","year":"2025","journal-title":"Nat Methods"},{"key":"2026060413251740700_ref9","author":"Achiam","year":"2023"},{"key":"2026060413251740700_ref10","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":"2026060413251740700_ref11","volume-title":"Brief Bioinform"},{"key":"2026060413251740700_ref12","doi-asserted-by":"crossref","first-page":"2400947","DOI":"10.1002\/aisy.202400947","article-title":"Assessing large multimodal models for one-shot learning and interpretability in biomedical image classification","volume":"7","author":"Hou","year":"2025","journal-title":"Adv Intell Syst"},{"key":"2026060413251740700_ref13","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":"2026060413251740700_ref14","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s41592-024-02525-x","article-title":"Evaluation of large language models for discovery of gene set function","volume":"22","author":"Hu","year":"2025","journal-title":"Nat Methods"},{"key":"2026060413251740700_ref15","doi-asserted-by":"crossref","first-page":"e2521062122","DOI":"10.1073\/pnas.2521062122","article-title":"Evaluating large language models in biomedical data science challenges through a classroom experiment","volume":"122","author":"Ma","year":"2025","journal-title":"Proc Natl Acad Sci"},{"key":"2026060413251740700_ref16","doi-asserted-by":"publisher","first-page":"100135","DOI":"10.1016\/j.crmeth.2021.100135","article-title":"Unbiased visualization of single-cell genomic data with SCUBI","volume":"2","author":"Hou","year":"2022","journal-title":"Cell Rep Methods"},{"key":"2026060413251740700_ref17","doi-asserted-by":"publisher","first-page":"3654","DOI":"10.1093\/bioinformatics\/btac368","article-title":"Palo: spatially aware color palette optimization for single-cell and spatial data","volume":"38","author":"Hou","year":"2022","journal-title":"Bioinformatics"},{"key":"2026060413251740700_ref18","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1186\/s13059-019-1874-1","article-title":"Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression","volume":"20","author":"Hafemeister","year":"2019","journal-title":"Genome Biol"},{"key":"2026060413251740700_ref19","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.cell.2021.12.018","article-title":"Spatial proteogenomics reveals distinct and evolutionarily conserved hepatic macrophage niches","volume":"185","author":"Guilliams","year":"2022","journal-title":"Cell"},{"key":"2026060413251740700_ref20","doi-asserted-by":"crossref","DOI":"10.1101\/2025.01.17.633590","article-title":"Single-cell decoding of human islet cell type-specific alterations in type 2 diabetes reveals converging genetic-and state-driven $\\beta$-cell gene expression defects. bioRxiv","author":"Bandesh","year":"2025"},{"key":"2026060413251740700_ref21","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41586-021-03929-x","article-title":"Blood and immune development in human fetal bone marrow and down syndrome","volume":"598","author":"Jardine","year":"2021","journal-title":"Nature"},{"key":"2026060413251740700_ref22","doi-asserted-by":"publisher","first-page":"4400","DOI":"10.1038\/s41467-025-59005-9","article-title":"Transcriptome analysis of archived tumors by visium, GeoMx DSP, and chromium reveals patient heterogeneity","volume":"16","author":"Dong","year":"2025","journal-title":"Nat Commun"},{"key":"2026060413251740700_ref23","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1038\/s41586-020-2797-4","article-title":"Cells of the adult human heart","volume":"588","author":"Litvi\u0148ukov\u00e1","year":"2020","journal-title":"Nature"},{"key":"2026060413251740700_ref24","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1038\/s41588-024-01688-9","article-title":"A single-cell atlas enables mapping of homeostatic cellular shifts in the adult human breast","volume":"56","author":"Reed","year":"2024","journal-title":"Nat Genet"},{"key":"2026060413251740700_ref25","doi-asserted-by":"publisher","first-page":"e62522","DOI":"10.7554\/eLife.62522","article-title":"Single-cell multiomic profiling of human lungs reveals cell-type-specific and age-dynamic control of SARS-CoV2 host genes","volume":"9","author":"Wang","year":"2020","journal-title":"Elife"},{"key":"2026060413251740700_ref26","article-title":"Combined single-cell RNA-seq profiling and enhancer editing reveals critical spatiotemporal controls over thalamic nuclei formation in the murine embryo. bioRxiv 2022\u201302","author":"Govek","year":"2022"},{"key":"2026060413251740700_ref27","volume-title":"Developmental Trajectories of Thalamic Nuclei Revealed by Single-Cell Transcriptome Profiling and Shh Perturbation","author":"CELLxGENE Discover","year":"2022"},{"key":"2026060413251740700_ref28","doi-asserted-by":"publisher","first-page":"7634","DOI":"10.1038\/s41467-022-35297-z","article-title":"Single-cell profiling of healthy human kidney reveals features of sex-based transcriptional programs and tissue-specific immunity","volume":"13","author":"McEvoy","year":"2022","journal-title":"Nat Commun"},{"key":"2026060413251740700_ref29","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1038\/s41586-023-06981-x","article-title":"Protracted neuronal recruitment in the temporal lobes of young children","volume":"626","author":"Nascimento","year":"2024","journal-title":"Nature"},{"key":"2026060413251740700_ref30","doi-asserted-by":"publisher","first-page":"3439","DOI":"10.1093\/bioinformatics\/bti525","article-title":"BioMart and Bioconductor: a powerful link between biological databases and microarray data analysis","volume":"21","author":"Durinck","year":"2005","journal-title":"Bioinformatics"},{"key":"2026060413251740700_ref31","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1038\/s41587-019-0068-4","article-title":"Characterization of cell fate probabilities in single-cell data with palantir","volume":"37","author":"Setty","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026060413251740700_ref32","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1038\/nmeth.4407","article-title":"Massively parallel single-nucleus RNA-seq with DroNc-seq","volume":"14","author":"Habib","year":"2017","journal-title":"Nat Methods"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag288\/68476398\/bbag288.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag288\/68476398\/bbag288.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T17:25:26Z","timestamp":1780593926000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag288\/8702547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag288","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag288"}}