{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:26:59Z","timestamp":1787164019052,"version":"build-2736575974"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014607","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000}}],"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472239"],"award-info":[{"award-number":["62472239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Team of Colleges and Universities in Shandong Province","award":["2023KJ329"],"award-info":[{"award-number":["2023KJ329"]}]},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["ZR2024MF011"],"award-info":[{"award-number":["ZR2024MF011"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402250"],"award-info":[{"award-number":["62402250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cultivation Fund of the Second Hospital of Shandong University","award":["2023JX16"],"award-info":[{"award-number":["2023JX16"]}]},{"name":"Shandong Province Key Research and Development Program \u2013 International Scientific and Technological Cooperation Project","award":["2024KJHZ029"],"award-info":[{"award-number":["2024KJHZ029"]}]},{"name":"Shandong Province Key Research and Development Program \u2013 International Scientific and Technological Cooperation Project","award":["2025KJHZ039"],"award-info":[{"award-number":["2025KJHZ039"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372255"],"award-info":[{"award-number":["62372255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62333018"],"award-info":[{"award-number":["62333018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["W2412087"],"award-info":[{"award-number":["W2412087"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005329","name":"Natural Science Foundation of Guizhou Province","doi-asserted-by":"publisher","award":["ZK[2024]ZD035"],"award-info":[{"award-number":["ZK[2024]ZD035"]}],"id":[{"id":"10.13039\/501100005329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    A key challenge in single-cell RNA sequencing (scRNA-seq) data analysis is accurately and efficiently identifying the cell type of each cell. Cell type annotation for scRNA-seq data not only needs to overcome batch effects caused by various factors but also requires effective handling of large-scale scRNA-seq datasets. Although deep learning has achieved remarkable progress in cell type annotation tasks, it still exhibits limitations in interpretability and robustness against batch effects. To tackle these issues, we propose a supervised framework based on the Transformer architecture, named scKanFormer, for cell type annotation on large-scale multi-class scRNA-seq data. To mitigate the problems of untraceable latent space, poor interpretability, and feature loss caused by the nonlinear aggregation of features in autoencoders, we employ the Transformer framework. This framework avoids dimensionality reduction and enables traceability from the attention layers back to the original input features. By integrating biological information, local and global attention mechanisms, and leveraging Kolmogorov-Arnold Networks (KAN), we enhance the model\u2019s ability to identify and interpret cellular features. The combination of Convolutional Neural Network (CNN) and Transformer enables more comprehensive data processing, thereby mitigating batch effects. To evaluate the effectiveness and robustness of scKanFormer, we compared it with nine state-of-the-art methods on benchmark datasets. Through systematic comparisons under different cell type annotation scenarios and across various cell types, we demonstrate that scKanFormer delivers precise, robust, and transferable high-resolution annotations. These annotations are insensitive to batch effects and exhibit clear biological interpretability. The data and source code are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/nathanyl\/scKanFormer\" xlink:type=\"simple\">https:\/\/github.com\/nathanyl\/scKanFormer<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1014607","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T17:55:18Z","timestamp":1786730118000},"page":"e1014607","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["scKanFormer: A Transformer-KAN framework with biologically informed attention for cell type annotation in large-scale scRNA-seq data"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-8191","authenticated-orcid":true,"given":"Lin","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengguo","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siguo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De-Shuang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"issue":"6","key":"pcbi.1014607.ref001","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1038\/s41573-023-00688-4","article-title":"Applications of single-cell RNA sequencing in drug discovery and development","volume":"22","author":"B Van de Sande","year":"2023","journal-title":"Nat Rev Drug Discov"},{"issue":"3","key":"pcbi.1014607.ref002","article-title":"An overview of computational methods in single-cell transcriptomic cell type annotation","volume":"26","author":"T Li","year":"2025","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014607.ref003","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41467-022-28803-w","article-title":"Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data","volume":"13","author":"A Ianevski","year":"2022","journal-title":"Nat Commun"},{"issue":"4","key":"pcbi.1014607.ref004","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1093\/bib\/bbz062","article-title":"Clustering and classification methods for single-cell RNA-sequencing data","volume":"21","author":"R Qi","year":"2020","journal-title":"Brief Bioinform"},{"issue":"4","key":"pcbi.1014607.ref005","article-title":"A spectral clustering with self-weighted multiple kernel learning method for single-cell RNA-seq data","volume":"22","author":"R Qi","year":"2021","journal-title":"Brief Bioinform"},{"issue":"10","key":"pcbi.1014607.ref006","article-title":"On the use of QDE-SVM for gene feature selection and cell type classification from scRNA-seq data","volume":"18","author":"GYL Ng","year":"2023","journal-title":"PLoS One"},{"issue":"5","key":"pcbi.1014607.ref007","article-title":"TSomVar: a tumor-only somatic and germline variant identification method with random forest","volume":"23","author":"S Shi","year":"2022","journal-title":"Brief Bioinform"},{"issue":"5","key":"pcbi.1014607.ref008","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1038\/nmeth.4644","article-title":"scmap: projection of single-cell RNA-seq data across data sets","volume":"15","author":"VY Kiselev","year":"2018","journal-title":"Nat Methods"},{"issue":"2","key":"pcbi.1014607.ref009","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1038\/s41590-018-0276-y","article-title":"Reference-based analysis of lung single-cell sequencing reveals a transitional profibrotic macrophage","volume":"20","author":"D Aran","year":"2019","journal-title":"Nat Immunol"},{"issue":"1","key":"pcbi.1014607.ref010","article-title":"A comparison of deep learning-based pre-processing and clustering approaches for single-cell RNA sequencing data","volume":"23","author":"J Wang","year":"2022","journal-title":"Brief Bioinform"},{"issue":"2","key":"pcbi.1014607.ref011","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1093\/bioinformatics\/btz592","article-title":"ACTINN: automated identification of cell types in single cell RNA sequencing","volume":"36","author":"F Ma","year":"2020","journal-title":"Bioinformatics"},{"issue":"10","key":"pcbi.1014607.ref012","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":"F Yang","year":"2022","journal-title":"Nat Mach Intell"},{"issue":"4","key":"pcbi.1014607.ref013","article-title":"CIForm as a Transformer-based model for cell-type annotation of large-scale single-cell RNA-seq data","volume":"24","author":"J Xu","year":"2023","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014607.ref014","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":"J Chen","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014607.ref015","doi-asserted-by":"crossref","first-page":"22308","DOI":"10.1038\/s41598-024-73356-1","article-title":"scGAA: a general gated axial-attention model for accurate cell-type annotation of single-cell RNA-seq data","volume":"14","author":"T Kong","year":"2024","journal-title":"Sci Rep"},{"issue":"2","key":"pcbi.1014607.ref016","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1007\/s12539-025-00738-y","article-title":"scIMGCN: an automatic single-cell type annotation method based on interpretable graph convolutional network","volume":"18","author":"B Tang","year":"2026","journal-title":"Interdiscip Sci"},{"key":"pcbi.1014607.ref017","doi-asserted-by":"crossref","first-page":"108809","DOI":"10.1016\/j.cmpb.2025.108809","article-title":"TransAnno-Net: a deep learning framework for accurate cell type annotation of mouse lung tissue using self-supervised pretraining","volume":"267","author":"Q Zhang","year":"2025","journal-title":"Comput Methods Programs Biomed"},{"issue":"4","key":"pcbi.1014607.ref018","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1093\/bfgp\/elae002","article-title":"Integration tools for scRNA-seq data and spatial transcriptomics sequencing data","volume":"23","author":"C Yan","year":"2024","journal-title":"Brief Funct Genomics"},{"issue":"1","key":"pcbi.1014607.ref019","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1186\/s13059-023-02985-y","article-title":"ExplaiNN: interpretable and transparent neural networks for genomics","volume":"24","author":"G Novakovsky","year":"2023","journal-title":"Genome Biol"},{"key":"pcbi.1014607.ref020","article-title":"Kan: Kolmogorov-arnold networks","author":"Z Liu","year":"2024","journal-title":"arXiv preprint arXiv:240419756"},{"key":"pcbi.1014607.ref021","author":"R Yu","year":"2024"},{"issue":"15","key":"pcbi.1014607.ref022","doi-asserted-by":"crossref","first-page":"7742","DOI":"10.3390\/app12157742","article-title":"Cervical cell segmentation method based on global dependency and local attention","volume":"12","author":"G Li","year":"2022","journal-title":"Appl Sci"},{"issue":"11","key":"pcbi.1014607.ref023","article-title":"Attention-based deep clustering method for scRNA-seq cell type identification","volume":"19","author":"S Li","year":"2023","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"pcbi.1014607.ref024","article-title":"scDFN: enhancing single-cell RNA-seq clustering with deep fusion networks","volume":"25","author":"T Liu","year":"2024","journal-title":"Brief Bioinform"},{"issue":"5","key":"pcbi.1014607.ref025","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab105","article-title":"Critical downstream analysis steps for single-cell RNA sequencing data","volume":"22","author":"Z Zhang","year":"2021","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014607.ref026","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1038\/s41467-021-21312-2","article-title":"Fast and precise single-cell data analysis using a hierarchical autoencoder","volume":"12","author":"D Tran","year":"2021","journal-title":"Nat Commun"},{"issue":"12","key":"pcbi.1014607.ref027","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"R Lopez","year":"2018","journal-title":"Nat Methods"},{"issue":"15","key":"pcbi.1014607.ref028","doi-asserted-by":"crossref","first-page":"2540","DOI":"10.1039\/C7LC90070H","article-title":"InDrops and Drop-seq technologies for single-cell sequencing","volume":"17","author":"AM Klein","year":"2017","journal-title":"Lab Chip"},{"key":"pcbi.1014607.ref029","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/s13059-016-0938-8","article-title":"CEL-Seq2: sensitive highly-multiplexed single-cell RNA-Seq","volume":"17","author":"T Hashimshony","year":"2016","journal-title":"Genome Biol"},{"issue":"1","key":"pcbi.1014607.ref030","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/nprot.2014.006","article-title":"Full-length RNA-seq from single cells using Smart-seq2","volume":"9","author":"S Picelli","year":"2014","journal-title":"Nat Protoc"},{"key":"pcbi.1014607.ref031","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"L McInnes","year":"2018","journal-title":"arXiv preprint arXiv:180203426"},{"issue":"3","key":"pcbi.1014607.ref032","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad152","article-title":"Dimensionality reduction and visualization of single-cell RNA-seq data with an improved deep variational autoencoder","volume":"24","author":"J Jiang","year":"2023","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014607.ref033","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.1038\/s41467-021-22368-w","article-title":"Single cell transcriptional and chromatin accessibility profiling redefine cellular heterogeneity in the adult human kidney","volume":"12","author":"Y Muto","year":"2021","journal-title":"Nat Commun"},{"issue":"10","key":"pcbi.1014607.ref034","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.1038\/s41587-022-01284-4","article-title":"Multi-omics single-cell data integration and regulatory inference with graph-linked embedding","volume":"40","author":"Z-J Cao","year":"2022","journal-title":"Nat Biotechnol"},{"issue":"18","key":"pcbi.1014607.ref035","doi-asserted-by":"crossref","DOI":"10.15252\/embj.2018100811","article-title":"A single-cell transcriptome atlas of the adult human retina","volume":"38","author":"SW Lukowski","year":"2019","journal-title":"EMBO J"},{"issue":"1","key":"pcbi.1014607.ref036","doi-asserted-by":"crossref","first-page":"3164","DOI":"10.1038\/s41467-019-11036-9","article-title":"Single-cell reconstruction of follicular remodeling in the human adult ovary","volume":"10","author":"X Fan","year":"2019","journal-title":"Nat Commun"},{"key":"pcbi.1014607.ref037","article-title":"Comparative analysis of commercial single-cell RNA sequencing technologies","author":"M De Simone","year":"2024","journal-title":"BioRxiv"},{"key":"pcbi.1014607.ref038","article-title":"A single-cell transcriptional timelapse of mouse embryonic development, from gastrula to pup","author":"C Qiu","year":"2023","journal-title":"bioRxiv"},{"issue":"4","key":"pcbi.1014607.ref039","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaa314","article-title":"Goals and approaches for each processing step for single-cell RNA sequencing data","volume":"22","author":"Z Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"pcbi.1014607.ref040","doi-asserted-by":"crossref","first-page":"2917","DOI":"10.1007\/s10462-023-10595-0","article-title":"A survey of the vision transformers and their CNN-transformer based variants","volume":"56","author":"A Khan","year":"2023","journal-title":"Artif Intell Rev"},{"issue":"1","key":"pcbi.1014607.ref041","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13073-023-01249-5","article-title":"Annotation of cell types (ACT): a convenient web server for cell type annotation","volume":"15","author":"F Quan","year":"2023","journal-title":"Genome Med"},{"issue":"2","key":"pcbi.1014607.ref042","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s11760-024-03696-y","article-title":"Hybrid-CT: a novel hybrid 2D\/3D CNN-transformer based on transfer learning and attention mechanisms for small object classification","volume":"19","author":"K Bayoudh","year":"2025","journal-title":"Signal Image Video Process"},{"key":"pcbi.1014607.ref043","article-title":"Large-margin softmax loss for convolutional neural networks","author":"W Liu","year":"2016","journal-title":"arXiv preprint arXiv:161202295"},{"issue":"1","key":"pcbi.1014607.ref044","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","article-title":"A tutorial on the cross-entropy method","volume":"134","author":"P-T de Boer","year":"2005","journal-title":"Ann Oper Res"},{"key":"pcbi.1014607.ref045","article-title":"Understanding adamw through proximal methods and scale-freeness","author":"Z Zhuang","year":"2022","journal-title":"arXiv preprint arXiv:220200089"},{"key":"pcbi.1014607.ref046","first-page":"10890","article-title":"R-drop: regularized dropout for neural networks","volume":"34","author":"L Wu","year":"2021","journal-title":"Adv Neural Inform Process Syst"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:46:29Z","timestamp":1787161589000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014607"}},"subtitle":[],"editor":[{"given":"William","family":"Majoros","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":46,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014607","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}