{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:36:27Z","timestamp":1760056587538,"version":"build-2065373602"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":39,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Japan and JST CREST","award":["JPMJCR2231"],"award-info":[{"award-number":["JPMJCR2231"]}]},{"name":"JSPS KAKENHI","award":["24\u00a0K15175, 25KJ1104, JP20H03240 and JP25K02261"],"award-info":[{"award-number":["24\u00a0K15175, 25KJ1104, JP20H03240 and JP25K02261"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurate classification of immune cells is crucial for elucidating their diverse roles in health and disease. However, this task remains very challenging in single-cell RNA sequencing (scRNA-seq) data due to the complex and hierarchical relationships of immune cell types. To address this, we introduce scHDeepInsight, a deep learning framework that extends our previous scDeepInsight model by integrating a biologically-informed classification architecture with an adaptive hierarchical focal loss (AHFL). The framework builds on our established method of converting gene expression data into two-dimensional structured images, enabling convolutional neural networks to effectively capture both global and fine-grained transcriptomic features. This design utilizes hierarchical relationships among immune cell types to enhance the classification ability beyond the flat classification approaches. scHDeepInsight dynamically adjusts loss contributions to balance performance across the hierarchy levels. Comprehensive benchmarking across seven diverse tissue datasets shows scHDeepInsight achieves an average accuracy of 93.2%, surpassing contemporary methods by 5.1 percentage points. The model successfully distinguishes 50 distinct immune cell subtypes with high accuracy, demonstrating proficiency for identifying rare and closely related cell subtypes. Additionally, SHAP-based interpretability quantifies individual gene contributions to reveal the biological basis of classification decisions. These qualities make scHDeepInsight a robust tool for high-resolution cell subtype characterization, well-suited for detailed profiling in immunological studies and extensible to nonimmune cell types.<\/jats:p>","DOI":"10.1093\/bib\/bbaf523","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T13:16:15Z","timestamp":1759842975000},"source":"Crossref","is-referenced-by-count":0,"title":["scHDeepInsight: a hierarchical deep learning framework for precise immune cell annotation in single-cell RNA-seq data"],"prefix":"10.1093","volume":"26","author":[{"given":"Shangru","family":"Jia","sequence":"first","affiliation":[{"name":"Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Artem","family":"Lysenko","sequence":"additional","affiliation":[{"name":"Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7095-7332","authenticated-orcid":false,"given":"Keith A","family":"Boroevich","sequence":"additional","affiliation":[{"name":"RIKEN Center for Integrative Medical Sciences , 1-7-22 Suehiro-cho, Tsurumi, Yokohama 230-0045 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7668-3501","authenticated-orcid":false,"given":"Alok","family":"Sharma","sequence":"additional","affiliation":[{"name":"Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 ,","place":["Japan"]},{"name":"RIKEN Center for Integrative Medical Sciences , 1-7-22 Suehiro-cho, Tsurumi, Yokohama 230-0045 ,","place":["Japan"]},{"name":"Institute for Integrated and Intelligent Systems, Griffith University , 170 Kessels Rd, Nathan, Brisbane, QLD 4111 ,","place":["Australia"]},{"name":"College of Informatics, Korea University, 145 Anam-ro, Seongbuk District , Seoul 02841 ,","place":["South Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5439-7918","authenticated-orcid":false,"given":"Tatsuhiko","family":"Tsunoda","sequence":"additional","affiliation":[{"name":"Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 ,","place":["Japan"]},{"name":"Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 ,","place":["Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"2025100908011199900_ref1","doi-asserted-by":"publisher","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":"Aran","year":"2019","journal-title":"Nat Immunol"},{"key":"2025100908011199900_ref2","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":"2025100908011199900_ref3","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1038\/nmeth.4644","article-title":"Scmap: Projection of single-cell RNA-seq data across data sets","volume":"15","author":"Kiselev","year":"2018","journal-title":"Nat Methods"},{"key":"2025100908011199900_ref4","doi-asserted-by":"crossref","first-page":"bbad266","DOI":"10.1093\/bib\/bbad266","article-title":"scDeepInsight: A supervised cell-type identification method for scRNA-seq data with deep learning","volume":"24","author":"Jia","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025100908011199900_ref5","doi-asserted-by":"publisher","first-page":"11399","DOI":"10.1038\/s41598-019-47765-6","article-title":"DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture","volume":"9","author":"Sharma","year":"2019","journal-title":"Sci Rep"},{"journal-title":"Adv Neural Inf Proces Syst 25 (NIPS)","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","key":"2025100908011199900_ref6"},{"first-page":"4768","volume-title":"Adv Neural Inf Proces Syst 30 (NIPS)","author":"Lundberg","key":"2025100908011199900_ref7"},{"key":"2025100908011199900_ref8","doi-asserted-by":"publisher","first-page":"eabl5197","DOI":"10.1126\/science.abl5197","article-title":"Cross-tissue immune cell analysis reveals tissue-specific features in humans","volume":"376","author":"Dom\u00ednguez Conde","year":"2022","journal-title":"Science"},{"key":"2025100908011199900_ref9","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1016\/j.ccell.2021.09.008","article-title":"Signatures of plasticity, metastasis, and immunosuppression in an atlas of human small cell lung cancer","volume":"39","author":"Chan","year":"2021","journal-title":"Cancer Cell"},{"key":"2025100908011199900_ref10","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1038\/s41586-021-03852-1","article-title":"Cells of the human intestinal tract mapped across space and time","volume":"597","author":"Elmentaite","year":"2021","journal-title":"Nature"},{"key":"2025100908011199900_ref11","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1038\/550451a","article-title":"The human cell atlas: From vision to reality","volume":"550","author":"Rozenblatt-Rosen","year":"2017","journal-title":"Nature"},{"key":"2025100908011199900_ref12","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1038\/s41590-020-0602-z","article-title":"Distinct microbial and immune niches of the human colon","volume":"21","author":"James","year":"2020","journal-title":"Nat Immunol"},{"key":"2025100908011199900_ref13","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":"2025100908011199900_ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-019-1906-x","article-title":"scRNA-seq assessment of the human lung, spleen, and esophagus tissue stability after cold preservation","volume":"21","author":"Madissoon","year":"2019","journal-title":"Genome Biol"},{"key":"2025100908011199900_ref15","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1038\/s41586-019-1652-y","article-title":"Decoding human fetal liver haematopoiesis","volume":"574","author":"Popescu","year":"2019","journal-title":"Nature"},{"key":"2025100908011199900_ref16","doi-asserted-by":"publisher","first-page":"eabl4896","DOI":"10.1126\/science.abl4896","article-title":"The tabula sapiens consortium. The tabula sapiens: A multiple-organ, single-cell transcriptomic atlas of humans","volume":"376","year":"2022","journal-title":"Science"},{"key":"2025100908011199900_ref17","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1038\/s41467-024-45240-z","article-title":"Semi-supervised integration of single-cell transcriptomics data","volume":"15","author":"Andreatta","year":"2024","journal-title":"Nat Commun"},{"key":"2025100908011199900_ref18","doi-asserted-by":"publisher","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":"2025100908011199900_ref19","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","author":"Zheng","year":"2017","journal-title":"Nat Commun"},{"key":"2025100908011199900_ref20","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1126\/science.1247651","article-title":"Massively parallel single-cell RNA-Seq for marker-free decomposition of tissues into cell types","volume":"343","author":"Jaitin","year":"2014","journal-title":"Science"},{"key":"2025100908011199900_ref21","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2025100908011199900_ref22","first-page":"6105","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"2025100908011199900_ref23","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/s10038-024-01231-y","article-title":"Advances in AI and machine learning for predictive medicine","volume":"69","author":"Sharma","year":"2024","journal-title":"J Hum Genet"},{"key":"2025100908011199900_ref24","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform manifold approximation and projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J Open Source Softw"},{"key":"2025100908011199900_ref25","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat Methods"},{"key":"2025100908011199900_ref26","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025100908011199900_ref27","article-title":"Exponential moving average of weights in deep learning: Dynamics and benefits","author":"Morales","year":"2024","journal-title":"Trans Mach Learn Res"},{"key":"2025100908011199900_ref28","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1038\/s41592-019-0535-3","article-title":"Supervised classification enables rapid annotation of cell atlases","volume":"16","author":"Pliner","year":"2019","journal-title":"Nat Methods"},{"key":"2025100908011199900_ref29","doi-asserted-by":"publisher","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":"Ianevski","year":"2022","journal-title":"Nat Commun"},{"key":"2025100908011199900_ref30","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":"2025100908011199900_ref31","doi-asserted-by":"publisher","first-page":"eabd1554","DOI":"10.1126\/sciimmunol.abd1554","article-title":"Immunophenotyping of COVID-19 and influenza highlights the role of type I interferons in development of severe COVID-19","volume":"5","author":"Lee","year":"2020","journal-title":"Sci Immunol"},{"key":"2025100908011199900_ref32","doi-asserted-by":"publisher","first-page":"rs.3.rs-3601404","DOI":"10.21203\/rs.3.rs-3601404\/v2","article-title":"GZMK+CD8+ T-cells target a specific acinar cell type in Sj\u00f6gren\u2019s disease","author":"Pranzatelli","year":"2024  11","journal-title":"Res Sq"},{"key":"2025100908011199900_ref33","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1038\/nmeth.4380","article-title":"Simultaneous epitope and transcriptome measurement in single cells","volume":"14","author":"Stoeckius","year":"2017","journal-title":"Nat Methods"},{"key":"2025100908011199900_ref34","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1038\/s41593-020-00789-y","article-title":"Single-cell profiling of myeloid cells in glioblastoma across species and disease stage reveals macrophage competition and specialization","volume":"24","author":"Pombo Antunes","year":"2021","journal-title":"Nat Neurosci"},{"key":"2025100908011199900_ref35","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1385\/IR:25:2:155","article-title":"Positive and negative roles of CD72 in B cell function","volume":"25","author":"Wu","year":"2002","journal-title":"Immunol Res"},{"key":"2025100908011199900_ref36","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1038\/s41588-021-00911-1","article-title":"A single-cell and spatially resolved atlas of human breast cancers","volume":"53","author":"Wu","year":"2021","journal-title":"Nat Genet"},{"key":"2025100908011199900_ref37","doi-asserted-by":"crossref","first-page":"eaba1983","DOI":"10.1126\/sciadv.aba1983","article-title":"Single-cell RNA-seq reveals ectopic and aberrant lung-resident cell populations in idiopathic pulmonary fibrosis","volume":"6","author":"Adams","year":"2020","journal-title":"Sci Adv"},{"key":"2025100908011199900_ref38","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1038\/s41586-020-2922-4","article-title":"A molecular cell atlas of the human lung from single cell RNA sequencing","volume":"587","author":"Travaglini","year":"2020","journal-title":"Nature"},{"key":"2025100908011199900_ref39","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1126\/science.abc6261","article-title":"Systems biological assessment of immunity to mild versus severe COVID-19 infection in humans","volume":"369","author":"Arunachalam","year":"2020","journal-title":"Science"},{"key":"2025100908011199900_ref40","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1016\/j.cell.2020.08.001","article-title":"Severe COVID-19 is marked by a dysregulated myeloid cell compartment","volume":"182","author":"Schulte-Schrepping","year":"2020","journal-title":"Cell"},{"key":"2025100908011199900_ref41","doi-asserted-by":"crossref","first-page":"4383","DOI":"10.1038\/s41467-018-06318-7","article-title":"Single cell RNA sequencing of human liver reveals distinct intrahepatic macrophage populations","volume":"9","author":"MacParland","year":"2018","journal-title":"Nat Commun"},{"key":"2025100908011199900_ref42","doi-asserted-by":"publisher","first-page":"1867","DOI":"10.1038\/s41591-018-0269-2","article-title":"Single cell dissection of plasma cell heterogeneity in symptomatic and asymptomatic myeloma","volume":"24","author":"Ledergor","year":"2018","journal-title":"Nat Med"},{"key":"2025100908011199900_ref43","doi-asserted-by":"publisher","first-page":"D886","DOI":"10.1093\/nar\/gkae1142","article-title":"CZ CELLxGENE discover: A single-cell data platform for scalable exploration, analysis and modeling of aggregated data","volume":"53","author":"Abdulla","year":"2025","journal-title":"Nucleic Acids Res"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf523\/64536329\/bbaf523.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf523\/64536329\/bbaf523.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:01:19Z","timestamp":1760011279000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf523\/8276461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf523","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"type":"print","value":"1467-5463"},{"type":"electronic","value":"1477-4054"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,31]]},"article-number":"bbaf523"}}