{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:28:24Z","timestamp":1767378504994,"version":"3.48.0"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62306142"],"award-info":[{"award-number":["No.62306142"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Funding Program for Excellent Postdoctoral Talent","award":["2023ZB224"],"award-info":[{"award-number":["2023ZB224"]}]},{"name":"Natural Science Foundation of the Higher Education Institutions of Jiangsu Province of China","award":["24KJB520041"],"award-info":[{"award-number":["24KJB520041"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Accurate cell type annotation is fundamental to single-cell analysis, yet remains challenging across heterogeneous datasets and modalities. In particular, transferring labels between scRNA-seq and scATAC-seq data poses unique difficulties due to discrepancies in sequencing protocols and feature spaces. Existing methods typically handle only a subset of these challenges, often requiring scenario-specific adjustments and offering limited interpretability. Here, we present CellPredX, a structurally unified but adaptively parameterized, semi-supervised cross-modality framework for label transfer across scRNA-seq, scATAC-seq, and cross-protocol datasets. While maintaining a unified model architecture and optimization strategy, CellPredX allows adaptive tuning of loss-weight hyperparameters to account for the varying degree of similarity or discrepancy between different reference\u2013query dataset pairs. CellPredX integrates domain adaptation and deep metric learning to align heterogeneous embeddings, and introduces a sparse center loss with an attention mechanism to enhance discriminative representations while suppressing noise. Moreover, an integrated interpreter module based on gradient attribution enables biological interpretability by identifying key markers and feature dimensions driving model predictions. Through extensive benchmarking across scRNA to scATAC, scATAC to scATAC, and scRNA to scRNA transfers, CellPredX consistently outperforms state-of-the-art annotation methods in both accuracy and robustness. The interpreter module further reveals biologically meaningful marker patterns that are consistent with known cell hierarchies. Together, these results demonstrate that CellPredX provides an interpretable and scalable solution for cross-modality cell type annotation in single-cell multi-omic integration.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013824","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:23:24Z","timestamp":1767378204000},"page":"e1013824","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["CellPredX, a computational framework for cross-data type, cross-sample, and cross-protocol cell type annotation through domain adaptation and deep metric learning"],"prefix":"10.1371","volume":"22","author":[{"given":"Yan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yu","family":"Xia","sequence":"additional","affiliation":[]},{"given":"He","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Long-Chen","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Yiheng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Ji-Peng","family":"Qiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2525-1776","authenticated-orcid":true,"given":"Guo","family":"Wei","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"issue":"11","key":"pcbi.1013824.ref001","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1038\/s41576-023-00618-5","article-title":"Gene regulatory network inference in the era of single-cell multi-omics","volume":"24","author":"P Badia-I-Mompel","year":"2023","journal-title":"Nat Rev Genet"},{"issue":"12","key":"pcbi.1013824.ref002","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.1038\/s41587-023-01716-9","article-title":"SEACells infers transcriptional and epigenomic cellular states from single-cell genomics data","volume":"41","author":"S Persad","year":"2023","journal-title":"Nat Biotechnol"},{"issue":"5","key":"pcbi.1013824.ref003","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1038\/s41569-022-00805-7","article-title":"Single-cell transcriptomics for the assessment of cardiac disease","volume":"20","author":"AMA Miranda","year":"2023","journal-title":"Nat Rev Cardiol"},{"issue":"1","key":"pcbi.1013824.ref004","first-page":"1","article-title":"scSorter: assigning cells to known cell types according to marker genes","volume":"22","author":"H Guo","year":"2021","journal-title":"Genome biology"},{"issue":"1","key":"pcbi.1013824.ref005","doi-asserted-by":"crossref","first-page":"6495","DOI":"10.1038\/s41467-023-41855-w","article-title":"Benchmarking strategies for cross-species integration of single-cell RNA sequencing data","volume":"14","author":"Y Song","year":"2023","journal-title":"Nat Commun"},{"key":"pcbi.1013824.ref006","first-page":"1","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","author":"H Cui","year":"2024","journal-title":"Nat Methods"},{"issue":"10","key":"pcbi.1013824.ref007","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":"6","key":"pcbi.1013824.ref008","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/s41587-020-0469-4","article-title":"Benchmarking single-cell RNA-sequencing protocols for cell atlas projects","volume":"38","author":"E Mereu","year":"2020","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1013824.ref009","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1038\/s41467-024-45198-y","article-title":"The impacts of active and self-supervised learning on efficient annotation of single-cell expression data","volume":"15","author":"MJ Geuenich","year":"2024","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1013824.ref010","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":"1","key":"pcbi.1013824.ref011","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.1013824.ref012","article-title":"Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models","volume":"17","author":"C Xu","year":"2021","journal-title":"Mol Syst Biol"},{"issue":"13","key":"pcbi.1013824.ref013","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Y Hao","year":"2021","journal-title":"Cell"},{"issue":"2","key":"pcbi.1013824.ref014","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s42256-021-00432-w","article-title":"Cell type annotation of single-cell chromatin accessibility data via supervised Bayesian embedding","volume":"4","author":"X Chen","year":"2022","journal-title":"Nat Mach Intell"},{"key":"pcbi.1013824.ref015","article-title":"scATAnno: automated cell type annotation for single-cell ATAC sequencing data","author":"Y Jiang","year":"2023","journal-title":"bioRxiv"},{"issue":"1","key":"pcbi.1013824.ref016","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1038\/s41467-023-37439-3","article-title":"Cellcano: supervised cell type identification for single cell ATAC-seq data","volume":"14","author":"W Ma","year":"2023","journal-title":"Nature Communications"},{"key":"pcbi.1013824.ref017","first-page":"1","article-title":"Deciphering cell types by integrating scATAC-seq data with genome sequences","author":"Y Zeng","year":"2024","journal-title":"Nat Comput Sci"},{"issue":"5","key":"pcbi.1013824.ref018","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1038\/s41587-021-01161-6","article-title":"scJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning","volume":"40","author":"Y Lin","year":"2022","journal-title":"Nat Biotechnol"},{"issue":"8","key":"pcbi.1013824.ref019","article-title":"scNCL: transferring labels from scRNA-seq to scATAC-seq data with neighborhood contrastive regularization","volume":"39","author":"X Yan","year":"2023","journal-title":"Bioinformatics"},{"issue":"10","key":"pcbi.1013824.ref020","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":"5","key":"pcbi.1013824.ref021","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s43588-022-00251-y","article-title":"Adversarial domain translation networks for integrating large-scale atlas-level single-cell datasets","volume":"2","author":"J Zhao","year":"2022","journal-title":"Nat Comput Sci"},{"issue":"10","key":"pcbi.1013824.ref022","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/s42256-020-00233-7","article-title":"Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis","volume":"2","author":"J Hu","year":"2020","journal-title":"Nat Mach Intell"},{"issue":"1","key":"pcbi.1013824.ref023","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1038\/s41587-021-01001-7","article-title":"Mapping single-cell data to reference atlases by transfer learning","volume":"40","author":"M Lotfollahi","year":"2022","journal-title":"Nat Biotechnol"},{"issue":"8","key":"pcbi.1013824.ref024","doi-asserted-by":"crossref","first-page":"5743","DOI":"10.1109\/TPAMI.2024.3370978","article-title":"A comprehensive survey on source-free domain adaptation","volume":"46","author":"J Li","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1013824.ref025","doi-asserted-by":"crossref","first-page":"109381","DOI":"10.1016\/j.patcog.2023.109381","article-title":"Deep metric learning for few-shot image classification: a review of recent developments","volume":"138","author":"X Li","year":"2023","journal-title":"Pattern Recognit"},{"key":"pcbi.1013824.ref026","unstructured":"Kokhlikyan N, Miglani V, Martin M, Wang E, Alsallakh B, Reynolds J, et al. Captum: a unified and generic model interpretability library for pytorch. arXiv preprint. 2020. doi: 10.48550\/arXiv.2009.07896"},{"issue":"3","key":"pcbi.1013824.ref027","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1109\/TPAMI.2019.2945942","article-title":"A review of domain adaptation without target labels","volume":"43","author":"WM Kouw","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intellig"},{"key":"pcbi.1013824.ref028","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume":"29","author":"K Sohn","year":"2016","journal-title":"Adv Neural Inform Process Syst"},{"key":"pcbi.1013824.ref029","doi-asserted-by":"crossref","unstructured":"Chen G, Lu Y, Lu J, Zhou J. Deep credible metric learning for unsupervised domain adaptation person re-identification. pp. 643\u201359.","DOI":"10.1007\/978-3-030-58598-3_38"},{"issue":"2","key":"pcbi.1013824.ref030","first-page":"1","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"KQ Weinberger","year":"2009","journal-title":"J Mach Learning Res"},{"issue":"2","key":"pcbi.1013824.ref031","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","article-title":"Domain adaptation via transfer component analysis","volume":"22","author":"SJ Pan","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"pcbi.1013824.ref032","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"key":"pcbi.1013824.ref033","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R. Momentum contrast for unsupervised visual representation learning. p. 9729\u201338."},{"key":"pcbi.1013824.ref034","unstructured":"Farzaneh AH, Qi X. Facial expression recognition in the wild via deep attentive center loss. p. 2402\u201311."},{"issue":"3","key":"pcbi.1013824.ref035","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1189\/jlb.0806510","article-title":"The CD14+ CD16+ blood monocytes: their role in infection and inflammation","volume":"81","author":"L Ziegler-Heitbrock","year":"2007","journal-title":"J Leukoc Biol"},{"key":"pcbi.1013824.ref036","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.molimm.2020.01.014","article-title":"Dapk1 improves inflammation, oxidative stress and autophagy in LPS-induced acute lung injury via p38MAPK\/NF-\u03baB signaling pathway","volume":"120","author":"T Li","year":"2020","journal-title":"Mol Immunol"},{"issue":"6518","key":"pcbi.1013824.ref037","doi-asserted-by":"crossref","DOI":"10.1126\/science.aba7612","article-title":"A human cell atlas of fetal chromatin accessibility","volume":"370","author":"S Domcke","year":"2020","journal-title":"Science"},{"issue":"1","key":"pcbi.1013824.ref038","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","article-title":"Benchmarking atlas-level data integration in single-cell genomics","volume":"19","author":"MD Luecken","year":"2022","journal-title":"Nat Methods"},{"issue":"6518","key":"pcbi.1013824.ref039","article-title":"A human cell atlas of fetal gene expression","volume":"370","author":"J Cao","year":"2020","journal-title":"Science"},{"issue":"10","key":"pcbi.1013824.ref040","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41587-021-00927-2","article-title":"Scalable, multimodal profiling of chromatin accessibility, gene expression and protein levels in single cells","volume":"39","author":"EP Mimitou","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"11","key":"pcbi.1013824.ref041","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1038\/s41592-021-01282-5","article-title":"Single-cell chromatin state analysis with Signac","volume":"18","author":"T Stuart","year":"2021","journal-title":"Nat Methods"},{"key":"pcbi.1013824.ref042","doi-asserted-by":"crossref","unstructured":"Wen Y, Zhang K, Li Z, Qiao Y. A discriminative feature learning approach for deep face recognition. p. 499\u2013515.","DOI":"10.1007\/978-3-319-46478-7_31"},{"issue":"2","key":"pcbi.1013824.ref043","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1038\/s41587-023-01767-y","article-title":"Dictionary learning for integrative, multimodal and scalable single-cell analysis","volume":"42","author":"Y Hao","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"2","key":"pcbi.1013824.ref044","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.cels.2019.06.004","article-title":"SingleCellNet: a computational tool to classify single cell RNA-Seq data across platforms and across species","volume":"9","author":"Y Tan","year":"2019","journal-title":"Cell Systems"},{"issue":"2","key":"pcbi.1013824.ref045","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"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:23:32Z","timestamp":1767378212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013824"}},"subtitle":[],"editor":[{"given":"Feng","family":"Bao","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013824","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]}}}