{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T23:12:23Z","timestamp":1774048343931,"version":"3.50.1"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"vor","delay-in-days":24,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972299"],"award-info":[{"award-number":["61972299"]}],"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":["62172312"],"award-info":[{"award-number":["62172312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Single-cell sequencing technology has enabled researchers to study cellular heterogeneity at the cell level. To facilitate the downstream analysis, clustering single-cell data into subgroups is essential. However, the high dimensionality, sparsity, and dropout events of the data make the clustering challenging. Currently, many deep learning methods have been proposed. Nevertheless, they either fail to fully utilize pairwise distances information between similar cells, or do not adequately capture their feature correlations. They cannot also effectively handle high-dimensional sparse data. Therefore, they are not suitable for high-fidelity clustering, leading to difficulties in analyzing the clear cell types required for downstream analysis. The proposed scSAMAC method integrates contrastive learning and negative binomial losses into a variational autoencoder, extracting features via contrastive unit similarity while preserving the intrinsic characteristics. This enhances the robustness and generalization during the clustering. In the contrastive learning, it constructs a mask module by adopting a negative sample generation method with gene feature saliency adjustment, which selects features more influential in the clustering phase and simulates data missing events. Additionally, it develops a novel loss, which consists of a soft k-means loss, a Wasserstein distance, and a contrastive loss. This fully utilizes data information and improves clustering performance. Furthermore, a multi-head attention mechanism module is applied to the latent variables at each layer of autoencoder to enhance feature correlation, integration, and information repair. Experimental results demonstrate that scSAMAC outperforms several state-of-the-art clustering methods.<\/jats:p>","DOI":"10.1093\/bib\/bbaf128","type":"journal-article","created":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T10:14:46Z","timestamp":1743243286000},"source":"Crossref","is-referenced-by-count":3,"title":["scSAMAC: saliency-adjusted masking induced attention contrastive learning for single-cell clustering"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1009-7195","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]},{"name":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]}]},{"given":"Yongkang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]},{"name":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1348-8773","authenticated-orcid":false,"given":"Jing","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]},{"name":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]}]},{"given":"Shihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science , South-Central Minzu University, 182# Minyuan road, Hongshan District, Wuhan 430074,","place":["China"]}]},{"given":"Xiaolong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]},{"name":"Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System , Wuhan University of Science and Technology, Huangjiahu west road 2#, Wuhan 430065,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"key":"2025032603473336700_ref1","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1016\/j.molcel.2015.04.005","article-title":"The technology and biology of single-cell rna sequencing","volume":"58","author":"Kolodziejczyk","year":"2015","journal-title":"Mol Cell"},{"key":"2025032603473336700_ref2","first-page":"15710","article-title":"Effective clustering of scrna-seq data to identify biomarkers without user input","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chowdhury","year":"2021"},{"key":"2025032603473336700_ref3","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1038\/ejhg.2012.129","article-title":"Rna-seq and human complex diseases: Recent accomplishments and future perspectives","volume":"21","author":"Costa","year":"2013","journal-title":"Eur J Hum Genet"},{"key":"2025032603473336700_ref4","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1038\/s41576-018-0088-9","article-title":"Challenges in unsupervised clustering of single-cell rna-seq data","volume":"20","author":"Kiselev","year":"2019","journal-title":"Nat Rev Genet"},{"key":"2025032603473336700_ref5","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1038\/nmeth.4207","article-title":"Visualization and analysis of single-cell rna-seq data by kernel-based similarity learning","volume":"14","author":"Wang","year":"2017","journal-title":"Nat Methods"},{"key":"2025032603473336700_ref6","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1038\/nbt.3192","article-title":"Spatial reconstruction of single-cell gene expression data","volume":"33","author":"Satija","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2025032603473336700_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-0984-y","article-title":"Pcareduce: Hierarchical clustering of single cell transcriptional profiles","volume":"17","author":"\u017durauskien\u0117","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2025032603473336700_ref8","doi-asserted-by":"publisher","first-page":"bbab588","DOI":"10.1093\/bib\/bbab588","article-title":"Schfc: A hybrid fuzzy clustering method for single-cell rna-seq data optimized by natural computation","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025032603473336700_ref9","doi-asserted-by":"publisher","first-page":"106939","DOI":"10.1016\/j.compbiomed.2023.106939","article-title":"Clustering ensemble in scrna-seq data analysis: Methods, applications and challenges","volume":"159","author":"Nie","year":"2023","journal-title":"Comput Biol Med"},{"key":"2025032603473336700_ref10","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"2025032603473336700_ref11","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1109\/BIBM49941.2020.9313569","article-title":"Accurately clustering single-cell rna-seq data by capturing structural relations between cells through graph convolutional network","volume-title":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Zeng","year":"2020"},{"key":"2025032603473336700_ref12","doi-asserted-by":"crossref","first-page":"56","DOI":"10.18653\/v1\/P17-3010","article-title":"Variation autoencoder based network representation learning for classification","volume-title":"Proceedings of ACL 2017, Student Research Workshop","author":"Li","year":"2017"},{"key":"2025032603473336700_ref13","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1038\/s42256-019-0037-0","article-title":"Clustering single-cell rna-seq data with a model-based deep learning approach","volume":"1","author":"Tian","year":"2019","journal-title":"Nat Mach Intell"},{"key":"2025032603473336700_ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-07931-2","article-title":"Single-cell rna-seq denoising using a deep count autoencoder","volume":"10","author":"Eraslan","year":"2019","journal-title":"Nat Commun"},{"key":"2025032603473336700_ref15","doi-asserted-by":"publisher","DOI":"10.1093\/nargab\/lqaa039","article-title":"Deep soft k-means clustering with self-training for single-cell rna sequence data","volume":"2","author":"Chen","year":"2020","journal-title":"NAR Genomics Bioinform"},{"key":"2025032603473336700_ref16","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1186\/s12859-021-04210-8","article-title":"Contrastive self-supervised clustering of scrna-seq data","volume":"22","author":"Ciortan","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2025032603473336700_ref17","doi-asserted-by":"publisher","first-page":"107924","DOI":"10.1016\/j.compbiolchem.2023.107924","article-title":"Dual-gcn-based deep clustering with triplet contrast for scrna-seq data analysis","volume":"106","author":"Wang","year":"2023","journal-title":"Comput Biol Chem"},{"key":"2025032603473336700_ref18","doi-asserted-by":"publisher","first-page":"bbae477","DOI":"10.1093\/bib\/bbae477","article-title":"Nsdcc: Dual-level contrastive clustering with nonuniform sampling for scrna-seq data analysis","volume":"25","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025032603473336700_ref19","doi-asserted-by":"crossref","first-page":"bbad216","DOI":"10.1093\/bib\/bbad216","article-title":"Scdfc: A deep fusion clustering method for single-cell rna-seq data","volume":"24","author":"Dayu","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025032603473336700_ref20","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1093\/bfgp\/elad017","article-title":"Single-cell rna-seq data clustering by deep information fusion","volume":"23","author":"Ren","year":"2024","journal-title":"Brief Funct Genomics"},{"key":"2025032603473336700_ref21","article-title":"High-order topology for deep single-cell multi-view fuzzy clustering","volume":"32","author":"Dayu","year":"2024","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"2025032603473336700_ref22","doi-asserted-by":"crossref","first-page":"1","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":"2025032603473336700_ref23","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"2025032603473336700_ref24","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"2025032603473336700_ref25","first-page":"583","article-title":"Cluster ensembles\u2014A knowledge reuse framework for combining multiple partitions","volume":"3","author":"Strehl","year":"2002","journal-title":"J Mach Learn Res"},{"key":"2025032603473336700_ref26","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Nav Res Logist Q"},{"key":"2025032603473336700_ref27","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1971.10482356","article-title":"Objective criteria for the evaluation of clustering methods","volume":"66","author":"Rand","year":"1971","journal-title":"J Am Stat Assoc"},{"key":"2025032603473336700_ref28","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"Hubert","year":"1985","journal-title":"J Classif"},{"key":"2025032603473336700_ref29","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1093\/bioinformatics\/btac011","article-title":"Scname: Neighborhood contrastive clustering with ancillary mask estimation for scrna-seq data","volume":"38","author":"Wan","year":"2022","journal-title":"Bioinformatics"},{"key":"2025032603473336700_ref30","doi-asserted-by":"publisher","first-page":"1873","DOI":"10.1038\/s41467-021-22008-3","article-title":"Model-based deep embedding for constrained clustering analysis of single cell rna-seq data","volume":"12","author":"Tian","year":"2021","journal-title":"Nat Commun"},{"key":"2025032603473336700_ref31","doi-asserted-by":"publisher","first-page":"e1010772","DOI":"10.1371\/journal.pcbi.1010772","article-title":"Scdssc: Deep sparse subspace clustering for scrna-seq data","volume":"18","author":"Wang","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2025032603473336700_ref32","doi-asserted-by":"publisher","first-page":"bbac625","DOI":"10.1093\/bib\/bbac625","article-title":"Scdcca: Deep contrastive clustering for single-cell rna-seq data based on auto-encoder network","volume":"24","author":"Wang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025032603473336700_ref33","doi-asserted-by":"publisher","first-page":"btae293","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":"2025032603473336700_ref34","doi-asserted-by":"publisher","first-page":"bbac585","DOI":"10.1093\/bib\/bbac585","article-title":"Scgmaae: Gaussian mixture adversarial autoencoders for diversification analysis of scrna-seq data","volume":"24","author":"Wang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025032603473336700_ref35","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1101\/gr.254557.119","article-title":"Sharp: Hyperfast and accurate processing of single-cell rna-seq data via ensemble random projection","volume":"30","author":"Wan","year":"2020","journal-title":"Genome Res"},{"key":"2025032603473336700_ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-26085-2","article-title":"Dubstepr is a scalable correlation-based feature selection method for accurately clustering single-cell data","volume":"12","author":"Ranjan","year":"2021","journal-title":"Nat Commun"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf128\/62699978\/bbaf128.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf128\/62699978\/bbaf128.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T10:15:26Z","timestamp":1743243326000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf128\/8093114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf128","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf128"}}