{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T14:16:12Z","timestamp":1785161772725,"version":"3.55.0"},"reference-count":49,"publisher":"American Chemical Society (ACS)","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100010023","name":"Natural Science Research of Jiangsu Higher Education Institutions of China","doi-asserted-by":"publisher","award":["24KJB520041"],"award-info":[{"award-number":["24KJB520041"]}],"id":[{"id":"10.13039\/501100010023","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010814","name":"Anhui Provincial Department of Education","doi-asserted-by":"publisher","award":["2025AHGXZK40444"],"award-info":[{"award-number":["2025AHGXZK40444"]}],"id":[{"id":"10.13039\/501100010814","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306142"],"award-info":[{"award-number":["62306142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Single-cell proteomic data generated by mass spectrometry-based technologies provide direct insights into cellular functional states and have become increasingly important for revealing cellular heterogeneity in complex biological systems. Accurate clustering of such data is essential for identifying functionally distinct cell subpopulations and understanding biological processes such as immune responses, tumor heterogeneity, and cell fate regulation. However, mass spectrometry-based single-cell proteomic data are often characterized by high dimensionality, measurement noise, technical bias, and complex nonlinear structures, which pose major challenges to conventional clustering methods. To address these issues, this study proposes a gradient-information-guided graph contrastive learning framework for single-cell proteomic clustering. The proposed method adaptively reconstructs intercellular relationship graphs through gradient-guided structure learning and introduces a gradient-weighted contrastive loss to alleviate the influence of false-negative samples. By better preserving similarity among biologically related cells, the framework learns more robust and biologically meaningful representations. Experimental results on multiple data sets demonstrate that the proposed method outperforms conventional clustering approaches and existing graph contrastive learning methods in terms of clustering accuracy, stability, and biological consistency. Overall, this work provides an effective framework for clustering mass spectrometry-based single-cell proteomic data and offers new insights into the application of graph contrastive learning in bioinformatics.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01102","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:21:31Z","timestamp":1784146891000},"page":"8620-8632","source":"Crossref","is-referenced-by-count":0,"title":["Gradient-Guided\nGraph Contrastive Learning for Mass\nSpectrometry-Based Proteomics Clustering"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5331-3655","authenticated-orcid":true,"given":"Yan","family":"Liu","sequence":"first","affiliation":[{"name":"Yangzhou University , , , ,","place":["Yangzhou, Jiangsu, China, 225100"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai-Yuan","family":"Xia","sequence":"additional","affiliation":[{"name":"Yangzhou University , , , ,","place":["Yangzhou, Jiangsu, China, 225100"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guo","family":"Wei","sequence":"additional","affiliation":[{"name":"Bengbu University , , , ,","place":["Bengbu, Anhui, China, 233030"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Yan","sequence":"additional","affiliation":[{"name":"Nanjing Forestry University , , , ,","place":["Nanjing, Jiangsu, China, 210037"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0045-4745","authenticated-orcid":true,"given":"Long-Chen","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology , , , ,","place":["Nanjing, Jiangsu, China, 210094"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Nanjing Agricultural University , , , ,","place":["Nanjing, Jiangsu, China, 211800"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji-Peng","family":"Qiang","sequence":"additional","affiliation":[{"name":"Yangzhou University , , , ,","place":["Yangzhou, Jiangsu, China, 225100"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Yangzhou University , , , ,","place":["Yangzhou, Jiangsu, China, 225100"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"issue":"1","key":"2026072709091356300_cit1","doi-asserted-by":"publisher","first-page":"5910","DOI":"10.1038\/s41467-023-41602-1","article-title":"Exploration of cell\nstate heterogeneity using single-cell proteomics through sensitivity-tailored\ndata-independent acquisition","volume":"14","author":"Petrosius","year":"2023","journal-title":"Nat. Commun."},{"key":"2026072709091356300_cit2","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/s41592-020-01002-5","article-title":"Defining the carrier\nproteome limit for single-cell\nproteomics","volume":"18","author":"Cheung","year":"2021","journal-title":"Nat. Methods"},{"key":"2026072709091356300_cit3","doi-asserted-by":"publisher","first-page":"5893","DOI":"10.1021\/acs.analchem.5c00661","article-title":"Trends\nin Mass Spectrometry-Based Single-Cell Proteomics","volume":"97","author":"Sanchez-Avila","year":"2025","journal-title":"Anal. Chem."},{"issue":"1","key":"2026072709091356300_cit4","doi-asserted-by":"publisher","first-page":"10100","DOI":"10.1038\/s41467-024-54438-0","article-title":"Multimodal single cell-resolved spatial proteomics reveal pancreatic\ntumor heterogeneity","volume":"15","author":"Xu","year":"2024","journal-title":"Nat. Commun."},{"key":"2026072709091356300_cit5","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1186\/s13059-025-03719-y","article-title":"Comparative\nbenchmarking of single-cell clustering algorithms for transcriptomic\nand proteomic data","volume":"26","author":"Yin","year":"2025","journal-title":"Genome Biol."},{"key":"2026072709091356300_cit6","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1126\/science.aaz6695","article-title":"Unpicking\nthe proteome in single cells","volume":"367","author":"Slavov","year":"2020","journal-title":"Science"},{"key":"2026072709091356300_cit7","doi-asserted-by":"publisher","first-page":"6889","DOI":"10.1007\/s00216-023-04759-8","article-title":"A review of the current\nstate of single-cell proteomics\nand future perspective","volume":"415","author":"Ahmad","year":"2023","journal-title":"Anal. Bioanal. Chem."},{"key":"2026072709091356300_cit8","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1038\/s41592-024-02559-1","article-title":"Challenging\nthe Astral mass analyzer to quantify\nup to 5,300 proteins per single cell at unseen accuracy to uncover\ncellular heterogeneity","volume":"22","author":"Bubis","year":"2025","journal-title":"Nat. Methods"},{"key":"2026072709091356300_cit9","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1080\/14789450.2021.1988571","article-title":"Replication of single-cell\nproteomics data reveals important computational\nchallenges","volume":"18","author":"Vanderaa","year":"2021","journal-title":"Expert Rev. Proteomics"},{"key":"2026072709091356300_cit10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cbpa.2020.04.018","article-title":"Single-cell\nprotein analysis by mass spectrometry","volume":"60","author":"Slavov","year":"2021","journal-title":"Curr.\nOpin. Chem. Biol."},{"key":"2026072709091356300_cit11","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1038\/s41587-022-01302-5","article-title":"Deep Visual Proteomics\ndefines single-cell identity and heterogeneity","volume":"40","author":"Mund","year":"2022","journal-title":"Nat. Biotechnol."},{"key":"2026072709091356300_cit12","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/TCBBIO.2024.3515053","article-title":"sigrgcn:\nA robust\nresidual graph convolutional network for scrna-seq data clustering","volume":"22","author":"Shu","year":"2025","journal-title":"IEEE Trans. Comput. Biol. Bioinf."},{"key":"2026072709091356300_cit13","doi-asserted-by":"publisher","first-page":"bbae562","DOI":"10.1093\/bib\/bbae562","article-title":"Multi-level multi-view\nnetwork based on structural contrastive learning for scRNA-seq data\nclustering","volume":"25","author":"Shu","year":"2024","journal-title":"Briefings Bioinf."},{"key":"2026072709091356300_cit14","doi-asserted-by":"publisher","first-page":"6271","DOI":"10.1021\/acs.jcim.2c01305","article-title":"Robust\ngraph regularized NMF with dissimilarity and similarity constraints\nfor ScRNA-seq data clustering","volume":"62","author":"Shu","year":"2022","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026072709091356300_cit15","doi-asserted-by":"publisher","first-page":"2786","DOI":"10.1109\/TCBBIO.2025.3600651","article-title":"scSAG2E: Sparse Autoencoders\nWith Gene Graph Embedding for scRNA-Seq\nData Clustering","volume":"22","author":"Xia","year":"2025","journal-title":"IEEE Trans. Comput. Biol. Bioinf."},{"key":"2026072709091356300_cit16","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1109\/TNNLS.2025.3610024","article-title":"Multiscale Contrastive Learning for\nNode Clustering\nBased on Variational Graph Auto-Encoder","volume":"37","author":"Aghayengejeh","year":"2026","journal-title":"IEEE\nTrans. Neural Netw. Learn. Syst."},{"key":"2026072709091356300_cit17","doi-asserted-by":"publisher","first-page":"117374","DOI":"10.1016\/j.chaos.2025.117374","article-title":"SCGC-JWAF:\nShallow contrastive graph\nclustering with Jaccard-based weighted adaptive filtering","volume":"201","author":"Aghayengejeh","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"2026072709091356300_cit18","doi-asserted-by":"publisher","first-page":"114975","DOI":"10.1016\/j.knosys.2025.114975","article-title":"DeepCut++:\nGraph-based unsupervised segmentation with feature fusion and diffusion\nlearning","volume":"334","author":"Pourhaji Aghayengejeh","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"2026072709091356300_cit19","doi-asserted-by":"publisher","first-page":"100792","DOI":"10.1016\/j.cosrev.2025.100792","article-title":"Revolutionizing\ntextual data insights:\nA comprehensive review of the dual relationship between transformers\nand clustering in textual data analysis","volume":"58","author":"Aghayengejeh","year":"2025","journal-title":"Comput.\nSci. Rev."},{"key":"2026072709091356300_cit20","doi-asserted-by":"publisher","first-page":"4121","DOI":"10.1109\/TKDE.2026.3680286","article-title":"Beyond Predefined\nClusters: A Comprehensive Review of Clustering Methods for Unknown\nCluster Numbers","volume":"38","author":"Aghayengejeh","year":"2026","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2026072709091356300_cit21","doi-asserted-by":"publisher","first-page":"100974","DOI":"10.1016\/j.cosrev.2026.100974","article-title":"From embeddings\nto interpretations: A comprehensive review of language models in clustering","volume":"61","author":"Aghayengejeh","year":"2026","journal-title":"Comput. Sci. Rev."},{"key":"2026072709091356300_cit22","article-title":"Semi-Supervised\nClassification with Graph Convolutional Networks","volume-title":"Proceedings Of The International Conference On Learning\nRepresentations (ICLR)","author":"Kipf","year":"2017"},{"issue":"1","key":"2026072709091356300_cit23","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s43586-024-00294-7","article-title":"Graph neural\nnetworks","volume":"4","author":"Corso","year":"2024","journal-title":"Nat. Rev. Methods Primers"},{"key":"2026072709091356300_cit24","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive\nsurvey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans.\nNeural Netw. Learn. Syst"},{"key":"2026072709091356300_cit25","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TKDE.2021.3090866","article-title":"Self-supervised learning: Generative\nor contrastive","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"2026072709091356300_cit26","first-page":"18661","article-title":"Supervised\ncontrastive learning","volume-title":"Proceedings of the 34th\nInternational Conference on Neural Information Processing Systems","author":"Khosla","year":"2020"},{"key":"2026072709091356300_cit27","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1038\/s41592-024-02214-9","article-title":"scPROTEIN: A versatile deep graph\ncontrastive learning framework for single-cell proteomics embedding","volume":"21","author":"Li","year":"2024","journal-title":"Nat. Methods"},{"key":"2026072709091356300_cit28","first-page":"1597","article-title":"A Simple Framewpork\nfor Contrastive Learning of Visual Representations","volume-title":"Proceedings Of The 37th International Conference On Machine\nLearning","author":"Chen","year":"2020"},{"key":"2026072709091356300_cit29","doi-asserted-by":"publisher","first-page":"8544","DOI":"10.1609\/aaai.v38i8.28698","article-title":"Regcl: Rethinking message passing in graph contrastive\nlearning","volume":"38","author":"Ji","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2026072709091356300_cit30","doi-asserted-by":"publisher","DOI":"10.1101\/2023.06.20.545604","article-title":"QuantUMS: Uncertainty\nMinimisation Enables Confident Quantification in Proteomics","author":"Kistner","year":"2023","journal-title":"bioRxiv"},{"key":"2026072709091356300_cit31","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proceedings of pthe 34th International Conference on Neural Information\nProcessing Systems","author":"You","year":"2020"},{"key":"2026072709091356300_cit32","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1145\/3485447.3512156","article-title":"Simgrace: A simple framework for graph\ncontrastive\nlearning without data augmentation","volume-title":"Proceedings\nof the ACM Web Conference 2022","author":"Xia","year":"2022"},{"key":"2026072709091356300_cit33","first-page":"21","article-title":"Mixhop:\nHigher-order graph convolutional architectures via sparsified neighborhood\nmixing","volume-title":"Proceedings of the 36 th International\nConference on MachineLearning","author":"Abu-El-Haija","year":"2019"},{"key":"2026072709091356300_cit34","article-title":"Combining neural\nnetworks with personalized pagerank for classification on graphs","volume-title":"International Conference On Learning Representations (LCLR)","author":"Klicpera","year":"2019"},{"key":"2026072709091356300_cit35","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1016\/j.imavis.2008.05.002","article-title":"Benchmarking\ngraph-based\nclustering algorithms","volume":"27","author":"Foggia","year":"2009","journal-title":"Image And Vision Comput."},{"key":"2026072709091356300_cit36","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","article-title":"Benchmarking atlas-level\ndata integration in single-cell genomics","volume":"19","author":"Luecken","year":"2022","journal-title":"Nat.\nMethods"},{"key":"2026072709091356300_cit37","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1080\/01621459.1983.10478008","article-title":"A method for comparing two hierarchical clusterings","volume":"78","author":"Fowlkes","year":"1983","journal-title":"J. Am. Stat. Assoc."},{"key":"2026072709091356300_cit38","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1016\/j.cell.2018.05.061","article-title":"Recovering gene interactions from single-cell\ndata using data diffusion","volume":"174","author":"Van Dijk","year":"2018","journal-title":"Cell"},{"key":"2026072709091356300_cit39","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","article-title":"Fast, sensitive\nand accurate integration of single-cell data with Harmony","volume":"16","author":"Korsunsky","year":"2019","journal-title":"Nat. Methods"},{"key":"2026072709091356300_cit40","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1038\/s41467-022-29576-y","article-title":"A universal deep neural network for\nin-depth cleaning of single-cell RNA-Seq data","volume":"13","author":"Li","year":"2022","journal-title":"Nat. Commun."},{"key":"2026072709091356300_cit41","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1038\/s41587-019-0113-3","article-title":"Efficient\nintegration of heterogeneous\nsingle-cell transcriptomes using Scanorama","volume":"37","author":"Hie","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"2026072709091356300_cit42","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TKDE.2025.3622998","article-title":"Trustworthy Neighborhoods\nMining: Homophily-Aware Neutral\nContrastive Learning for Graph Clustering","volume":"38","author":"Peng","year":"2026","journal-title":"IEEE\nTrans. Knowl. Data Eng."},{"key":"2026072709091356300_cit43","first-page":"3534","article-title":"Universal graph self-contrastive\nlearning","volume-title":"Propceedings Of The Thirty-Fourth\nInternational Joint Conference On Artificial Intelligence","author":"Yang","year":"2025"},{"key":"2026072709091356300_cit44","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s13059-021-02267-5","article-title":"Single-cell\nproteomic and transcriptomic analysis of macrophage heterogeneity\nusing SCoPE2","volume":"22","author":"Specht","year":"2021","journal-title":"Genome Biol."},{"key":"2026072709091356300_cit45","doi-asserted-by":"publisher","first-page":"13119","DOI":"10.1021\/acs.analchem.9b03349","article-title":"High-throughput single cell proteomics\nenabled\nby multiplex isobaric labeling in a nanodroplet sample preparation\nplatform","volume":"91","author":"Dou","year":"2019","journal-title":"Anal. Chem."},{"issue":"1","key":"2026072709091356300_cit46","doi-asserted-by":"publisher","first-page":"6246","DOI":"10.1038\/s41467-021-26514-2","article-title":"High-throughput and high-efficiency sample\npreparation for single-cell proteomics using a nested nanowell chip","volume":"12","author":"Woo","year":"2021","journal-title":"Nat. Commun."},{"key":"2026072709091356300_cit47","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1186\/s13059-022-02817-5","article-title":"Exploring\nfunctional protein covariation across single cells using nPOP","volume":"23","author":"Leduc","year":"2022","journal-title":"Genome Biol."},{"key":"2026072709091356300_cit48","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1038\/s41587-022-01389-w","article-title":"Increasing the throughput\nof sensitive proteomics by\nplexDIA","volume":"41","author":"Derks","year":"2023","journal-title":"Nat. Biotechnol."},{"key":"2026072709091356300_cit49","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1038\/s41592-023-01830-1","article-title":"Prioritized\nmass spectrometry increases the depth,\nsensitivity and data completeness of single-cell proteomics","volume":"20","author":"Huffman","year":"2023","journal-title":"Nat. Methods"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01102","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8620\/65966858\/acs.jcim.6c01102.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/8620\/65966858\/acs.jcim.6c01102.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:29:34Z","timestamp":1785158974000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/14\/8620\/5211352\/Gradient-Guided-Graph-Contrastive-Learning-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":49,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7,15]]},"published-print":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01102","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}