Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

SANNO: A Graph-Transformer Enhanced Optimal Transport Tool for Spatial Transcriptomic Annotation.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: SANNO: A Graph-Transformer Enhanced Optimal Transport Tool for Spatial Transcriptomic Annotation.
Συγγραφείς: Zeng Y; School of Big Data and Software Engineering, Chongqing University, Chongqing, 400000, China. zengys@cqu.edu.cn.; Jinfeng Laboratory, Chongqing, 400000, China. zengys@cqu.edu.cn., Chen Y; Department of Pathology, Department of Medical Research Center, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China., Shangguan N; School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510000 , China., Li W; School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510000 , China., Cai X; School of Big Data and Software Engineering, Chongqing University, Chongqing, 400000, China., Zhang H; School of Big Data and Software Engineering, Chongqing University, Chongqing, 400000, China., Wang Z; Jinfeng Laboratory, Chongqing, 400000, China. biowz@mail.ustc.edu.cn., Zhao H; Department of Pathology, Department of Medical Research Center, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, 510120, China. zhaohy8@mail.sysu.edu.cn.
Πηγή: Interdisciplinary sciences, computational life sciences [Interdiscip Sci] 2026 Sep; Vol. 18 (3), pp. 1113-1127. Date of Electronic Publication: 2025 Aug 11.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Springer-Verlag Country of Publication: Germany NLM ID: 101515919 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1867-1462 (Electronic) Linking ISSN: 18671462 NLM ISO Abbreviation: Interdiscip Sci Subsets: MEDLINE
Imprint Name(s): Original Publication: [Heidelberg] : Springer-Verlag
Ιατρικοί όροι (MeSH): Computational Biology*/methods , Spatial Transcriptomics*, Software ; Algorithms ; Single-Cell Analysis ; Humans
Περίληψη: The latest progress in spatial transcriptomics has empowered scientists to investigate spatial heterogeneity with single-cell precision. A pivotal yet demanding aspect of spatial transcriptomics data analysis is cell type annotation. However, current methods exhibit limited performance as they are primarily designed for scRNA-seq data. Especially, these approaches often neglect spatial coordinate information and encounter challenges in identifying novel cell types. Here, we introduce SANNO, a novel approach that employs Optimal Transport (OT) to concurrently identify both known and novel cell types in spatially resolved single-cell data. Specifically, SANNO leverages a graph-Transformer module to model spatial coordinates and gene expression. This produces unified representations for both reference and query data. Building on this, SANNO employs a dual-strategy classifier. The first is an Unbalanced Optimal Transport (UOT) module that aligns query data with reference prototypes. The second is a self-supervised OT-based module that enhances global cluster separation and local cellular consistency, effectively eliminating batch effects. To further improve prediction accuracy, SANNO integrates an entropy-based re-weighted loss function. This significantly boosts the confidence of query cell predictions. Comprehensive experiments reveal that SANNO surpasses state-of-the-art techniques across both intra- and cross-spatial datasets, particularly in the identification of novel cell types. Additionally, SANNO demonstrates commendable performance in annotating cells within single-cell data, underscoring its potential as a versatile tool for cell annotation across single-cell and spatial transcriptomics datasets.
(© 2025. International Association of Scientists in the Interdisciplinary Areas.)
Competing Interests: Declarations. Conflict of interest: The authors declare that no competing interests exist.
References: Chen KH, Boettiger AN, Moffitt JR et al (2015) Spatially resolved, highly multiplexed RNA profiling in single cells. Science 348(6233):aaa6090.  https://doi.org/10.1126/science.aaa6090. (PMID: 10.1126/science.aaa6090258589774662681)
Hickey JW, Neumann EK, Radtke AJ et al (2022) Spatial mapping of protein composition and tissue organization: a primer for multiplexed antibody-based imaging. Nat Methods 19(3):284–295.  https://doi.org/10.1038/s41592-021-01316-y. (PMID: 10.1038/s41592-021-01316-y34811556)
Moses L, Pachter L (2022) Museum of spatial transcriptomics. Nat Methods 19(5):534–546.  https://doi.org/10.1038/s41592-022-01409-2. (PMID: 10.1038/s41592-022-01409-235273392)
Williams CG, Lee HJ, Asatsuma T et al (2022) An introduction to spatial transcriptomics for biomedical research. Genome Med 14(1):68.  https://doi.org/10.1186/s13073-022-01075-1. (PMID: 10.1186/s13073-022-01075-1357613619238181)
He S, Bhatt R, Brown C et al (2022) High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging. Nat Biotechnol 40(12):1794–1806. https://doi.org/10.1038/s41587-022-01483-z. (PMID: 10.1038/s41587-022-01483-z36203011)
Merritt CR, Ong GT, Church SE et al (2020) Multiplex digital spatial profiling of proteins and RNA in fixed tissue. Nat Biotechnol 38(5):586–599.  https://doi.org/10.1038/s41587-020-0472-9. (PMID: 10.1038/s41587-020-0472-932393914)
Bethani I, Skånland SS, Dikic I et al (2010) Spatial organization of transmembrane receptor signalling. EMBO J 29(16):2677–2688. https://doi.org/10.1038/emboj.2010.175. (PMID: 10.1038/emboj.2010.175207171382924650)
Manz BN, Groves JT (2010) Spatial organization and signal transduction at intercellular junctions. Nat Rev Mol Cell Biol 11(5):342–352.  https://doi.org/10.1038/nrm2883. (PMID: 10.1038/nrm2883203545363693730)
Huang Q, Liu Y, Du Y et al (2021) Evaluation of cell type annotation R packages on single-cell RNA-seq data. Genom Proteomics Bioinform 19(2):267–281.  https://doi.org/10.1016/j.gpb.2020.07.004. (PMID: 10.1016/j.gpb.2020.07.004)
Pasquini G, Arias JER, Schäfer P et al (2021) Automated methods for cell type annotation on scRNA-seq data. Comput Struct Biotechnol J 19:961–969.  https://doi.org/10.1016/j.csbj.2021.01.015. (PMID: 10.1016/j.csbj.2021.01.015336138637873570)
Chen J, Xu H, Tao W et al (2023) Transformer for one stop interpretable cell type annotation. Nat Commun 14(1):223. https://doi.org/10.1038/s41467-023-35923-4. (PMID: 10.1038/s41467-023-35923-4366415329840170)
Xu J, Lu C, Jin S et al (2025) Deep learning-based cell-specific gene regulatory networks inferred from single-cell multiome data. Nucleic Acids Res 53(5):gkaf138.  https://doi.org/10.1093/nar/gkaf138. (PMID: 10.1093/nar/gkaf1384003770911879466)
Li J, Chen S, Pan X et al (2022) Cell clustering for spatial transcriptomics data with graph neural networks. Nat Comput Sci 2(6):399–408.  https://doi.org/10.1038/s43588-022-00266-5. (PMID: 10.1038/s43588-022-00266-538177586)
Partel G, Wählby C (2021) Spage2vec: unsupervised representation of localized spatial gene expression signatures. FEBS J 288(6):1859–1870.  https://doi.org/10.1111/febs.15572. (PMID: 10.1111/febs.1557232976679)
Zhao E, Stone MR, Ren X et al (2021) Spatial transcriptomics at subspot resolution with BayesSpace. Nat Biotechnol 39(11):1375–1384.  https://doi.org/10.1038/s41587-021-00935-2. (PMID: 10.1038/s41587-021-00935-2340837918763026)
Hu J, Li X, Coleman K et al (2021) SpaGCN: integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nat Methods 18(11):1342–1351.  https://doi.org/10.1038/s41592-021-01255-8. (PMID: 10.1038/s41592-021-01255-834711970)
Zeng Z, Li Y, Li Y et al (2022) Statistical and machine learning methods for spatially resolved transcriptomics data analysis. Genome Biol 23(1):83.  https://doi.org/10.1186/s13059-022-02653-7. (PMID: 10.1186/s13059-022-02653-7353373748951701)
Zeng Y, Yin R, Luo M et al (2023) Identifying spatial domain by adapting transcriptomics with histology through contrastive learning. Brief Bioinform 24(2):bbad048.  https://doi.org/10.1093/bib/bbad048. (PMID: 10.1093/bib/bbad04836781228)
Codeluppi S, Borm LE, Zeisel A et al (2018) Spatial organization of the somatosensory cortex revealed by osmFISH. Nat Methods 15(11):932–935.  https://doi.org/10.1038/s41592-018-0175-z. (PMID: 10.1038/s41592-018-0175-z30377364)
Pandey S, Shekhar K, Regev A et al (2018) Comprehensive identification and spatial mapping of habenular neuronal types using single-cell RNA-seq. Curr Biol 28(7):1052–1065.  https://doi.org/10.1016/j.cub.2018.02.040. (PMID: 10.1016/j.cub.2018.02.040295764756042852)
Shekhar K, Lapan SW, Whitney IE et al (2016) Comprehensive classification of retinal bipolar neurons by single-cell transcriptomics. Cell 166(5):1308–1323.  https://doi.org/10.1016/j.cell.2016.07.054. (PMID: 10.1016/j.cell.2016.07.054275653515003425)
Ianevski A, Giri AK, Aittokallio T (2022) Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data. Nat Commun 13(1):1246.  https://doi.org/10.1038/s41467-022-28803-w. (PMID: 10.1038/s41467-022-28803-w352731568913782)
Vandereyken K, Sifrim A, Thienpont B et al (2023) Methods and applications for single-cell and spatial multi-omics. Nat Rev Genet 24(8):494–515.  https://doi.org/10.1038/s41576-023-00580-2. (PMID: 10.1038/s41576-023-00580-2368641789979144)
Hu J, Li X, Hu G et al (2020) Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis. Nat Mach Intell 2(10):607–618.  https://doi.org/10.1038/s42256-020-00233-7. (PMID: 10.1038/s42256-020-00233-7338175548009055)
Brbić M, Zitnik M, Wang S et al (2020) MARS: discovering novel cell types across heterogeneous single-cell experiments. Nat Methods 17(12):1200–1206.  https://doi.org/10.1038/s41592-020-00979-3. (PMID: 10.1038/s41592-020-00979-333077966)
Kimmel JC, Kelley DR (2021) Semisupervised adversarial neural networks for single-cell classification. Genome Res 31(10):1781–1793.  https://doi.org/10.1101/gr.268581.120. (PMID: 10.1101/gr.268581.120336274758494222)
Lotfollahi M, Naghipourfar M, Luecken MD et al (2022) Mapping single-cell data to reference atlases by transfer learning. Nat Biotechnol 40(1):121–130.  https://doi.org/10.1038/s41587-021-01001-7. (PMID: 10.1038/s41587-021-01001-734462589)
Xiong YX, Wang MG, Chen L et al (2023) Cell-type annotation with accurate unseen cell-type identification using multiple references. PLoS Comput Biol 19(6):e1011261.  https://doi.org/10.1371/journal.pcbi.1011261. (PMID: 10.1371/journal.pcbi.10112613737934110335708)
Brbić M, Cao K, Hickey JW et al (2022) Annotation of spatially resolved single-cell data with stellar. Nat Methods 19(11):1411–1418.  https://doi.org/10.1038/s41592-022-01651-8. (PMID: 10.1038/s41592-022-01651-83628072012186200)
Wu Q, Zhao W, Li Z et al (2022) NodeFormer: a scalable graph structure learning transformer for node classification. In: Proceedings of the 36th International Conference on Advances in Neural Information Processing Systems, pp 27387–27401. https://doi.org/10.5555/3600270.3602256.
Jang E, Gu S, Poole B (2016) Categorical reparameterization with gumbel-softmax. arXiv. http://arxiv.org/abs/1611.01144.
Rahimi A, Recht B (2007) Random features for large-scale kernel machines. In: Proceedings of the 21st International Conference on Neural Information Processing Systems, pp 1177–1184. https://doi.org/10.5555/2981562.2981710.
Bayati M, Montanari A (2011) The dynamics of message passing on dense graphs, with applications to compressed sensing. IEEE Trans Inf Theory 57(2):764–785.  https://doi.org/10.1109/TIT.2010.2094817. (PMID: 10.1109/TIT.2010.2094817)
Kingma DP, Salimans T, Welling M (2015) Variational dropout and the local reparameterization trick. In: Proceedings of the 29th International Conference on Neural Information Processing Systems, pp 2575–2583. https://doi.org/10.5555/2969442.2969527.
Maddison CJ, Mnih A, Teh YW (2016) The concrete distribution: a continuous relaxation of discrete random variables. arXiv. http://arxiv.org/abs/1611.00712.
Zeng Y, Zhou X, Rao J et al (2020) Accurately clustering single-cell RNA-seq data by capturing structural relations between cells through graph convolutional network. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp 519–522. https://www.biorxiv.org/content/biorxiv/early/2020/09/03/2020.09.02.278804.full.pdf.
Zeng Y, Wei Z, Pan Z et al (2022) A robust and scalable graph neural network for accurate single-cell classification. Brief Bioinform 23(2):bbab570.  https://doi.org/10.1093/bib/bbab570. (PMID: 10.1093/bib/bbab57035018408)
Caron M, Misra I, Mairal J et al (2020) Unsupervised learning of visual features by contrasting cluster assignments. Adv Neural Inf Process Syst 33:9912–9924.  https://doi.org/10.48550/arXiv.2006.09882. (PMID: 10.48550/arXiv.2006.09882)
Cuturi M (2013) Sinkhorn distances: lightspeed computation of optimal transport. Adv Neural Inf Process Syst 26:2292–2300.  https://doi.org/10.48550/arXiv.1306.0895. (PMID: 10.48550/arXiv.1306.0895)
Saito K, Saenko K (2021) OVANet: one-vs-all network for universal domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9000–9009. https://doi.org/10.48550/arXiv.2104.03344.
Saito K, Kim D, Sclaroff S et al (2020) Universal domain adaptation through self supervision. Adv Neural Inf Process Syst 33:16282–16292.  https://doi.org/10.48550/arXiv.2002.07953. (PMID: 10.48550/arXiv.2002.07953)
HuBMAP Consortium (2019) The human body at cellular resolution: the NIH Human Biomolecular Atlas Program. Nature 574(7777):187–192.  https://doi.org/10.1038/s41586-019-1629-x. (PMID: 10.1038/s41586-019-1629-x)
Moffitt JR, Bambah-Mukku D, Eichhorn SW et al (2018) Molecular, spatial, and functional single-cell profiling of the hypothalamic preoptic region. Science 362(6416):eaau5324.  https://doi.org/10.1126/science.aau5324. (PMID: 10.1126/science.aau5324303854646482113)
Kim J, Rustam S, Mosquera JM et al (2022) Unsupervised discovery of tissue architecture in multiplexed imaging. Nat Methods 19(12):1653–1661.  https://doi.org/10.1038/s41592-022-01657-2. (PMID: 10.1038/s41592-022-01657-23631656211102857)
Chen H, Murray E, Sinha A et al (2021) Dissecting mammalian spermatogenesis using spatial transcriptomics. Cell Rep 37(5):109915.  https://doi.org/10.1016/j.celrep.2021.109915. (PMID: 10.1016/j.celrep.2021.109915347316008606188)
Tran HTN, Ang KS, Chevrier M et al (2020) A benchmark of batch-effect correction methods for single-cell RNA sequencing data. Genome Biol 21:1–32.  https://doi.org/10.1186/s13059-019-1850-9. (PMID: 10.1186/s13059-019-1850-9)
Grant Information: 62402071 National Natural Science Foundation of China Youth Program; 2024M763866 China Postdoctoral Science Foundation; 2024IAIS-QN020 Fundamental Research Funds for the Central Universities; GZC20233321 Postdoctoral Fellowship Program of CPSF
Contributed Indexing: Keywords: Cell classification; Graph transformer; Spatial transcriptomics
Entry Date(s): Date Created: 20250811 Date Completed: 20260923 Latest Revision: 20260923
Update Code: 20260924
DOI: 10.1007/s12539-025-00752-0
PMID: 40789829
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1867-1462
DOI:10.1007/s12539-025-00752-0