{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:35:20Z","timestamp":1775097320259,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The Israeli Council for Higher Education Ph.D. fellowship The Center for Interdisciplinary Data Science Research at the Hebrew University of Jerusalem"},{"name":"Minerva Center on Cell Intelligence"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-024-00721-5","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:03:11Z","timestamp":1733288591000},"page":"941-954","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Interpreting single-cell and spatial omics data using deep neural network training dynamics"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8398-6025","authenticated-orcid":false,"given":"Jonathan","family":"Karin","sequence":"first","affiliation":[]},{"given":"Reshef","family":"Mintz","sequence":"additional","affiliation":[]},{"given":"Barak","family":"Raveh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0074-9196","authenticated-orcid":false,"given":"Mor","family":"Nitzan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"721_CR1","doi-asserted-by":"publisher","first-page":"vbad030","DOI":"10.1093\/bioadv\/vbad030","volume":"3","author":"X Ji","year":"2023","unstructured":"Ji, X. et al. scannotate: an automated cell-type annotation tool for single-cell RNA-sequencing data. Bioinform. Adv. 3, vbad030 (2023).","journal-title":"Bioinform. Adv."},{"key":"721_CR2","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1038\/s41596-020-0292-x","volume":"15","author":"M Efremova","year":"2020","unstructured":"Efremova, M., Vento-Tormo, M., Teichmann, S. A. & Vento-Tormo, R. Cellphonedb: inferring cell\u2013cell communication from combined expression of multi-subunit ligand\u2013receptor complexes. Nat. Protoc. 15, 1484\u20131506 (2020).","journal-title":"Nat. Protoc."},{"key":"721_CR3","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41592-021-01346-6","volume":"19","author":"M Lange","year":"2022","unstructured":"Lange, M. et al. Cellrank for directed single-cell fate mapping. Nat. Methods 19, 159\u2013170 (2022).","journal-title":"Nat. Methods"},{"key":"721_CR4","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1038\/s41586-022-05406-5","volume":"611","author":"A Afriat","year":"2022","unstructured":"Afriat, A. et al. A spatiotemporally resolved single-cell atlas of the plasmodium liver stage. Nature 611, 563\u2013569 (2022).","journal-title":"Nature"},{"key":"721_CR5","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.csbj.2022.11.055","volume":"21","author":"C-Y Hsieh","year":"2023","unstructured":"Hsieh, C.-Y. et al. scdrug: from single-cell RNA-seq to drug response prediction. Comput. Struct. Biotechnol. J. 21, 150\u2013157 (2023).","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"721_CR6","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1038\/s41596-021-00534-0","volume":"16","author":"ZA Clarke","year":"2021","unstructured":"Clarke, Z. A. et al. Tutorial: guidelines for annotating single-cell transcriptomic maps using automated and manual methods. Nat. Protoc. 16, 2749\u20132764 (2021).","journal-title":"Nat. Protoc."},{"key":"721_CR7","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1186\/s13059-024-03422-4","volume":"25","author":"M Lange","year":"2024","unstructured":"Lange, M. et al. Mapping lineage-traced cells across time points with moslin. Genome Biol. 25, 277 (2024).","journal-title":"Genome Biol."},{"key":"721_CR8","doi-asserted-by":"publisher","first-page":"e9946","DOI":"10.15252\/msb.20209946","volume":"16","author":"D Schwabe","year":"2020","unstructured":"Schwabe, D., Formichetti, S., Junker, J. P., Falcke, M. & Rajewsky, N. The transcriptome dynamics of single cells during the cell cycle. Mol. Syst. Biol. 16, e9946 (2020).","journal-title":"Mol. Syst. Biol."},{"key":"721_CR9","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1038\/s41596-021-00573-7","volume":"16","author":"N Moriel","year":"2021","unstructured":"Moriel, N. et al. Novosparc: flexible spatial reconstruction of single-cell gene expression with optimal transport. Nat. Protoc. 16, 4177\u20134200 (2021).","journal-title":"Nat. Protoc."},{"key":"721_CR10","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1038\/s41586-019-1773-3","volume":"576","author":"M Nitzan","year":"2019","unstructured":"Nitzan, M., Karaiskos, N., Friedman, N. & Rajewsky, N. Gene expression cartography. Nature 576, 132\u2013137 (2019).","journal-title":"Nature"},{"key":"721_CR11","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1038\/s41587-023-01663-5","volume":"41","author":"J Karin","year":"2023","unstructured":"Karin, J., Bornfeld, Y. & Nitzan, M. scPrisma infers, filters and enhances topological signals in single-cell data using spectral template matching. Nat. Biotechnol. 41, 1645\u20131654 (2023).","journal-title":"Nat. Biotechnol."},{"key":"721_CR12","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1038\/s41587-020-00803-5","volume":"39","author":"DB Burkhardt","year":"2021","unstructured":"Burkhardt, D. B. et al. Quantifying the effect of experimental perturbations at single-cell resolution. Nat. Biotechnol. 39, 619\u2013629 (2021).","journal-title":"Nat. Biotechnol."},{"key":"721_CR13","doi-asserted-by":"publisher","first-page":"e122","DOI":"10.1093\/nar\/gkab775","volume":"49","author":"X Shao","year":"2021","unstructured":"Shao, X. et al. scdeepsort: a pre-trained cell-type annotation method for single-cell transcriptomics using deep learning with a weighted graph neural network. Nucleic Acids Res. 49, e122\u2013e122 (2021).","journal-title":"Nucleic Acids Res."},{"key":"721_CR14","doi-asserted-by":"publisher","first-page":"bbad266","DOI":"10.1093\/bib\/bbad266","volume":"24","author":"S Jia","year":"2023","unstructured":"Jia, S., Lysenko, A., Boroevich, K. A., Sharma, A. & Tsunoda, T. scdeepinsight: a supervised cell-type identification method for scRNA-seq data with deep learning. Brief. Bioinform. 24, bbad266 (2023).","journal-title":"Brief. Bioinform."},{"key":"721_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021). Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64, 107\u2013115.","DOI":"10.1145\/3446776"},{"key":"721_CR16","unstructured":"Arpit, D. et al. A closer look at memorization in deep networks. In International Conference on Machine Learning (eds Precup, D. & Teh, Y. W.) 233\u2013242 (PMLR, 2017)."},{"key":"721_CR17","first-page":"17044","volume":"33","author":"G Pleiss","year":"2020","unstructured":"Pleiss, G., Zhang, T., Elenberg, E. & Weinberger, K. Q. Identifying mislabeled data using the area under the margin ranking. Adv. Neural Inform. Process. Syst. 33, 17044\u201317056 (2020).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"721_CR18","doi-asserted-by":"crossref","unstructured":"Swayamdipta, S. et al. Dataset cartography: mapping and diagnosing datasets with training dynamics. In Proc. 2020 Conference on Empirical Methods in Natural Language Processing (eds Webber, B. et al.) 9275\u20139293 (Association for Computational Linguistics, 2020); https:\/\/aclanthology.org\/2020.emnlp-main.746","DOI":"10.18653\/v1\/2020.emnlp-main.746"},{"key":"721_CR19","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N. & McGuinness, K. Unsupervised label noise modeling and loss correction. In International Conference on Machine Learning, (eds Chaudhuri, K. & Salakhutdinov, R.) 312\u2013321 (PMLR, 2019)."},{"key":"721_CR20","unstructured":"L\u00ea, M. T., Wolinski, P. & Arbel, J. Efficient neural networks for tiny machine learning: a comprehensive review. Preprint at https:\/\/arxiv.org\/abs\/2311.11883v1 (2023)."},{"key":"721_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-017-1382-0","volume":"19","author":"FA Wolf","year":"2018","unstructured":"Wolf, F. A., Angerer, P. & Theis, F. J. Scanpy: large-scale single-cell gene expression data analysis. Genome Biol. 19, 1\u20135 (2018).","journal-title":"Genome Biol."},{"key":"721_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-019-1663-x","volume":"20","author":"FA Wolf","year":"2019","unstructured":"Wolf, F. A. et al. Paga: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells. Genome Biol. 20, 1\u20139 (2019).","journal-title":"Genome Biol."},{"key":"721_CR23","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41587-019-0071-9","volume":"37","author":"W Saelens","year":"2019","unstructured":"Saelens, W., Cannoodt, R., Todorov, H. & Saeys, Y. A comparison of single-cell trajectory inference methods. Nat. Biotechnol. 37, 547\u2013554 (2019).","journal-title":"Nat. Biotechnol."},{"key":"721_CR24","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.3390\/ijms21062181","volume":"21","author":"C Feng","year":"2020","unstructured":"Feng, C. et al. Dimension reduction and clustering models for single-cell rna sequencing data: a comparative study. Int. J. Mol. Sci. 21, 2181 (2020).","journal-title":"Int. J. Mol. Sci."},{"key":"721_CR25","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1038\/s41587-021-01206-w","volume":"40","author":"A Gayoso","year":"2022","unstructured":"Gayoso, A. et al. A Python library for probabilistic analysis of single-cell omics data. Nat. Biotechnol. 40, 163\u2013166 (2022).","journal-title":"Nat. Biotechnol."},{"key":"721_CR26","doi-asserted-by":"publisher","first-page":"e16","DOI":"10.1182\/blood-2010-12-326355","volume":"118","author":"KL Wong","year":"2011","unstructured":"Wong, K. L. et al. Gene expression profiling reveals the defining features of the classical, intermediate, and nonclassical human monocyte subsets. Blood 118, e16\u2013e31 (2011).","journal-title":"Blood"},{"key":"721_CR27","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s41586-021-03634-9","volume":"596","author":"A Rao","year":"2021","unstructured":"Rao, A., Barkley, D., Fran\u00e7a, G. S. & Yanai, I. Exploring tissue architecture using spatial transcriptomics. Nature 596, 211\u2013220 (2021).","journal-title":"Nature"},{"key":"721_CR28","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1038\/s41587-021-00830-w","volume":"40","author":"DM Cable","year":"2022","unstructured":"Cable, D. M. et al. Robust decomposition of cell type mixtures in spatial transcriptomics. Nat. Biotechnol. 40, 517\u2013526 (2022).","journal-title":"Nat. Biotechnol."},{"key":"721_CR29","doi-asserted-by":"publisher","first-page":"eaau5324","DOI":"10.1126\/science.aau5324","volume":"362","author":"JR Moffitt","year":"2018","unstructured":"Moffitt, J. R. et al. Molecular, spatial, and functional single-cell profiling of the hypothalamic preoptic region. Science 362, eaau5324 (2018).","journal-title":"Science"},{"key":"721_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-019-6305-x","volume":"20","author":"T Kim","year":"2019","unstructured":"Kim, T. et al. screclassify: post hoc cell type classification of single-cell RNA-seq data. BMC Genomics 20, 1\u201310 (2019).","journal-title":"BMC Genomics"},{"key":"721_CR31","unstructured":"V1 Adult Mouse Brain Coronal Section 2. Version Cell Ranger 1.1.0 (10x Genomics, 2020)."},{"key":"721_CR32","doi-asserted-by":"publisher","first-page":"eaar7042","DOI":"10.1126\/science.aar7042","volume":"361","author":"G Gut","year":"2018","unstructured":"Gut, G., Herrmann, M. D. & Pelkmans, L. Multiplexed protein maps link subcellular organization to cellular states. Science 361, eaar7042 (2018).","journal-title":"Science"},{"key":"721_CR33","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s41587-021-01006-2","volume":"40","author":"T Lohoff","year":"2022","unstructured":"Lohoff, T. et al. Integration of spatial and single-cell transcriptomic data elucidates mouse organogenesis. Nature Biotechnol. 40, 74\u201385 (2022).","journal-title":"Nature Biotechnol."},{"key":"721_CR34","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/cancers10020052","volume":"10","author":"J Roche","year":"2018","unstructured":"Roche, J. The epithelial-to-mesenchymal transition in cancer. Cancers 10, 52 (2018).","journal-title":"Cancers"},{"key":"721_CR35","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.coisb.2018.02.009","volume":"9","author":"AL MacLean","year":"2018","unstructured":"MacLean, A. L., Hong, T. & Nie, Q. Exploring intermediate cell states through the lens of single cells. Curr. Opin. Syst. Biol. 9, 32\u201341 (2018).","journal-title":"Curr. Opin. Syst. Biol."},{"key":"721_CR36","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1038\/s41588-019-0489-5","volume":"51","author":"JL McFaline-Figueroa","year":"2019","unstructured":"McFaline-Figueroa, J. L. et al. A pooled single-cell genetic screen identifies regulatory checkpoints in the continuum of the epithelial-to-mesenchymal transition. Nat. Genet. 51, 1389\u20131398 (2019).","journal-title":"Nat. Genet."},{"key":"721_CR37","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1002\/wdev.86","volume":"2","author":"A Weiss","year":"2013","unstructured":"Weiss, A. & Attisano, L. The TGF\u03b2 superfamily signaling pathway. Wiley Interdisc. Rev. Dev. Biol. 2, 47\u201363 (2013).","journal-title":"Wiley Interdisc. Rev. Dev. Biol."},{"key":"721_CR38","doi-asserted-by":"publisher","first-page":"101595","DOI":"10.1016\/j.molmet.2022.101595","volume":"66","author":"S Tritschler","year":"2022","unstructured":"Tritschler, S. et al. A transcriptional cross species map of pancreatic islet cells. Mol. Metab. 66, 101595 (2022).","journal-title":"Mol. Metab."},{"key":"721_CR39","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1126\/science.180605","volume":"193","author":"AA Like","year":"1976","unstructured":"Like, A. A. & Rossini, A. A. Streptozotocin-induced pancreatic insulitis: new model of diabetes mellitus. Science 193, 415\u2013417 (1976).","journal-title":"Science"},{"key":"721_CR40","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1038\/s42255-023-00876-x","volume":"5","author":"K Hrovatin","year":"2023","unstructured":"Hrovatin, K. et al. Delineating mouse \u03b2-cell identity during lifetime and in diabetes with a single cell atlas. Nat. Metab. 5, 1615\u20131637 (2023).","journal-title":"Nat. Metab."},{"key":"721_CR41","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1038\/s42003-020-01243-2","volume":"3","author":"M Hahn","year":"2020","unstructured":"Hahn, M. et al. Topologically selective islet vulnerability and self-sustained downregulation of markers for \u03b2-cell maturity in streptozotocin-induced diabetes. Commun. Biol. 3, 541 (2020).","journal-title":"Commun. Biol."},{"key":"721_CR42","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1038\/s42255-020-0171-3","volume":"2","author":"S Sachs","year":"2020","unstructured":"Sachs, S. et al. Targeted pharmacological therapy restores \u03b2-cell function for diabetes remission. Nat. Metab. 2, 192\u2013209 (2020).","journal-title":"Nat. Metab."},{"key":"721_CR43","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1038\/s41556-023-01337-z","volume":"26","author":"RK Zwick","year":"2024","unstructured":"Zwick, R. K. et al. Epithelial zonation along the mouse and human small intestine defines five discrete metabolic domains. Nat. Cell Biol. 26, 250\u2013262 (2024).","journal-title":"Nat. Cell Biol."},{"key":"721_CR44","first-page":"69","volume":"168","author":"ED Sontag","year":"1998","unstructured":"Sontag, E. D. et al. Vc dimension of neural networks. NATO ASI Ser. F 168, 69\u201396 (1998).","journal-title":"NATO ASI Ser. F"},{"key":"721_CR45","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B. & Vinyals, O. Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64, 107\u2013115 (2021).","journal-title":"Commun. ACM"},{"key":"721_CR46","unstructured":"Hacohen, G., Choshen, L. & Weinshall, D. Let\u2019s agree to agree: neural networks share classification order on real datasets. In International Conference on Machine Learning (eds Daum\u00e9, H. III & Singh, A.) 3950\u20133960 (PMLR, 2020)."},{"key":"721_CR47","first-page":"20596","volume":"34","author":"M Paul","year":"2021","unstructured":"Paul, M., Ganguli, S. & Dziugaite, G. K. Deep learning on a data diet: finding important examples early in training. Adv. Neural Inform. Process. Syst. 34, 20596\u201320607 (2021).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"721_CR48","unstructured":"Agarap, A. F. Deep learning using rectified linear units (ReLU). Preprint at https:\/\/arxiv.org\/abs\/1803.08375v2 (2018)."},{"key":"721_CR49","unstructured":"Paszke, A. et al. Automatic differentiation in PyTorch. In Advances in Neural Information Processing Systems (eds Guyon, I. et al.) 8024\u20138035 (MIT Press, 2017)."},{"key":"721_CR50","unstructured":"4k PBMCs from a healthy donor. 10x Genomics https:\/\/www.10xgenomics.com\/datasets\/4-k-pbm-cs-from-a-healthy-donor-2-standard-2-1-0 (2017)."},{"key":"721_CR51","unstructured":"8k PBMCs from a healthy donor. 10x Genomics https:\/\/www.10xgenomics.com\/datasets\/8-k-pbm-cs-from-a-healthy-donor-2-standard-2-1-0 (2017)."},{"key":"721_CR52","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41592-021-01358-2","volume":"19","author":"G Palla","year":"2022","unstructured":"Palla, G. et al. Squidpy: a scalable framework for spatial omics analysis. Nat. Methods 19, 171\u2013178 (2022).","journal-title":"Nat. Methods"},{"key":"721_CR53","doi-asserted-by":"publisher","unstructured":"Karin, J. Interpreting single-cell and spatial omics data using deep neural networks training dynamics. Zenodo https:\/\/doi.org\/10.5281\/zenodo.13838816 (2024).","DOI":"10.5281\/zenodo.13838816"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00721-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00721-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00721-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T19:04:53Z","timestamp":1734635093000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-024-00721-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"references-count":53,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["721"],"URL":"https:\/\/doi.org\/10.1038\/s43588-024-00721-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.04.06.588373","asserted-by":"object"}]},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"23 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}