{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:22:02Z","timestamp":1790698922975,"version":"4.1.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>With the growing number of single-cell datasets collected under more complex experimental conditions, there is an opportunity to leverage single-cell variability to reveal deeper insights into how cells respond to perturbations. Many existing approaches rely on discretizing the data into clusters for differential gene expression (DGE), effectively ironing out any information unveiled by the single-cell variability across cell-types. In addition, DGE often assumes a statistical distribution that, if erroneous, can lead to false positive differentially expressed genes. Here, we present Cellograph: a semi-supervised framework that uses graph neural networks to quantify the effects of perturbations at single-cell granularity. Cellograph not only measures how prototypical cells are of each condition but also learns a latent space that is amenable to interpretable data visualization and clustering. The learned gene weight matrix from training reveals pertinent genes driving the differences between conditions. We demonstrate the utility of our approach on publicly-available datasets including cancer drug therapy, stem cell reprogramming, and organoid differentiation. Cellograph outperforms existing methods for quantifying the effects of experimental perturbations and offers a novel framework to analyze single-cell data using deep learning.<\/jats:p>","DOI":"10.1186\/s12859-024-05641-9","type":"journal-article","created":{"date-parts":[[2024,1,14]],"date-time":"2024-01-14T22:02:01Z","timestamp":1705269721000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Cellograph: a semi-supervised approach to analyzing multi-condition single-cell RNA-sequencing data using graph neural networks"],"prefix":"10.1186","volume":"25","author":[{"given":"Jamshaid A.","family":"Shahir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalie","family":"Stanley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy E.","family":"Purvis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,15]]},"reference":[{"issue":"5","key":"5641_CR1","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1016\/j.cell.2015.04.044","volume":"161","author":"A Klein","year":"2015","unstructured":"Klein A, Mazutis L, Akartuna I, Tallapragada N, Veres A, Li V, Peshkin L, Weitz D, Kirschner M. Droplet barcoding for single-cell transcriptomics applied to embryonic stem cells. Cell. 2015;161(5):1187\u2013201. https:\/\/doi.org\/10.1016\/j.cell.2015.04.044.","journal-title":"Cell"},{"key":"5641_CR2","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20188746","author":"MD Luecken","year":"2019","unstructured":"Luecken MD, Theis FJ. Current best practices in single-cell RNA-seq analysis: a tutorial. Mol Syst Biol. 2019. https:\/\/doi.org\/10.15252\/msb.20188746.","journal-title":"Mol Syst Biol"},{"key":"5641_CR3","doi-asserted-by":"publisher","DOI":"10.1101\/041384","author":"L Haghverdi","year":"2016","unstructured":"Haghverdi L, B\u00fcttner M, Wolf FA, Buettner F, Theis FJ. Diffusion pseudotime robustly reconstructs lineage branching. Nat Methods. 2016. https:\/\/doi.org\/10.1101\/041384.","journal-title":"Nat Methods"},{"issue":"2","key":"5641_CR4","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1038\/s41587-021-01033-z","volume":"40","author":"E Dann","year":"2021","unstructured":"Dann E, Henderson NC, Teichmann SA, Morgan MD, Marioni JC. Differential abundance testing on single-cell data using k-nearest neighbor graphs. Nat Biotechnol. 2021;40(2):245\u201353. https:\/\/doi.org\/10.1038\/s41587-021-01033-z.","journal-title":"Nat Biotechnol"},{"issue":"3","key":"5641_CR5","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1038\/s41587-021-01066-4","volume":"40","author":"YA Reshef","year":"2021","unstructured":"Reshef YA, Rumker L, Kang JB, Nathan A, Korsunsky I, Asgari S, Murray MB, Moody DB, Raychaudhuri S. Co-varying neighborhood analysis identifies cell populations associated with phenotypes of interest from single-cell transcriptomics. Nat Biotechnol. 2021;40(3):355\u201363. https:\/\/doi.org\/10.1038\/s41587-021-01066-4.","journal-title":"Nat Biotechnol"},{"issue":"5","key":"5641_CR6","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1038\/s41587-020-00803-5","volume":"39","author":"DB Burkhardt","year":"2021","unstructured":"Burkhardt DB, Stanley JS, Tong A, Perdigoto AL, Gigante SA, Herold KC, Wolf G, Giraldez AJ, Dijk D, Krishnaswamy S, et al. Quantifying the effect of experimental perturbations at single-cell resolution. Nat Biotechnol. 2021;39(5):619\u201329. https:\/\/doi.org\/10.1038\/s41587-020-00803-5.","journal-title":"Nat Biotechnol"},{"issue":"11","key":"5641_CR7","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1038\/s41592-019-0576-7","volume":"16","author":"M Amodio","year":"2019","unstructured":"Amodio M, Dijk D, Srinivasan K, Chen WS, Mohsen H, Moon KR, Campbell A, Zhao Y, Wang X, Venkataswamy M, et al. Exploring single-cell data with deep multitasking neural networks. Nat Methods. 2019;16(11):1139\u201345. https:\/\/doi.org\/10.1038\/s41592-019-0576-7.","journal-title":"Nat Methods"},{"issue":"12","key":"5641_CR8","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","volume":"15","author":"R Lopez","year":"2018","unstructured":"Lopez R, Regier J, Cole MB, Jordan MI, Yosef N. Deep generative modeling for single-cell transcriptomics. Nat Methods. 2018;15(12):1053\u20138. https:\/\/doi.org\/10.1038\/s41592-018-0229-2.","journal-title":"Nat Methods"},{"key":"5641_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22197-x","author":"J Wang","year":"2021","unstructured":"Wang J, Ma A, Chang Y, Gong J, Jiang Y, Qi R, Wang C, Fu H, Ma Q, Xu D, et al. scGNN is a novel graph neural network framework for single-cell RNA-seq analyses. Nat Commun. 2021. https:\/\/doi.org\/10.1038\/s41467-021-22197-x.","journal-title":"Nat Commun"},{"key":"5641_CR10","doi-asserted-by":"publisher","unstructured":"Ravindra N, Sehanobish A, Pappalardo JL, Hafler DA, Dijk D. Disease state prediction from single-cell data using graph attention networks. In: Proceedings of the ACM conference on health, inference, and learning 2020. https:\/\/doi.org\/10.1145\/3368555.3384449","DOI":"10.1145\/3368555.3384449"},{"key":"5641_CR11","doi-asserted-by":"publisher","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y. Graph attention networks. arXiv; 2017. https:\/\/doi.org\/10.48550\/ARXIV.1710.10903.","DOI":"10.48550\/ARXIV.1710.10903"},{"key":"5641_CR12","doi-asserted-by":"publisher","unstructured":"Sehanobish A, Ravindra NG, Dijk D. Gaining insight into SARS-CoV-2 infection and COVID-19 severity using self-supervised edge features and graph neural networks. arXiv; 2020. https:\/\/doi.org\/10.48550\/ARXIV.2006.12971.","DOI":"10.48550\/ARXIV.2006.12971"},{"issue":"5","key":"5641_CR13","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1093\/bioinformatics\/btab804","volume":"38","author":"D Buterez","year":"2021","unstructured":"Buterez D, Bica I, Tariq I, Andr\u00e9s-Terr\u00e9 H, Li\u00f2 P. CellVGAE: an unsupervised scRNA-seq analysis workflow with graph attention networks. Bioinformatics. 2021;38(5):1277\u201386. https:\/\/doi.org\/10.1093\/bioinformatics\/btab804.","journal-title":"Bioinformatics"},{"key":"5641_CR14","doi-asserted-by":"publisher","unstructured":"Rhee S, Seo S, Kim S. Hybrid approach of relation network and localized graph convolutional filtering for breast cancer subtype classification. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence; 2018. https:\/\/doi.org\/10.24963\/ijcai.2018\/490.","DOI":"10.24963\/ijcai.2018\/490"},{"key":"5641_CR15","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. CoRR abs\/1609.02907; 2016. arXiv:1609.02907."},{"issue":"1","key":"5641_CR16","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1038\/s41467-021-24172-y","volume":"12","author":"Q Song","year":"2021","unstructured":"Song Q, Su J, Zhang W. scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics. Nat Commun. 2021;12(1):3826.","journal-title":"Nat Commun"},{"key":"5641_CR17","doi-asserted-by":"publisher","unstructured":"McDaid AF, Greene D, Hurley N. Normalized mutual information to evaluate overlapping community finding algorithms. arXiv; 2011. https:\/\/doi.org\/10.48550\/ARXIV.1110.2515.","DOI":"10.48550\/ARXIV.1110.2515"},{"key":"5641_CR18","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J. Umap: uniform manifold approximation and projection for dimension reduction; 2018. arXiv:1802.03426.","DOI":"10.21105\/joss.00861"},{"issue":"1","key":"5641_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41596-020-00409-w","volume":"16","author":"TS Andrews","year":"2021","unstructured":"Andrews TS, Kiselev VY, McCarthy D, Hemberg M. Tutorial: guidelines for the computational analysis of single-cell RNA sequencing data. Nat Protoc. 2021;16(1):1\u20139.","journal-title":"Nat Protoc"},{"key":"5641_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-017-1382-0","volume":"19","author":"FA Wolf","year":"2018","unstructured":"Wolf FA, Angerer P, Theis FJ. SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 2018;19:1\u20135.","journal-title":"Genome Biol"},{"issue":"4","key":"5641_CR21","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1038\/s41551-022-00863-9","volume":"6","author":"BE Mead","year":"2022","unstructured":"Mead BE, Hattori K, Levy L, Imada S, Goto N, Vukovic M, Sze D, Kummerlowe C, Matute JD, Duan J, et al. Screening for modulators of the cellular composition of gut epithelia via organoid models of intestinal stem cell differentiation. Nat Biomed Eng. 2022;6(4):476\u201394. https:\/\/doi.org\/10.1038\/s41551-022-00863-9.","journal-title":"Nat Biomed Eng"},{"key":"5641_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21884-z","author":"AF Aissa","year":"2021","unstructured":"Aissa AF, Islam AB, Ariss MM, Go CC, Rader AE, Conrardy RD, Gajda AM, Rubio-Perez C, Valyi-Nagy K, Pasquinelli M, et al. Single-cell transcriptional changes associated with drug tolerance and response to combination therapies in cancer. Nat Commun. 2021. https:\/\/doi.org\/10.1038\/s41467-021-21884-z.","journal-title":"Nat Commun"},{"issue":"17\u201318","key":"5641_CR23","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1101\/gad.348678.121","volume":"35","author":"M Yagi","year":"2021","unstructured":"Yagi M, Ji F, Charlton J, Cristea S, Messemer K, Horwitz N, Di Stefano B, Tsopoulidis N, Hoetker MS, Huebner AJ, et al. Dissecting dual roles of MyoD during lineage conversion to mature myocytes and myogenic stem cells. Genes Dev. 2021;35(17\u201318):1209\u201328. https:\/\/doi.org\/10.1101\/gad.348678.121.","journal-title":"Genes Dev"},{"key":"5641_CR24","doi-asserted-by":"publisher","DOI":"10.1152\/ajplung.00062.2019","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Jiang M, Nouraie M, Roth MG, Tabib T, Winters S, Chen X, Sembrat J, Chu Y, Cardenes N, et al. Gdf15 is an epithelial-derived biomarker of idiopathic pulmonary fibrosis. Am J Physiol-Lung Cell Mol Physiol. 2019. https:\/\/doi.org\/10.1152\/ajplung.00062.2019.","journal-title":"Am J Physiol-Lung Cell Mol Physiol"},{"key":"5641_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-81349-7","author":"M Yang","year":"2021","unstructured":"Yang M, Darwish T, Larraufie P, Rimmington D, Cimino I, Goldspink DA, Jenkins B, Koulman A, Brighton CA, Ma M, et al. Inhibition of mitochondrial function by metformin increases glucose uptake, glycolysis and GDF-15 release from intestinal cells. Sci Rep. 2021. https:\/\/doi.org\/10.1038\/s41598-021-81349-7.","journal-title":"Sci Rep"},{"key":"5641_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s12943-015-0381-6","author":"CH Schrader","year":"2015","unstructured":"Schrader CH, Kolb M, Zaoui K, Flechtenmacher C, Grabe N, Weber K-J, Hielscher T, Plinkert PK, Hess J. Kallikrein-related peptidase 6 regulates epithelial-to-mesenchymal transition and serves as prognostic biomarker for head and neck squamous cell carcinoma patients. Mol Cancer. 2015. https:\/\/doi.org\/10.1186\/s12943-015-0381-6.","journal-title":"Mol Cancer"},{"key":"5641_CR27","doi-asserted-by":"publisher","DOI":"10.3892\/ol.2021.13085","author":"D Zhou","year":"2021","unstructured":"Zhou D, He Y, Li H, Huang W. KLK6 mediates stemness and metabolism of gastric carcinoma cells via the PI3K\/AKT\/mTOR signaling pathway. Oncol Lett. 2021. https:\/\/doi.org\/10.3892\/ol.2021.13085.","journal-title":"Oncol Lett"},{"issue":"9","key":"5641_CR28","doi-asserted-by":"publisher","first-page":"12465","DOI":"10.1007\/s13277-016-5101-3","volume":"37","author":"L Wallace","year":"2016","unstructured":"Wallace L, Mehrabi S, Bacanamwo M, Yao X, Aikhionbare FO. Expression of mitochondrial genes MT-ND1, MT-ND6, MT-CYB, MT-COI, MT-ATP6, and 12S\/MT-RNR1 in colorectal adenopolyps. Tumor Biol. 2016;37(9):12465\u201375. https:\/\/doi.org\/10.1007\/s13277-016-5101-3.","journal-title":"Tumor Biol"},{"key":"5641_CR29","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.705512","author":"K Zhao","year":"2022","unstructured":"Zhao K, Yi Y, Ma Z, Zhang W. INHBA is a prognostic biomarker and correlated with immune cell infiltration in cervical cancer. Front Genet. 2022. https:\/\/doi.org\/10.3389\/fgene.2021.705512.","journal-title":"Front Genet"},{"issue":"9","key":"5641_CR30","doi-asserted-by":"publisher","first-page":"3004","DOI":"10.1210\/en.2017-00353","volume":"158","author":"Y-L Lin","year":"2017","unstructured":"Lin Y-L, Persaud SD, Nhieu J, Wei L-N. Cellular retinoic acid-binding protein 1 modulates stem cell proliferation to affect learning and memory in male mice. Endocrinology. 2017;158(9):3004\u201314. https:\/\/doi.org\/10.1210\/en.2017-00353.","journal-title":"Endocrinology"},{"issue":"1","key":"5641_CR31","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41592-021-01336-8","volume":"19","author":"MD Luecken","year":"2022","unstructured":"Luecken MD, B\u00fcttner M, Chaichoompu K, Danese A, Interlandi M, M\u00fcller MF, Strobl DC, Zappia L, Dugas M, Colom\u00e9-Tatch\u00e9 M, et al. Benchmarking atlas-level data integration in single-cell genomics. Nat Methods. 2022;19(1):41\u201350.","journal-title":"Nat Methods"},{"key":"5641_CR32","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar7042","author":"G Gut","year":"2018","unstructured":"Gut G, Herrmann MD, Pelkmans L. Multiplexed protein maps link subcellular organization to cellular states. Science. 2018. https:\/\/doi.org\/10.1126\/science.aar7042.","journal-title":"Science"},{"issue":"12","key":"5641_CR33","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41592-019-0619-0","volume":"16","author":"I Korsunsky","year":"2019","unstructured":"Korsunsky I, Millard N, Fan J, Slowikowski K, Zhang F, Wei K, Baglaenko Y, Brenner M, Loh P-R, Raychaudhuri S. Fast, sensitive and accurate integration of single-cell data with harmony. Nat Methods. 2019;16(12):1289\u201396.","journal-title":"Nat Methods"},{"issue":"7","key":"5641_CR34","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1016\/j.cell.2019.05.031","volume":"177","author":"T Stuart","year":"2019","unstructured":"Stuart T, Butler A, Hoffman P, Hafemeister C, Papalexi E, Mauck WM, Hao Y, Stoeckius M, Smibert P, Satija R. Comprehensive integration of single-cell data. Cell. 2019;177(7):1888\u2013902.","journal-title":"Cell"},{"key":"5641_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-019-1850-9","volume":"21","author":"HTN Tran","year":"2020","unstructured":"Tran HTN, Ang KS, Chevrier M, Zhang X, Lee NYS, Goh M, Chen J. A benchmark of batch-effect correction methods for single-cell RNA sequencing data. Genome Biol. 2020;21:1\u201332.","journal-title":"Genome Biol"},{"issue":"1","key":"5641_CR36","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.cels.2021.12.006","volume":"13","author":"W Stallaert","year":"2022","unstructured":"Stallaert W, Kedziora KM, Taylor CD, Zikry TM, Ranek JS, Sobon HK, Taylor SR, Young CL, Cook JG, Purvis JE, et al. The structure of the human cell cycle. Cell Syst. 2022;13(1):103. https:\/\/doi.org\/10.1016\/j.cels.2021.12.006.","journal-title":"Cell Syst"},{"key":"5641_CR37","doi-asserted-by":"publisher","DOI":"10.1126\/sciimmunol.aan2946","author":"N Aghaeepour","year":"2017","unstructured":"Aghaeepour N, Ganio EA, Mcilwain D, Tsai AS, Tingle M, Van Gassen S, Gaudilliere DK, Baca Q, McNeil L, Okada R, et al. An immune clock of human pregnancy. Sci Immunol. 2017. https:\/\/doi.org\/10.1126\/sciimmunol.aan2946.","journal-title":"Sci Immunol"},{"key":"5641_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41591-023-02327-2","volume":"29","author":"L Sikkema","year":"2023","unstructured":"Sikkema L, Ram\u00edrez-Su\u00e1stegui C, Strobl DC, Gillett TE, Zappia L, Madissoon E, Markov NS, Zaragosi L-E, Ji Y, Ansari M, et al. An integrated cell atlas of the lung in health and disease. Nat Med. 2023;29:1\u201315.","journal-title":"Nat Med"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05641-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-024-05641-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05641-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T10:02:10Z","timestamp":1705312930000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-024-05641-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,15]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["5641"],"URL":"https:\/\/doi.org\/10.1186\/s12859-024-05641-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.02.24.528672","asserted-by":"object"}]},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,15]]},"assertion":[{"value":"31 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}