CellVGAE: an unsupervised scRNA-seq analysis workflow with graph attention networks
Open accessPublished version of a preprint
Abstract
Motivation: Single-cell RNA sequencing allows high-resolution views of individual cells for libraries of up to millions of samples, thus motivating the use of deep learning for analysis. In this study, we introduce the use of graph neural networks for the unsupervised exploration of scRNA-seq data by developing a variational graph autoencoder architecture with graph attention layers that operates directly on the connectivity between cells, focusing on dimensionality reduction and clustering. With the help of several case studies, we show that our model, named CellVGAE, can be effectively used for exploratory analysis even on challenging datasets, by extracting meaningful features from the data and providing the means to visualize and interpret different aspects of the model. Results: We show that CellVGAE is more interpretable than existing scRNA-seq variational architectures by analysing the graph attention coefficients. By drawing parallels with other scRNA-seq studies on interpretability, we assess the validity of the relationships modelled by attention, and furthermore, we show that CellVGAE can intrinsically capture information such as pseudotime and NF-ĸB activation dynamics, the latter being a property that is not generally shared by existing neural alternatives. We then evaluate the dimensionality reduction and clustering performance on 9 difficult and well-annotated datasets by comparing with three leading neural and non-neural techniques, concluding that CellVGAE outperforms competing methods. Finally, we report a decrease in training times of up to × 20 on a dataset of 1.3 million cells compared to existing deep learning architectures. Availabilityand implementation: The CellVGAE code is available at https://github.com/davidbuterez/CellVGAE. Supplementary information: Supplementary data are available at Bioinformatics online.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Methods that use only gene expression data typically transform the co-expression matrix into a more topologically meaningful form.
“Methods that rely solely on gene expression data typically transform the co-expression matrix into a more topologically meaningful form [146, 147, 148].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [146]
Gene expression data can also directly construct disease and gene networks that are input into a joint matrix factorization and GCN method to infer disease-gene associations, similar to a recommendation task.
“Alternatively, gene expression data can directly be used to construct disease and gene networks that are then input into a joint matrix factorization and GCN method to draw disease-gene associations, akin to a recommendation task (Section 2.2) [146].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [146]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · see citing works
Fast unfolding of communities in large networks
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., & Lefebvre, E. (2008) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/2008/10/p10008 · Cited by 21,424 · see citing works
Comprehensive Integration of Single-Cell Data
Stuart, T., Butler, A., Hoffman, P., Hafemeister, C., Papalexi, E., Mauck, W. M., Hao, Y., Stoeckius, M., Smibert, P., & Satija, R. (2019) · Cell · doi:10.1016/j.cell.2019.05.031 · Cited by 15,453 · see citing works
Integrating single-cell transcriptomic data across different conditions, technologies, and species
Butler, A., Hoffman, P., Smibert, P., Papalexi, E., & Satija, R. (2018) · Nature Biotechnology · doi:10.1038/nbt.4096 · Cited by 13,174 · see citing works
Enrichr: a comprehensive gene set enrichment analysis web server 2016 update
Kuleshov, M. V., Jones, M. R., Rouillard, A. D., Fernandez, N. F., Duan, Q., Wang, Z., Koplev, S., Jenkins, S. L., Jagodnik, K. M., Lachmann, A., et al. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkw377 · Cited by 10,799 · see citing works
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826 · see citing works
SCANPY: large-scale single-cell gene expression data analysis
Wolf, F. A., Angerer, P., & Theis, F. J. (2018) · Genome Biology · doi:10.1186/s13059-017-1382-0 · Cited by 8,881 · see citing works
Enrichr: interactive and collaborative HTML5 gene list enrichment analysis tool
Chen, E. Y., Tan, C. M., Kou, Y., Duan, Q., Wang, Z., Meirelles, G. V., Clark, N. R., & Ma’ayan, A. (2013) · BMC Bioinformatics · doi:10.1186/1471-2105-14-128 · Cited by 7,814 · see citing works
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · see citing works
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101 · see citing works
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228 · see citing works
mRNA-Seq whole-transcriptome analysis of a single cell
Tang, F., Barbacioru, C., Wang, Y., Nordman, E., Lee, C., Xu, N., Wang, X., Bodeau, J., Tuch, B. B., Siddiqui, A., et al. (2009) · Nature Methods · doi:10.1038/nmeth.1315 · Cited by 3,969 · see citing works
Deep learning for computer vision: A brief review
Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/7068349 · Cited by 3,403 · see citing works
Fast Graph Representation Learning with PyTorch GeometricPreprint
Fey, M., & Lenssen, J. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02428 · Cited by 3,403 · see citing works
hdbscan: Hierarchical density based clustering
McInnes, L., Healy, J., & Astels, S. (2017) · The Journal of Open Source Software · doi:10.21105/joss.00205 · Cited by 2,833 · see citing works
Ranade, V. (2009) · American Journal of Therapeutics · doi:10.1097/mjt.0b013e31817c941f · Cited by 2,790 · see citing works
Deep generative modeling for single-cell transcriptomics
Lopez, R., Regier, J., Cole, M. B., Jordan, M. I., & Yosef, N. (2018) · Nature Methods · doi:10.1038/s41592-018-0229-2 · Cited by 2,530 · see citing works
Current best practices in single-cell RNA-seq analysis: a tutorial
Luecken, M. D., & Theis, F. J. (2019) · Molecular Systems Biology · doi:10.15252/msb.20188746 · Cited by 2,231 · see citing works
Wolf, F. A., Hamey, F. K., Plass, M., Solana, J., Dahlin, J. S., Göttgens, B., Rajewsky, N., Simon, L., & Theis, F. J. (2019) · Genome Biology · doi:10.1186/s13059-019-1663-x · Cited by 1,698 · see citing works
A step-by-step workflow for low-level analysis of single-cell RNA-seq data with Bioconductor
Lun, A. T. L., McCarthy, D. J., & Marioni, J. C. (2016) · F1000Research · doi:10.12688/f1000research.9501.2 · Cited by 1,586 · see citing works
Single-Cell Transcriptome Profiling of Human Pancreatic Islets in Health and Type 2 Diabetes
Segerstolpe, Å., Palasantza, A., Eliasson, P., Andersson, E.-M., Andréasson, A.-C., Sun, X., Picelli, S., Sabirsh, A., Clausen, M., Bjursell, M. K., et al. (2016) · Cell Metabolism · doi:10.1016/j.cmet.2016.08.020 · Cited by 1,550 · see citing works
Baron, M., Veres, A., Wolock, S. L., Faust, A. L., Gaujoux, R., Vetere, A., Ryu, J. H., Wagner, B. K., Shen-Orr, S. S., Klein, A. M., et al. (2016) · Cell Systems · doi:10.1016/j.cels.2016.08.011 · Cited by 1,508 · see citing works
SC3: consensus clustering of single-cell RNA-seq data
Kiselev, V. Y., Kirschner, K., Schaub, M. T., Andrews, T., Yiu, A., Chandra, T., Natarajan, K. N., Reik, W., Barahona, M., Green, A. R., et al. (2017) · Nature Methods · doi:10.1038/nmeth.4236 · Cited by 1,500 · see citing works
A survey of human brain transcriptome diversity at the single cell level
Darmanis, S., Sloan, S. A., Zhang, Y., Enge, M., Caneda, C., Shuer, L. M., Hayden Gephart, M. G., Barres, B. A., & Quake, S. R. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1507125112 · Cited by 1,401 · see citing works
A Single-Cell Transcriptome Atlas of the Human Pancreas
Muraro, M. J., Dharmadhikari, G., Grün, D., Gröen, N., Dielen, T., Jansen, E., van Gurp, L., Engelse, M. A., Carlotti, F., de Koning, E. J. P., et al. (2016) · Cell Systems · doi:10.1016/j.cels.2016.09.002 · Cited by 1,288 · see citing works
Comprehensive Classification of Retinal Bipolar Neurons by Single-Cell Transcriptomics
Shekhar, K., Lapan, S. W., Whitney, I. E., Tran, N. M., Macosko, E. Z., Kowalczyk, M., Adiconis, X., Levin, J. Z., Nemesh, J., Goldman, M., et al. (2016) · Cell · doi:10.1016/j.cell.2016.07.054 · Cited by 1,176 · see citing works
Single-cell RNA-seq denoising using a deep count autoencoder
Eraslan, G., Simon, L. M., Mircea, M., Mueller, N. S., & Theis, F. J. (2019) · Nature Communications · doi:10.1038/s41467-018-07931-2 · Cited by 1,084 · see citing works
Transcriptional Heterogeneity and Lineage Commitment in Myeloid Progenitors
Paul, F., Arkin, Y., Giladi, A., Jaitin, D. A., Kenigsberg, E., Keren-Shaul, H., Winter, D., Lara-Astiaso, D., Gury, M., Weiner, A., et al. (2015) · Cell · doi:10.1016/j.cell.2015.11.013 · Cited by 1,082 · see citing works
Orchestrating single-cell analysis with Bioconductor
Amezquita, R. A., Lun, A. T. L., Becht, E., Carey, V. J., Carpp, L. N., Geistlinger, L., Marini, F., Rue-Albrecht, K., Risso, D., Soneson, C., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0654-x · Cited by 945 · see citing works
Single-Cell RNA-Seq Technologies and Related Computational Data Analysis
Chen, G., Ning, B., & Shi, T. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00317 · Cited by 913 · see citing works
Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning
Wang, B., Zhu, J., Pierson, E., Ramazzotti, D., & Batzoglou, S. (2017) · Nature Methods · doi:10.1038/nmeth.4207 · Cited by 706 · see citing works
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
Zhao, S., Song, J., & Ermon, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015885 · Cited by 674 · see citing works
Loh, K. M., Chen, A. C., Koh, P. W., Deng, T. Z., Sinha, R., Tsai, J. M., Barkal, A. A., Shen, K., Jain, R., Morganti, R. M., et al. (2016) · Cell · doi:10.1016/j.cell.2016.06.011 · Cited by 493 · see citing works
Single-Cell Transcriptomics of the Human Endocrine Pancreas
Wang, Y. J., Schug, J., Won, K., Liu, C., Naji, A., Avrahami, D., Golson, M. L., & Kaestner, K. H. (2016) · Diabetes · doi:10.2337/db16-0405 · Cited by 434 · see citing works
Peixoto, T. P. (2014) · Figshare · doi:10.6084/m9.figshare.1164194 · Cited by 397 · see citing works
The unreasonable effectiveness of deep learning in artificial intelligence
Sejnowski, T. J. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1907373117 · Cited by 352 · see citing works
InfoVAE: Information Maximizing Variational AutoencodersPreprint
Zhao, S., Song, J., & Ermon, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.02262 · Cited by 341 · see citing works
Natural Language Processing Advancements By Deep Learning: A SurveyPreprint
Torfi, A., Shirvani, R. A., Keneshloo, Y., Tavaf, N., & Fox, E. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01200 · Cited by 322 · see citing works
scVAE: variational auto-encoders for single-cell gene expression data
Grønbech, C. H., Vording, M. F., Timshel, P. N., Sønderby, C. K., Pers, T. H., & Winther, O. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa293 · Cited by 268 · see citing works
Automated methods for cell type annotation on scRNA-seq data
Pasquini, G., Rojo Arias, J. E., Schäfer, P., & Busskamp, V. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.01.015 · Cited by 249 · see citing works
Fast Approximate kNN Graph Construction for High Dimensional Data via Recursive Lanczos Bisection
Chen, J., Fang, H., & Saad, Y. (2008) · Cited by 236 · see citing works
Peixoto, T. P. (2015) · Figshare · doi:10.6084/m9.figshare.1164194.v13 · Cited by 221 · see citing works
Using neural networks for reducing the dimensions of single-cell RNA-Seq data
Lin, C., Jain, S., Kim, H., & Bar-Joseph, Z. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkx681 · Cited by 197 · see citing works
Evaluation of tools for highly variable gene discovery from single-cell RNA-seq data
Yip, S. H., Sham, P. C., & Wang, J. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bby011 · Cited by 195 · see citing works
Interpretable factor models of single-cell RNA-seq via variational autoencoders
Svensson, V., Gayoso, A., Yosef, N., & Pachter, L. S. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa169 · Cited by 192 · see citing works
Over 1000 tools reveal trends in the single-cell RNA-seq analysis landscape
Zappia, L., & Theis, F. J. (2021) · Genome biology · doi:10.1186/s13059-021-02519-4 · Cited by 165 · see citing works
AutoImpute: Autoencoder based imputation of single-cell RNA-seq data
Talwar, D., Mongia, A., Sengupta, D., & Majumdar, A. (2018) · Scientific Reports · doi:10.1038/s41598-018-34688-x · Cited by 163 · see citing works
Platelets and Their Interactions with Other Immune Cells
Lam, F. W., Vijayan, K. V., & Rumbaut, R. E. (2015) · Comprehensive physiology · doi:10.1002/cphy.c140074 · Cited by 156 · see citing works
Lane, K. M., Valen, D. V., DeFelice, M. M., Macklin, D. N., Kudo, T., Jaimovich, A., Carr, A., Meyer, T., Pe’er, D., Boutet, S. C., et al. (2017) · Cell Systems · doi:10.1016/j.cels.2017.03.010 · Cited by 144 · see citing works
Impact of similarity metrics on single-cell RNA-seq data clustering
Kim, T., Chen, I. R., Lin, Y., Wang, A. Y.-Y., Yang, J. Y. H., & Yang, P. (2019) · Briefings in Bioinformatics · doi:10.1093/bib/bby076 · Cited by 138 · see citing works
DREM 2.0: Improved reconstruction of dynamic regulatory networks from time-series expression data
Schulz, M. H., Devanny, W. E., Gitter, A., Zhong, S., Ernst, J., & Bar‐Joseph, Z. (2012) · BMC Systems Biology · doi:10.1186/1752-0509-6-104 · Cited by 134 · see citing works
EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN GraphPreprint
Fu, C., & Cai, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.07228 · Cited by 107 · see citing works
Lin, E., Mukherjee, S., & Kannan, S. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-3401-5 · Cited by 81 · see citing works
Self-assembling manifolds in single-cell RNA sequencing data
Tarashansky, A. J., Xue, Y., Li, P., Quake, S. R., & Wang, B. (2019) · eLife · doi:10.7554/elife.48994 · Cited by 80 · see citing works
Self-citationNormalization of single-cell RNA-seq counts by log( x + 1) or log(1 + x )
Booeshaghi, A. S., & Pachter, L. S. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab085 · Cited by 78 · see citing works
Wang, J. M., Cheng, Y., Shi, L., Ying, R. S., Wu, X. Y., Li, G. Y., Moorman, J. P., & Yao, Z. Q. (2013) · Journal of Virology · doi:10.1128/jvi.01515-13 · Cited by 70 · see citing works
A multiresolution framework to characterize single-cell state landscapes
Mohammadi, S., Dávila-Velderrain, J., & Kellis, M. (2020) · Nature Communications · doi:10.1038/s41467-020-18416-6 · Cited by 64 · see citing works
Platelet influence on T- and B-cell responses
Sowa, J. M., Crist, S. A., Ratliff, T. L., & Elzey, B. D. (2009) · Archivum Immunologiae et Therapiae Experimentalis · doi:10.1007/s00005-009-0032-y · Cited by 54 · see citing works
Activated platelet–T-cell conjugates in peripheral blood of patients with HIV infection
Green, S. A., Smith, M., Hasley, R. B., Stephany, D., Harned, A., Nagashima, K., Abdullah, S. A. A., Pittaluga, S., Imamichi, T., Qin, J., et al. (2015) · AIDS · doi:10.1097/qad.0000000000000701 · Cited by 52 · see citing works
Disease state prediction from single-cell data using graph attention networks
Ravindra, N. G., Sehanobish, A., Pappalardo, J. L., Hafler, D. A., & van Dijk, D. (2020) · ACM Conference on Health, Inference, and Learning (CHIL) · doi:10.1145/3368555.3384449 · Cited by 47 · see citing works
Single-Cell Clustering Based on Shared Nearest Neighbor and Graph Partitioning
Zhu, X., Zhang, J., Xu, Y., Wang, J., Peng, X., & Li, H. (2020) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-019-00357-4 · Cited by 40 · see citing works
Towards Gene Expression Convolutions using Gene Interaction GraphsPreprint
Dutil, F., Cohen, J., Weiß, M., Derevyanko, G., & Bengio, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.06975 · Cited by 28 · see citing works
Unsupervised generative and graph representation learning for modelling cell differentiation
Bica, I., Andrés-Terré, H., Cvejic, A., & Lió, P. (2020) · Scientific Reports · doi:10.1038/s41598-020-66166-8 · Cited by 20 · see citing works
Self-citationPlatelet Induced Functional Alteration of CD4+ and CD8+ T Cells in HNSCC
Polasky, C., Wendt, F., Pries, R., & Wollenberg, B. (2020) · International Journal of Molecular Sciences · doi:10.3390/ijms21207507 · Cited by 20 · see citing works
Hematopathology: Morphology, Immunophenotype, Cytogenetics, and Molecular Approaches
Naeim, F., Rao, P. N., & Grody, W. W. (2008) · Cited by 18 · see citing works
Pseudotime Reconstruction Using TSCAN
Ji, Z., & Ji, H. (2019) · Methods in molecular biology · doi:10.1007/978-1-4939-9057-3_8 · Cited by 16 · see citing works
Constraining Variational Inference with Geometric Jensen-Shannon DivergencePreprint
Deasy, J., Simidjievski, N., & Lió, P. (2020) · arXiv (Cornell University) · doi:10.17863/cam.65769 · Cited by 15 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 6
- Brody S. et al (2022) How attentive are graph attention networks? Submitted to The Tenth International Conference on Learning Representations, under review.
- Kingma D.P., Welling M. (2014) Auto-encoding variational Bayes. 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings.
- Kipf T.N., Welling M. (2016a) Semi-supervised classification with graph convolutional networks. 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
- Kipf T.N., Welling M. (2016b). Variational graph auto-encoders. Bayesian Deep Learning Workshop (NIPS 2016), December 10, 2016 - Centre Convencions Internacional Barcelona, Barcelona, Spain.
- Maas A.L. et al (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th International Conference on Machine Learning, Atlanta, Georgia, USA, 2013.
- Veličković P. et al (2018) Graph attention networks. 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings
Cited by
Sorted by citations
Graph representation learning in biomedicine and healthcare
Li, M. M., Huang, K., & Zitnik, M. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00942-x · Cited by 294 · see citing works
“Alternatively, variational graph autoen-coders produce cell embeddings and interpretable attention weights, indicating what genes the model attends to when deriving an embedding for a given cell 146 .”
Graph Attention Networks: A Comprehensive Review of Methods and Applications
Vrahatis, A. G., Lazaros, K., & Kotsiantis, S. B. (2024) · Future Internet · doi:10.3390/fi16090318 · Cited by 286 · see citing works
“The CellVGAE model [23] is a graph autoencoder model for studying scRNA-seq data, outperforming other deep learning architectures in terms of training times.”
Transformer Architecture and Attention Mechanisms in Genome Data Analysis: A Comprehensive Review
Choi, S. R., & Lee, M. (2023) · Biology · doi:10.3390/biology12071033 · Cited by 265 · see citing works
Buterez, D., Janet, J. P., Kiddle, S. J., Oglić, D., & Lió, P. (2024) · Nature Communications · doi:10.1038/s41467-024-45566-8 · Cited by 139 · see citing works
“6.”
Self-citationApplication of Deep Learning on Single-Cell RNA Sequencing Data Analysis: A Review
Brendel, M., Su, C., Bai, Z., Zhang, H., Elemento, O., & Wang, F. (2022) · Genomics Proteomics & Bioinformatics · doi:10.1016/j.gpb.2022.11.011 · Cited by 102 · see citing works
SIMBA: single-cell embedding along with features
Chen, H., Ryu, J., Vinyard, M. E., Lerer, A. K., & Pinello, L. (2023) · Nature Methods · doi:10.1038/s41592-023-01899-8 · Cited by 82 · see citing works
“Previous applications of embedding models include functional annotation of genes 35 , modeling TF-binding preferences 13,36 and more recent single-cell RNA-seq analyses 37,38 .”
Matsushima, A., Pineda, S. S., Crittenden, J. R., Lee, H., Galani, K., Mantero, J. C., Tombaugh, G. C., Kellis, M., Heiman, M., & Graybiel, A. M. (2023) · Nature Communications · doi:10.1038/s41467-022-35752-x · Cited by 72 · see citing works
Graph representation learning for single-cell biology
Hetzel, L., Fischer, D. S., Günnemann, S., & Theis, F. J. (2021) · Current Opinion in Systems Biology · doi:10.1016/j.coisb.2021.05.008 · Cited by 55 · see citing works
APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System
Javed, S. H., Ahmad, M. B., Asif, M., Akram, W., Mahmood, K., Das, A. K., & Shetty, S. S. (2023) · IEEE Access · doi:10.1109/access.2023.3291599 · Cited by 49 · see citing works
“The importance of the features of neighboring nodes is determined through the application of Attention Coefficients, which are computed using Eq 9 [43]: Here a is a function that computes the Attention Coefficients and i and j are neighboring nodes.”
MethodFeng, C., Liu, C., & Jiang, D. (2023) · Renewable Energy · doi:10.1016/j.renene.2023.02.053 · Cited by 48 · see citing works
Graph neural networks for single-cell omics data: a review of approaches and applications
Li, S., Hua, H., & Chen, S. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf109 · Cited by 43 · see citing works
An end-to-end attention-based approach for learning on graphs
Buterez, D., Janet, J. P., Oglić, D., & Lió, P. (2025) · Nature Communications · doi:10.1038/s41467-025-60252-z · Cited by 48 · see citing works
Self-citationGraph neural network approaches for single-cell data: a recent overview
Lazaros, K., Koumadorakis, D. E., Vlamos, P., & Vrahatis, A. G. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09662-6 · Cited by 27 · see citing works
“A graph is initially constructed utilizing the Pearson’s correlation coefficient method.”
Ding, Q., Yang, W., Luo, M., Xu, C., Xu, Z., Pang, F., Cai, Y., Anashkina, A. A., Su, X., Chen, N., et al. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac300 · Cited by 13 · see citing works
Application of Deep Learning for Single Cell Multi-Omics: A State-of-the-Art Review
Wani, S. A., Khan, S. A., & Quadri, S. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10230-x · Cited by 13 · see citing works
Modelling local and general quantum mechanical properties with attention-based pooling
Buterez, D., Janet, J. P., Kiddle, S. J., Oglić, D., & Lió, P. (2023) · Communications Chemistry · doi:10.1038/s42004-023-01045-7 · Cited by 13 · see citing works
“…used across the life sciences, with remarkable potential and achievements in computational biology single-cell sequencing data 1,2 ), structural biology (prediction of protein structures 3 and protein sequence design 4 ), drug discovery 5 and simulating rigid and fl uid dynamics 6 being only…”
Self-citationLin, E., Liu, B., Lac, L., Fung, D. L. X., Leung, C. K.-S., & Hu, P. (2023) · Machine Learning Science and Technology · doi:10.1088/2632-2153/acd7c3 · Cited by 12 · see citing works
“VST chooses the top variable genes using the relationship between variance and mean (Buterez et al 2021).”
BackgroundMethodInfluentialA robust multi-scale clustering framework for single-cell RNA-seq data analysis
Jiang, S., Wang, C., Sun, Q., & Zhang, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-03603-6 · Cited by 10 · see citing works
Shahir, J. A., Stanley, N., & Purvis, J. E. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05641-9 · Cited by 9 · see citing works
“…to reconstruct input graphs, adding additional, relevant edges, which can facilitate clustering and other downstream tasks in single-cell analysis [13]. scGNN is another GNN framework for single-cell analysis that selectively prunes edges in the initial k NN graph when pre-processing the data…”
BackgroundMethodApplications for Augmented and Virtual Reality in Robot-Assisted Spine Surgery
Eliahu, K., Liounakos, J. I., & Wang, M. Y. (2022) · Current Robotics Reports · doi:10.1007/s43154-022-00073-w · Cited by 7 · see citing works
Spectral Subspace Clustering for Attributed Graphs
Lin, X., Yang, R., Zheng, H., & Ke, X. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709207 · Cited by 6 · see citing works
Diffusion-based Graph-agnostic Clustering
Xie, K., Yang, R., & Wang, S. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714652 · Cited by 6 · see citing works
Hackenberg, M., Brunn, N., Vogel, T., & Binder, H. (2025) · Communications Biology · doi:10.1038/s42003-025-07872-9 · Cited by 7 · see citing works
“…graph neural networks and graph attention networks have gained popularity for embedding neighborhood information when modeling gene expression data, by incorporating local information about cells with similar expression pro fi les or spatial niche information from spatial transcriptomics 71 – 73 .”
scVGATAE: A Variational Graph Attentional Autoencoder Model for Clustering Single-Cell RNA-seq Data
Liu, L., Wu, X., Yu, J. Q., Zhang, Y., Niu, K., & Yu, A. (2024) · Biology · doi:10.3390/biology13090713 · Cited by 5 · see citing works
“Several methods, including CellVGAE [16] and scVGAE, utilize the GNN structure for cell clustering.”
MethodEnhanced integration of single-cell multi-omics data using graph attention networks
Liao, X., Li, Y., Li, S., Wen, L., Li, X., & Yu, B. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.4c00864 · Cited by 5 · see citing works
Single-cell RNA sequencing data analysis utilizing multi-type graph neural networks
Xu, L., Li, Z., Ren, J., Liu, S., & Xu, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108921 · Cited by 4 · see citing works
Zhu, X., Zhao, L., Teng, F., Meng, S., & Xie, M. (2025) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-025-00702-w · Cited by 5 · see citing works
An, S., Shi, J., Liu, R., Chen, Y., Wang, J., Hu, S., Xia, X., Dong, G., Bo, X., He, Z., et al. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae198 · Cited by 3 · see citing works
“In addition, scMGCA (Yu et al. 2023) and CellVGAE (Buterez et al. 2022) are based on the architectures of graph convolutional autoencoders and variational graph autoencoders with graph attention layers, respectively.”
scCCTR: An iterative selection-based semi-supervised clustering model for single-cell RNA-seq data
Chen, J., Sun, Q., Wang, C., & Gao, C. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.03.018 · Cited by 2 · see citing works
Boosting Single-Cell RNA Sequencing Analysis with Simple Neural AttentionPreprint
Davalos, O. A., Heydari, A. A., Fertig, E. J., Sindi, S., & Hoyer, K. K. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.05.29.542760 · Cited by 2 · see citing works
“The use of attention-based NN for scRNAseq analysis is still in its infancy, with only a few successful scRNAseq applications to date (Yang et al., 2022; Buterez et al., 2021; Xu et al., 2021).”
Tian, S., Ji, C., Ni, J., Wang, Y., & Zheng, C.-H. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3458170 · Cited by 1 · see citing works
“The corresponding generation models also include scVAE [15], DiffVAE [16], and CellVGAE [17].”
Integrating single-cell RNA sequencing with multi-omics to decode disease microenvironments
Devi, A., Pathak, V., Dwibedi, V., Singh, J., Pathak, A. K., George, N., Kumar, A. C. S., Kaur, G., Rath, S. K., & Chatterjee, A. (2026) · Molecular Biology Reports · doi:10.1007/s11033-026-12250-7 · Cited by 1 · see citing works
Matsushima, A., Pineda, S. S., Crittenden, J. R., Lee, H., Galani, K., Mantero, J. C., Kellis, M., Heiman, M., & Graybiel, A. M. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.25.489455 · Cited by 1 · see citing works
Chen, D. J., & Shooshtari, P. (2023) · F1000Research · doi:10.12688/f1000research.125579.1
scGGC: a two-stage strategy for single-cell clustering through cellular gene pathway construction
Zhang, Z., Sun, Q., Wang, C., & Jiang, S. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf368
Shahir, J. A., Stanley, N., & Purvis, J. E. (2024) · Figshare · doi:10.6084/m9.figshare.26667673
Shahir, J. A., Stanley, N., & Purvis, J. E. (2024) · Figshare · doi:10.6084/m9.figshare.26667676
Shahir, J. A., Stanley, N., & Purvis, J. E. (2024) · Figshare · doi:10.6084/m9.figshare.26667670
Shahir, J. A., Stanley, N., & Purvis, J. E. (2024) · Figshare · doi:10.6084/m9.figshare.26667679
Multi-omics Single-Cell Data Integration via High-Order Kernel Spectral Clustering
Jiang, H., & Ching, W. (2026) · Intelligent control and learning systems · doi:10.1007/978-981-95-3129-5_11
Min, S., Lac, L., & Hu, P. (2026) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2026.01.010
“With its ability to learn different representations from cell interaction graphs, GAT has turned out to be very efficient for scRNA-seq data analysis and is quite proficient with respect to cell classification tasks [8].”
Fu, Z., Fu, J., Wang, X., Liu, Y., & Ran, T. (2026) · Frontiers in Genetics · doi:10.3389/fgene.2026.1863100
“CellVGAE also uses graph attention networks for an unsupervised scRNA-seq VAE analysis framework (Buterez et al., 2022).”
Zhang, G., Qin, M., Kou, X., Luo, H., Wang, J., & Luo, J. (2026) · Journal of Computational Biology · doi:10.1177/15578666261465432
“CellVGAE (Buterez et al., 2022) is a neural model for clustering based on a variational graph AE with a graph attention layer. scFseCluster (Wang et al., 2023) incorporates a metaheuristic algorithm to extract the optimal set of genes that can enhance scRNA-seq data clustering analysis. scVI (Lopez…”
Chaudhary, D., Yadalam, P. K., & Ganesh, P. (2026) · Journal of Indian Society of Periodontology · doi:10.4103/jisp.jisp_566_25
“[12,13] The main modeling component, the hybrid GAT-AE, [14-16] is designed to learn latent node representations and reconstruct interaction scores.”
GCAN: A data feature learning method for scRNA-seq data
Bai, J., & Xu, L. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.109295
scLTF: A self-training clustering framework for large-scale single-cell RNA-Seq data
Yuan, H., Wang, C., Sun, Q., Sun, M., & Fan, M. (2026) · PLoS ONE · doi:10.1371/journal.pone.0359153
“On the other hand, methods based on variational autoencoders, such as cellVGAE [28], model cellular relationships via graph-based encoding and decoding, improving clustering performance and stability; however, they incur high computational cost, particularly when applied to large-scale single-cell…”
Generation of scRNA-seq Data by Combining Generation Adversarial Network and Label
Zhu, X., Qiao, T., Teng, F., Lyu, Q., Zhou, Y., & Xiong, C. (2026) · International Conference on Information Science and Technology · doi:10.1109/icist71072.2026.11727687
- Authors
- Buterez, D., Bica, I., Tariq, I., Andrés-Terré, H., & Liò, P.
- Affiliations
- University of Cambridge (GB)
- University of Oxford (GB)
- Massachusetts Institute of Technology (US)
- Department of Computer Science and Technology, University of Cambridge , Cambridge CB3 0FD, UK
- Corresponding author
- Buterez, David
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2021-12-02
- Volume
- 38
- Issue
- 5
- Pages
- 1277-1286
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC8825872
- OpenAlex
- W4226296494
- Cited by
- 44
- References
- 65
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 9 · 2023: 9 · 2022: 5 · 2021: 1
- FWCI
- 2.12
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion, cc-by)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- variational graph autoencoder, graph attention networks, single-cell RNA sequencing, unsupervised dimensionality reduction, cell clustering, interpretability, pseudotime, graph neural networks
- MeSH terms
- Single-Cell Gene Expression Analysis, Cluster Analysis, Sequence Analysis, RNA, Gene Expression Profiling, Workflow, Single-Cell Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
