The DOI matches its Crossref record; 82 of the 83 references it cites were found in a registry or an index, and 1 are not checked yet.
Probabilistic harmonization and annotation of single‐cell transcriptomics data with deep generative models
Open accessPublished version of a preprint
Abstract
As the number of single‐cell transcriptomics datasets grows, the natural next step is to integrate the accumulating data to achieve a common ontology of cell types and states. However, it is not straightforward to compare gene expression levels across datasets and to automatically assign cell type labels in a new dataset based on existing annotations. In this manuscript, we demonstrate that our previously developed method, scVI, provides an effective and fully probabilistic approach for joint representation and analysis of scRNA‐seq data, while accounting for uncertainty caused by biological and measurement noise. We also introduce single‐cell ANnotation using Variational Inference (scANVI), a semi‐supervised variant of scVI designed to leverage existing cell state annotations. We demonstrate that scVI and scANVI compare favorably to state‐of‐the‐art methods for data integration and cell state annotation in terms of accuracy, scalability, and adaptability to challenging settings. In contrast to existing methods, scVI and scANVI integrate multiple datasets with a single generative model that can be directly used for downstream tasks, such as differential expression. Both methods are easily accessible through scvi‐tools.
Overview
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
Verification
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?
The cited source says what the claim attributes to it.
In the citing paper
“To map SEA-AD data to cell types consistently across all 84 donors, we first defined robust transcriptional types, named supertypes, in the BICCN reference; 125 supertypes represented cell types that could be reliably reidentified in reference datasets (mean F1 score = 0.91) using hierarchical probabilistic Bayesian mapping47,48(Extended Data Fig. 5a,b).”
From Integrated multimodal cell atlas of Alzheimer’s disease (2024) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 4×
“We use Adam (Kingma & Ba, 2015) as a first-order stochastic optimizer to update the model parameters.”
InfluentialRobinson, M. D., McCarthy, D. J., & Smyth, G. K. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btp616 · Cited by 41,364 · cited 2×
“Notably, CORAL achieves overall competitive performance except when transferring labels on the MarrowTM pairs, from 10x to Smart-Seq2.”
limma powers differential expression analyses for RNA-sequencing and microarray studies
Ritchie, M. E., Phipson, B., Wu, D., Hu, Y., Law, C. W., Shi, W., & Smyth, G. K. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv007 · Cited by 40,458 · cited 1×
“A wide range of methods have already been developed for this fundamental problem, initially for Microarrays and later on for bulk RNA sequencing, such as ComBat [15] and limma [16] which rely on generalized linear models with empirical Bayes shrinkage to avoid over-correction.”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“We use deterministic warmup [67] and batch normalization [68] in order to learn an expressive model.”
MethodUnpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
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
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
Data Analysis Using Regression and Multilevel/Hierarchical Models
Gelman, A., & Hill, J. (2006) · doi:10.1017/cbo9780511790942 · Cited by 13,597
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 · cited 9×
“…or disease models in order to increase statistical robustness (Wen & Tang, 2018), achieve consistency and reproducibility among studies (Haghverdi et al , 2018; Butler et al , 2018), and ultimately converge to a common ontology of cell states and types (Wagner et al , 2016; Regev et al , 2017).”
InfluentialKass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Flagged first, then by citations
Research works printed but not linked: 4
- Goldberger J, Ben‐Reuven E (2017) Training deep neural‐networks using a noise adaptation layer. In Proceedings of the International Conference on Learning Representations, Toulon, France
- Kingma DP, Mohamed S, Jimenez Rezende D, Welling M (2014) Semisupervised learning with deep generative models. Adv Neural Inf Process Syst 27: 3581–3589
- Kingma DP, Welling M (2014) Auto‐encoding variational Bayes. In Proceedings of the International Conference on Learning Representations, Banff, Canada
- Louizos C, Swersky K, Li Y, Welling M, Zemel R (2016) The variational fair autoencoder. In Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico
Cited by
Sorted by citations
Items 601–700 of 702
Multiscale Grassmann manifolds for single-cell RNA-seq data analysis
Wang, X. X., Cottrell, S., & Wei, G.-W. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae6752
“Deep learning-based approaches such as scDeepCluster [49], DESC [50], scVI [51], and scANVI [52] have also been proposed for single-cell RNA-seq analysis using neural network-based representation learning frameworks.”
Single-Cell Foundation Models: Architectures, Pretraining Strategies, and Benchmarking ChallengesPreprint
Harrison, E., & Johansson, G. (2026) · doi:10.14293/pr2199.003494.v1
Koladiya, A., Good, Z., Varra, S. R., Domizi, P., Bendall, S. C., & Davis, K. L. (2026) · Cancer Research · doi:10.1158/0008-5472.can-25-3699 · Cited by 2
“In contrast, un-supervised or semi-supervised models like scANVI (36) and SpaGCN (37) can identify new clusters or incorporate spatial context more directly—capabilities not currently built into CellFuse.”
Hezil, N., Bouridane, A., Hamoudi, R., Al-Maadeed, S. A., & Talaat, I. M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.30.721868
“Variational autoencoders (VAEs) [35], conditional VAEs [36], and adversarial autoencoders [37] have each been adapted to single-cell genomics [38,39].”
STAT: A multi-agent framework for integrated and interactive spatial transcriptomics analysisPreprint
Chen, Y. H., Han, S., Chao, Z., Liu, Y., Zhang, F., Chen, H., Wang, J., Xiao, J., & Yang, C. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.01.722244 · Cited by 3
“Rather than issuing a single annotation call, the planner recognised that the session contained two cell-resolution slices and one spot-level slice, and expanded the query into a three-step plan: scANVI [9] label transfer for the two Xenium slices and RCTD deconvolution for the Visium slice (Fig.”
On the Role of Embeddings in Diffusion-Based Generation of scRNA-seq Data
Rackl, M., Fuchs, F., & Andreas Hotho, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19096-3_25
Semi-supervised disentangled representation learning for single-cell RNA sequencing data
Liu, H., Zou, Y., & Wei, Z. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag222
“We next evaluated SCDRL on a subset of the CO VID-19 study by Stephenson et al. [30], processed and provided by scvi-tools [31].”
Early-life mucosal T cells direct intestinal stem cell fate via a coordinated developmental programPreprint
Strine, M. S., Gawon, K., Phan, L., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.08.723752
Robust integration of single-cell datasets with imbalanced modality composition
Sheng, Q., Zhou, Y., Zhu, F., Xu, L., & Jin, S. (2026) · Nature Communications · doi:10.1038/s41467-026-72933-4 · Cited by 1
“…and benchmarked Palette against fi ve state-of-the-art mosaic integration methods (Methods), as well as six widely adopted single-modality algorithms spanning both supervised (scANVI 53 , scPoli 54 , and our previously proposed SIGNAL 55 ) and unsupervised settings (fastMNN, Seurat v3, and Harmony).”
scMarkerGene: an interpretable neural network framework for cell-type-specific marker gene discovery
Zhang, J., Kou, S. H., Zhao, J., Li, X., & ZHAO, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag223
Bharadwaj, P. K. (2026) · Research Square · doi:10.21203/rs.3.rs-9709612/v1
Survey of Emerging Trends in Artificial Intelligence for Bioinformatics
Ghanem, S. I. (2025) · International Conference on Computer Theory and Applications (ICCTA) · doi:10.1109/iccta68914.2025.11520011
Computational modelling of cell identity
Shim, W. J., Chow, C. S. Y., Bao, S. C., Zhao, Q., & Palpant, N. J. (2026) · Biochemical Journal · doi:10.1042/bcj20250132
Lee, S., Cho, S., Han, D., Kim, J., Hur, H., Kim, H. H., Cheong, J., & Kim, T.-M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.21.726806
A cross-tissue POSTN+ fibroblast atlas links periodontal, tumor, and fibrotic stromal nichesPreprint
Wang, C., Yang, H., Lin, M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.20.726414
“…in human-only re-derivation; Table S3), and the POSTN+/KLF4 contrast — are not load-bearing on the absolute mouse-context POSTN+ frequencies. scANVI[19] was not run because no harmonised cell-type label is available across the eight cohorts; the only globally defined cell-level annotation in our…”
Atlas-Level Single-Cell and Spatial Transcriptomics Data Integration via PRIMEPreprint
Wu, X., Wang, X., Wang, J., & Wan, S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.20.726698
Mahmoud, A., Sukhwa, C., Giarrizzo, M., Choi, P. H., Pintar, J., Walch, H., Zhao, N., Bermeo, J., Chung, S. K., Raghavan, M. S., et al. (2026) · Developmental Cell · doi:10.1016/j.devcel.2026.04.014 · Cited by 1
MOREAU, T. R., Aquino, Y., Zhu, Y. Y. J., Bondet, V., Vega, C. A., Donnadieu, F., Dubois, F., Periou, B., Rahal, F., TIZERARINE, M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.27.728148
“14.6) [ 62 ] to transfer immune-lineage labels from the GEX to the ATAC data points from each sample.”
InfluentialUSADAE: a deep learning approach to disentangle hidden covariates in RNA-seq data
Chen, X., Guo, L., Chen, Y., Mo, D., & Liu, X. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag261
“Autoencoder-based frameworks like BERMUDA [ 17], scVI [ 18, 19], DESC [ 20], scANVI [ 21], and Fugue [ 22] employ reconstruction losses to learn low-dimensional embeddings that preserve cellular identity while correcting batch effects. deepMNN [ 23] abandons autoencoders for a residual network,…”
Kövér, B., Willis, T. L., Sherwin, O., Kaufman-Cook, J., Kemkem, Y., Segoviano, M. V., Lodge, E. J., Zamojski, M., Mendelev, N., Zhang, Z., et al. (2026) · Yearbook of pediatric endocrinology · doi:10.1016/j.celrep.2026.117407 · Cited by 2
A Common Reference Landscape of Mouse CD4+ T Cell StatesPreprint
Mehrotra, N., Bangs, D. J., Figueroa, A. L., Bee, G. C. W., Lai, R., Shinkawa, T., Osum, K. C., Freuchet, A., Zhang, Z., Nogueira, L., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.29.728553 · Cited by 1
Hierarchical classification of immune cell transcriptomes at population-scalePreprint
Beltz, C., Qiu, Z., Sadowski, L., Kraske, J. A., Aggarwal, A., Quintanal-Villalonga, À., Manoj, P., Littbarski, A., Bajaj, S., Meškauskaitė, B., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.30.728980 · Cited by 1
Park, C., Choi, J. M., & Chae, H. (2026) · Journal of Computational Biology · doi:10.1177/15578666261457147
“…with six representative cell-type prediction methods: CellPredX (Liu et al., 2026), HiCat (Bi et al., 2025), scAdapt (Zhou et al., 2021), scSemiCluster (Chen et al., 2021), scNym (Kimmel and Kelley, 2021), scANVI (Xu et al., 2021), Seurat (Butler et al., 2018), and scmap (Kiselev et al., 2018).”
Robust semi-supervised scRNA-seq integration from virtual adversarial learningPreprint
He, C., Filippidis, P., Xing, J., Kleinstein, S., & Guan, L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.07.730754
“Because of their high biological specificity, these markers offer an accessible solution for sub-cell type auto-annotation [12, 22–25], which can also serve as auxiliary information to improve data harmo-49 nization quality through supervised/semi-supervised integration [13, 26–29].”
Doddi, A., Dawes, P., Chan, Y., & Lim, E. T. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.08.727881
Current Practices and Considerations for Benchmarking Human Gastrointestinal Organoids
Brown, M. E., Gleizes, A. R., Yu, Q., Adhikari, U. D., Nagarajan, R., Rout, P., Camp, J. G., Yilmaz, Ö. H., Tape, C. J., Tyska, M. J., et al. (2026) · Cellular and Molecular Gastroenterology and Hepatology · doi:10.1016/j.jcmgh.2026.101832
Fu, Z., Fu, J., Chen, C. F., Zhang, K., Wang, J., Ran, T., & Wang, S. (2026) · Frontiers in Genetics · doi:10.3389/fgene.2026.1822168
“175 versus DIPVAE, InfoVAE, β -TCVAE -TCVAE, These seven classical/linear baselines (PCA, KPCA, ICA, FA, NMF, TSVD, and DICL) collectively serve as the empirical validation of the graph-free linear encoder alternative discussed in the Introduction section: each replaces f θ ( X , A ) with a graph-free linear or kernel…”
InfluentialShi, C. H., Zhai, Y., Chow, S. H.-C., Li, L., Carver, C. M., Teneche, M. G., Flores, J., Kern, C., Adams, P. D., Ren, B., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.13.732076 · Cited by 3
Jia, Q., Goodrich, J. A., & Conti, D. V. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag395
“Among them, scANVI (Xu et al. 2021), a semi-supervised extension of scVI (Lopez et al. 2018), is an effective approach that jointly models labeled reference and unlabeled query data.”
Wan, Z., & Xu, P. (2026) · Infection Genetics and Evolution · doi:10.1016/j.meegid.2026.105969
Kang, J., An, J., & Choi, J. K. (2026) · Journal for ImmunoTherapy of Cancer · doi:10.1136/jitc-2026-015632
“Only the terms with an adjusted p value<0.05 were considered as significant (figure 2b).”
InfluentialOrganoid modeling of lung branching morphogenesis and epithelial lineage specification
Pan, M., Cai, B., Li, G., et al. (2026) · Developmental Cell · doi:10.1016/j.devcel.2026.05.012
Сергеевна, Ч. Е., Shcherbakova, L. N., Vigovskiy, M. A., Ильдарович, Т. А., Logunov, D. Y., Tychinin, D. I., Svetlichnyy, D. V., Kulebyakin, K. Y., Tkachuk, V., & Chechekhin, V. I. (2026) · Nucleic Acids Research · doi:10.1093/nar/gkag612
“2.1) were run with the authors’ default parameters [ 4–7 , 25–27 ].”
InfluentialHu, C., Xiao, B., & Chen, C. Y. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.16.732528
Zhu, Y., Hu, Y., Xie, M. B., Qin, H., Szul, Z. J., Young, D. M., Yuan, W., Wang, Q., Liu, Y. H., Shen, W., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.16.732716
“…approaches, encompassing foundation models (scGPT [15], scCello [27], Nicheformer [16], and SToFM [28]), deep learning models (scANVI [14], Spatial-ID [29], and GraphST [30]), probabilistic frameworks (DestVI [31], Cell2location [1], and RCTD [32]), dimensinality-reduction-based…”
An Integrated muti-omics cell atlas of the human trabecular meshwork and ciliary bodyPreprint
Jian, J., Bao, X., Wang, J., Zheng, Y., Li, J., Shao, J., Yang, T., Yaman, I., Li, J., Chen, H., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.17.732980 · Cited by 1
HeartMap charts new territory in cardiac disease biology
Staudt, D., & Mercola, M. A. (2026) · Nature Cardiovascular Research · doi:10.1038/s44161-026-00835-1
Fu, Z., Fu, J., Wang, X., Liu, Y., & Ran, T. (2026) · Frontiers in Genetics · doi:10.3389/fgene.2026.1863100
“…single-cell representation learning (Lopez et al., 2018; Grønbech et al., 2020). scVI (Lopez et al., 2018) and its semi-supervised extension scANVI (Xu et al., 2021) exemplify this paradigm, fitting a negative-binomial likelihood with a multi-layer perceptron (MLP) encoder to yield Euclidean…”
Multimodal Human Scalp Atlas Defines Cell Landscape and Lineage Architecture In SituPreprint
Li, E. B., Stephens, C. M., Klay, M., Carcamo, A., Han, J., Quan, V. L., Colavincenzo, M. L., Pearlman, R. L., Yoo, S. S., Wang, D., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.29.735239
Transformers for single-cell RNA sequencing: a survey
Hu, T., & Wei, Z. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag332
“…from various papers and observe that Transformers are compared against a range of conventional methods, including: scNym [ 47], SciBet [ 48], Seurat [ 55], SingleR [ 46], SCINA [ 44], Garnett [ 56], scSorter [ 57], CellTypist [ 58], scANVI [ 59], ACTINN [ 60], Scanpy [ 61], and SingleCellNet [ 62].”
An integrated skin cell atlas decodes the pilosebaceous unit
Düz, T., Törőcsik, D., Momnougui, S. M. E., Oubounyt, M., Al, B., Gallinat, S., Baumbach, J., & Holzscheck, N. (2026) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2026.06.1282 · Cited by 1
HLiCA: An integrated cell atlas of the healthy human liverPreprint
Edgar, R. D., Portman, J. R., Hu, H., Pouyabahar, D., Rahman, R. R., Stueckmann, D., Choi, Y., Neavin, D. R., Atif, J., Clarke, Z. A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.30.735539
Cross-dataset annotation harmonization for cell-type hierarchy construction
Zhou, T., Chen, Y., Zhu, Y., Jia, J., Zhang, X., & Wei, L. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag506
“…to batch effects, and reference-to-query tools, such as Seurat and scANVI (Butler et al. 2018, Kiselev et al. 2018, de Kanter et al. 2019, Stuart et al. 2019, Xu et al. 2021), are computationally intensive in pairwise alignment and may ignore hierarchical relationship between cell types.”
McMullen, R., Pavlovic, B. J., Swope, D., Aley, D., Schaefer, N. K., & Pollen, A. A. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.13.738326
Li, Y.-C., Wei, M., Wang, X.-F., Wang, Z., Pan, J., Wang, L., Huang, Y., Huang, Z.-A., & You, Z.-H. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c01857
Ghenciulescu, N., Reinders, M. J. T., & Mahfouz, A. E. (2026) · Biochemistry and Biophysics Reports · doi:10.1016/j.bbrep.2026.102692
“The data includes both the SCRAN-normalized gene counts and a batch-corrected, 30-dimensional embedding obtained using scANVI [48] during dataset integration.”
A single-cell atlas of cancer-educated ecotypes across high-risk pediatric sarcomasPreprint
Seitz, C. M., Catacora, K., Scheuermann, S., Fischer, T. T., Engelmann, F., King, A., Imle, R., Nuernbergk, A., Kristmann, B., Mallm, J., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-10374394/v1 · Cited by 1
Brodeur, T. Y., Lanser, T. B., Salter, L., Sessions, K. J., Hogan, T. C., Bonney, E. A., McGee, E. A., Frietze, S. E., & Krementsov, D. N. (2026) · The Journal of Immunology · doi:10.1093/jimmun/vkag153 · Cited by 1
Organism-scale annotation with Pan-human AzimuthPreprint
Sarkar, S., Li, Z., Molla, G., Shenoy, A., Zhang, B. Y., Collins, D., Vasilevsky, N., Gaut, J. P., Puig-Barbe, A., Bueckle, A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.16.738997 · Cited by 2
Du, Z., Zhang, X., Zhang, Q. P., Li, J., Cao, Z., Gao, G., Lin, T., Wang, D., & Gao, S. (2026) · Genome Research · doi:10.1101/gr.281629.125
Mao, Q., Ahmadi, A., de Vries, S. I., Heezen, L. G. M., Vacca, O., Doisy, M., Aartsma-Rus, A. M., van Putten, M., Goyenvalle, A., Mahfouz, A. E., et al. (2026) · iScience · doi:10.1016/j.isci.2026.116906
Kanannejad, S., Bongiorni, N., Nordera, E., Redaelli, S., Rusconi, I., Zanin, R., Giustacchini, A., & Chatterjee, S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.27.740477
“A label applied to a transcriptionally heterogeneous group can also be actively misleading when used with tools that train classifiers to transfer cell type labels from reference to query datasets [28, 52, 60].”
Jurgens, E. M., Mitra, S., Herrera, K., Nemirovsky, D., Bready, B., Derkach, A., Hosszu, K., McAvoy, D. P., Firestone, R., Rajeeve, S., et al. (2026) · Science Translational Medicine · doi:10.1126/scitranslmed.aed0039 · Cited by 2
Jiang, L., Chien, C., Zhang, H., et al. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1894439
“The snRNA-seq and spatial transcriptome data were processed using the “Seurat” package (Xu et al., 2021).”
Zang, M., Xuan, Y., Li, G., Liu, Y., Chen, J., Lu, J., Liu, F., & Pan, H. (2026) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2026.154385
scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
Yan, X., Zang, Z., Chi, C., Zhou, J., Yu, C., Wu, J., Cheng, S., Yang, F., Luo, J., Lei, Z., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818917
“Comparison with scANVI [33] (Table 4) shows that scHelix consistently yields superior integration.”
Move BeTween modAlities (MBTA) employs flow matching to predict single cell data modalitiesPreprint
Xu, B., Zhang, Y., & Michor, F. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.05.743110
“However, users may instead rely on other batch correction methods [66, 67, 68] to project the query data to the reference data.”
Zhubanchaliyev, A., Najm, M., Laigle, V., Bonnet, É., & Martignetti, L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.07.743516
“After scANVI [41] integration to correct institution-level technical variation, scROMA in base mode identified 26 significantly active Hallmark pathways [8] at single-cell resolution (Fig.”
InfluentialClassification of Tex10-Deficient Spermatogenesis Using Deep Learning
Zhang, G., & Chen, Y. (2026) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/ids69480.2026.00028
“Extending this model, we then apply single-cell ANnotation using Variational Inference (scANVI) [5] to perform classification, transferring developmental labels from healthy wild-type cells to the Tex10-deficient population.”
Wilson, A. P., Chaaban, H., & Burge, K. Y. (2026) · Bioinformatics and Biology Insights · doi:10.1177/11779322261477368
“More recently, probabilistic models such as scANVI, 8 interpretable statistical methods such as PCLDA, 9 and deep-learning-based approaches such as scSorterDL, 10 have sought to improve the identification and characterization of complex cellular states.”
Wang, N., Cardenas, C., Caballero, V. E. N., Turner, D., Feinberg, H., Yuan, D., Scott, N., DeBerardine, M., Dan, S., Caceres, L., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.06.743394
“Additionally, some integration methods attempt to use a semi-supervised approach, such as scANVI 52 .”
Translational insights and clinical challenges of targeting cancer stem cells
Ahmed, M., Al-Haidari, A., Agarwal, S., Sun, J., Hammarlund, E. U., Rönnstrand, L., Pienta, K. J., Tatlı, Ö., & Kazi, J. U. (2026) · Signal Transduction and Targeted Therapy · doi:10.1038/s41392-026-02887-y · Cited by 1
“149 These approaches also support biomarker identi fi cation in clinical contexts by linking gene signatures to drug-response predictions that can guide treatment hypotheses.”
Park, S., Clarke, H. H., Cao, F., Rose, A., Yang, E., Felix, R. R., Read, J., Chen, J., Pauli, J. L., & Palmiter, R. D. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.07.743567
“Class and subclass labels were further validated against the Allen taxonomy by using scanVI 38 to compare neighboring cells’ identification with labeled Allen taxonomy.”
Inhibition of salt-inducible kinases 2 and 3 reduces inflammatory signature in psoriasis
Pilz, A. C., Briem, E., Colli, M. L., Hillig, C., Lavazais, S., Menden, M. P., Biedermann, T., Lauffer, F., Eyerich, K., Vos, S. D., et al. (2026) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2026.07.033
Central T cell tolerance from sparse peptide sampling
Meyer, H. V., Dasgupta, S., Banerjee, A., Lin, Y., Prabakar, R. K., Chapin, S. R., Kingsford, C., & Navlakha, S. (2026) · Science Advances · doi:10.1126/sciadv.aeg8240
scGraphPilot: Functionally Guided Graph Transfer for Robust Cross-Patient Cell Type Annotation
Li, Y.-C., Huang, Y., Wei, M., et al. (2026) · International Conference on Bioinformatics and Intelligent Computing (BIC) · doi:10.1145/3809986.3810021
“To further assess the effectiveness of the proposed framework, scGraphPilot was compared with nine widely used cell type annotation approaches, including MarkerCount [18], SingleR [19], scmap-Cell [20], scClassify [21], SciBet [22], treeArches [23], scANVI [24], scPoli [25], and scGPT [26].”
Gao, Z., Wang, S., Qiu, D., Wei, X., Ma, T., Wang, S., Zhang, Y., Cao, W., Deng, W., Yao, L., et al. (2026) · Biosafety and Health · doi:10.1016/j.bsheal.2026.08.003
Data-centric feedback loops for next-generation immunotherapy development
Shalita, R., & Amit, I. (2026) · Nature Biomedical Engineering · doi:10.1038/s41551-026-01785-6
Fanijo, S. O., Jannesari, A., & Dickerson, J. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100983
Comprehensive Guide to Gene Expression Analysis from Bulk and Single-Nucleus Transcriptomes
Sankaraeswaran, A., Taguchi, Y.-H., & Gromiha, M. M. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5284-8_10
scOLAR: Ontology-Anchored Open-Set Annotation of Single-Cell RNA-seq DataPreprint
Liu, Y., Yi, S., Yin, H., & Ju, W. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.05.749179
Ageas enables time-agnostic cell fate inference from single-cell and spatial multi-omics dataPreprint
Jiang, J., Kong, A., & Yu, G. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.30.748098 · Cited by 1
“…and applied iterative fine-tuning to resolve ambiguities among closely re-711 lated cell subtypes using discriminative variable genes. scANVI [36] is a deep generative model that extends variational autoencoders to perform semi-supervised learning, mapping both labeled and unlabeled cells…”
Cell-based therapies of autoimmune diseases in the context of artificial intelligence development
Dinesh, D., Das, S. S., Bhattacharya, B., & Pai, K. S. R. (2026) · Clinical and Experimental Medicine · doi:10.1007/s10238-026-02302-4
“…than working in isolation, tools like scANVI (Single-Cell ANNotation using Variational Inference) leverage semi-supervised variational autoencoders to align cell types across diverse autoimmune datasets, boosting accuracy where earlier, fully unsuper - vised techniques fall short [30 ](Table 1).”
Jiang, T., Foster, A. R., Pournara, A. V., Steele, L., Shabbir, M., Smith, E., Evans, K., Baxter, T., Diddams, K., Wright, L., et al. (2026) · medRxiv · doi:10.64898/2026.09.02.26362057
Sun, L., Ma, L., Chen, L., Cai, W., 韦建瑞, Guo, K., Gu, H., & Zhou, L. (2026) · The International Journal of Biochemistry & Cell Biology · doi:10.1016/j.biocel.2026.107027
Systematic benchmarking and optimal strategy selection of cross-species integration methods
Wang, R., Zheng, J., Mao, C., Zhang, Y., Ding, Z., & Wang, G. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag490
“This study applied the scVI [ 38], scANVI [ 39], and neural network models based on hierarchical Bayesian frameworks for cross-species data integration ( Supplementary Table S3).”
A Survey on the Evolution and Future Trajectory of Flow Cytometry Analysis
Xu, T., Putri, G., Chuah, A., Vlieger, R., & Brüstle, A. (2026) · ACM Computing Surveys · doi:10.1145/3845984
Hagen, T., Liu, I., Nagainis, A. A., Khosrojerdi, N., Yousefi, H., Gunnels, T., Moarefi, A. H., Green, K., Azimi, N., Momen-Roknabadi, A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.13.751267
TORC: Target-Oriented Reference Construction for Supervised Cell-Type Identification in scRNA-seq
Wei, X., Ma, W., Wu, Z., & Wu, H. S. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5539-9_5
Accurate and scalable decontamination of imaging-based spatial transcriptomics via optimal transportPreprint
Chen, Y., Liu, Y., Chao, Z., Han, S., Zeng, Y., Yu, B., Zhang, F., Wu, A. R., Wang, J., Chen, H., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.09.750350
“Cell-type labels were transferred from the cor-645 responding single-cell reference using scANVI[47, 48], which was trained on the reference and the spatial data together and returned a predicted label and posterior probability for each spatial cell (Supplementary Note 5).”
Solano, L. E., Rahimzadeh, N., Shi, Z., & Swarup, V. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.10.750690
Arts, J. A., Cunha, D. L., Harjuntausta, S., Vattulainen, M., Smits, J. G. A., Bonthuis, I., Bento, D. F., Bocci, F., Skottman, H., & Zhou, H. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.16.751974
“To assign cell state identities to the scATAC-seq clusters, we applied label transfer with scANVI [20] (Supplementary Table 5), integrating chromatin accessibility with gene expression profiles by matching accessible genomic regions detected in scATAC-seq to nearby genes detected in scRNA-seq.”
Chebouba, L., Chehili, H., Bouaziz, A. L., Mahcene, E., & Mahmoudi, N. E. H. (2026) · International Journal of Computational Intelligence and Applications · doi:10.1142/s146902682650046x
Matveeva, K. S., & Shevyrev, D. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27188416
“Within each tissue, we integrated samples using single-cell Variational Inference (scVI) and annotated cell types by transferring labels from matched tissue data in the Tabula Sapiens atlas with scANVI (single-cell Annotation using Variational Inference) [88,89].”
Senescence-directed nanotherapy ameliorates fibrosis and overcomes immune exclusion in cancer
Hinterleitner, C., Barthet, V. J. A., Goldberg, H. V., Vogt, K. C., Perea, A. M., Hillger, L. R., Ruiz, S. B., McHugh, D., Ho, Y.-J., Perez, A. C., et al. (2026) · Science · doi:10.1126/science.aeg4791 · Cited by 1
Cujba, A.-M., Aguilar-Fernández, S., Antoinette, A., Said, W., Müller, M., Kock, K. H., Nestor, J., Sonthalia, R., Buyamin, E. V., Rawat, P., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.21.749940
Neuroendocrine prostate cancer converges on a fetal pulmonary neuroendocrine-like program
Yue, W., Kyprianou, N., Tewari, A. K., & Padanilam, B. J. (2026) · Cancer Genetics · doi:10.1016/j.cancergen.2026.09.011
MiCAS: Mixture-based Cell Annotation with Open-Set Recognition for scRNA-seq DataPreprint
İzci, E., & Doğan, B. (2026) · Research Square · doi:10.21203/rs.3.rs-10438566/v1
Variational inference methods for single-cell genomics
Yu, B., Tan, Z., Chu, H., & Yang, C. (2026) · Statistical Learning and Data Science · doi:10.1016/j.slads.2026.100032
Cell-of-origin shapes tumor subtype in BRCA1 -associated triple-negative breast cancerPreprint
Lev, T., Samy, A. L. P. A., Mallya, S., Adam, I., Pueschl, D., Ma, D., McMullen, T. P., Lev, M. S., Gonzalez, J. G., Longworth, A. J., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.29.755499
Mou, L., Lu, Y., Wu, Z., Zhang, Q., & Pu, Z. (2026) · Xenotransplantation · doi:10.1111/xen.70171 · Cited by 1
Rahman, A., Rahman, A., Mostafa, S., & Islam, M. T. (2026) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms69103.2026.00204
“Deep latent-variable approaches such as scVI and scANVI provide important alternatives, but were treated as outside the scope of this short cross-cancer framework study [13], [14].”
Dupré, J.-S., Signer, M., Rao, J., Adam, L., Gaspa-Toneu, L., Bellavista, M., Cubela, I., Sadiraj, L., Fuhrer, T., Scherer, J., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.10.09.757894
Kimler, K., Lance, C., Bohár, B., Ahmed, A., Zhou, R. R., Bartolomé-Casado, R., Gudiño, V., Flores, R. O. R., Junghus, F. V., Mörbe, U., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.10.09.753994
Emerging frontiers for AI in single-cell genomics
Mitra, S., Li, J., & Leslie, C. S. (2026) · Molecular Cell · doi:10.1016/j.molcel.2026.09.014
IRF7 signalling in tanycytes controls brain–body–immune response across the ovarian cycle
Nampoothiri, S. S., Fernandois, D., Journiac, N., Delahaye, F., Mbouamboua, Y., Sauvé, F., Couralet, M., Gallet, S., Mroueh, N., Aponte, M. L. S., et al. (2026) · Nature Metabolism · doi:10.1038/s42255-026-01635-4
Liu, X., Zhang, B., Zou, K., Wan, R., & Zhu, Q. (2026) · Biosensors · doi:10.3390/bios16100581
“When only a subset of cells in a reference atlas has reliable annotations, representation learning can be coupled to cell-type labels. scANVI extends the scVI generative framework by introducing a discrete cell-type variable and jointly learning from labeled and unlabeled cells [45].”
Spatial Transcriptomics Analysis of Ewing Sarcoma
Luo, H., Grünewald, T. G. P., & Gerstung, M. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5587-0_30
Li, W., & Chang, X. (2026) · Research Square · doi:10.21203/rs.3.rs-11202430/v1
Metadata
- Authors
- Xu, C., Lopez, R., Mehlman, E., Regier, J., Jordan, M. I., & Yosef, N.
- Affiliations
- University of California, Berkeley (US)
- École Polytechnique (FR)
- University of Michigan (US)
- Harvard University (US)
- Corresponding author
- Yosef, Nir
- Venue
- Molecular Systems Biology
- Published
- 2021-01-01
- Volume
- 17
- Issue
- 1
- Pages
- e9620-e9620
- ISSN
- 1744-4292 (ISSN-L)
- PMC
- PMC7829634
- OpenAlex
- W3121168830
- Semantic Scholar
- 58c22899af553a611bbd3acfd8d2b43f86d2b3fe
- Cited by
- 691
- References
- 83
- Citations by year
- 2026: 206 · 2025: 188 · 2024: 126 · 2023: 91 · 2022: 44 · 2021: 29
- FWCI
- 23.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Molecular Systems Biology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- HHS | NIH | National Institute of Allergy and Infectious Diseases (U19 AI090023)
- NIH | National Institute of Mental Health (U19 MH114821)
- 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 Regulatory Network Analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Keywords
- single-cell transcriptomics, data integration, cell type annotation, scVI, scANVI, variational inference, deep generative models, stochastic modeling, uncertainty quantification, semi-supervised learning, differential gene expression
- MeSH terms
- Supervised Machine Learning, Humans, Sequence Analysis, RNA, Computational Biology, Gene Expression Profiling, Databases, Genetic, Molecular Sequence Annotation, 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
