The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
Deep generative modeling for single-cell transcriptomics
Open accessPublished version of a preprint
Abstract
Single-cell transcriptome measurements can reveal unexplored biological diversity, but they suffer from technical noise and bias that must be modeled to account for the resulting uncertainty in downstream analyses. Here we introduce single-cell variational inference (scVI), a ready-to-use scalable framework for the probabilistic representation and analysis of gene expression in single cells ( https://github.com/YosefLab/scVI ). scVI uses stochastic optimization and deep neural networks to aggregate information across similar cells and genes and to approximate the distributions that underlie observed expression values, while accounting for batch effects and limited sensitivity. We used scVI for a range of fundamental analysis tasks including batch correction, visualization, clustering, and differential expression, and achieved high accuracy for each task.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Importantly, both Harmony’s and scVI’s design inherently incorporates batch labels in its training process.”
From Zero-shot evaluation reveals limitations of single-cell foundation models (2025) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“On the other hand, the transcriptional state of individual cells may vary in ways that are poorly captured in pseudo-bulk (for example, due to the presence of multiple cell types)38.”
From Transcriptome-wide analysis of differential expression in perturbation atlases (2025) · cites this paper as [38]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Both scGPT and Geneformer produce cell embeddings intended to project potentially noisy gene expression measurements to a more biologically relevant latent space [18–21], and then these cell embeddings are fine-tuned for cell type classification.”
From Zero-shot evaluation reveals limitations of single-cell foundation models (2025) · cites this paper as [20]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For instance, in scRNA-seq analysis, zero-inflated autoencoders were introduced to handle data sparsity by employing a specialized loss function that aligns with the binomial distribution of single-cell data [33].”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [33]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Multi-omics integration represents another natural application area, where specialized agents analyze transcriptomic, epigenomic, proteomic, and spatial datasets, reconciling heterogeneous signals through shared representation spaces, a task particularly suited to foundation models capable of cross-modal alignment [12, 43, 44].”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [43]
Experimental — accuracy not yet measured
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
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 [47]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Importantly, statistical and deep-learning methods designed for single-cell RNA-seq data often utilize a negative binomial (or zero-inflated negative binomial) error model [10, 15].”
From Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression (2019) · cites this paper as [10]
In the citing paper
“Latent representations, as learned by frameworks such as single-cell variational inference41, can be used for batch correction, clustering, visualization and DGE analysis.”
From Best practices for single-cell analysis across modalities (2023) · cites this paper as [41]
In the citing paper
“Recently, deep learning has been used to produce an embedded workflow that can fit the data, denoise it and perform downstream analysis such as clustering and differential expression within the framework of the model (scVI: Lopez et al, 2018).”
From Current best practices in single-cell RNA-seq analysis: a tutorial (2019) · cites this paper as Lopez et al, 2018
In the citing paper
“Current proposed single-cell foundation models produce cell embeddings. These embeddings are intended to project potentially noisy gene expression measurements to a more biologically relevant latent space and to thus improve our ability to resolve cell types, consistent with previous machine learning methods in this field (including scVI) [30, 31, 24, 32].”
From Assessing the limits of zero-shot foundation models in single-cell biology (2023) · cites this paper as [24]
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
Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2
Love, M. I., Huber, W., & Anders, S. (2014) · Genome Biology · doi:10.1186/s13059-014-0550-8 · Cited by 95,106
Robinson, M. D., McCarthy, D. J., & Smyth, G. K. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btp616 · Cited by 41,364
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Data Analysis Using Regression and Multilevel/Hierarchical Models
Gelman, A., & Hill, J. (2006) · doi:10.1017/cbo9780511790942 · Cited by 13,597
Kass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
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
Adjusting batch effects in microarray expression data using empirical Bayes methods
Johnson, W. E., Li, C., & Rabinovic, A. (2007) · Biostatistics · doi:10.1093/biostatistics/kxj037 · Cited by 8,658
Massively parallel digital transcriptional profiling of single cells
Zheng, G. X. Y., Terry, J. M., Belgrader, P., Ryvkin, P., Bent, Z. W., Wilson, R., Ziraldo, S. B., Wheeler, T. D., McDermott, G. P., Zhu, J., et al. (2017) · Nature Communications · doi:10.1038/ncomms14049 · Cited by 7,353
Highly parallel genome-wide expression profiling of individual cells using nanoliter droplets.
Macosko, E. Z., Basu, A., Satija, R., Nemesh, J., Shekhar, K., Goldman, M., Tirosh, I., Bialas, A. R., Kamitaki, N., Martersteck, E. M., et al. (2015) · Cell · doi:10.1016/j.cell.2015.05.002 · Cited by 7,110
Research works printed but not linked: 1
- Sønderby, C. K., Raiko, T., Maaløe, L., Sønderby, S. K. & Winther, O. Ladder variational autoencoders. In Advances in Neural Information Processing Systems (eds Lee, D. D. et al.) 3738–3746 (NIPS Foundation, La Jolla, CA, 2016).
Cited by
Sorted by citations
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
Dictionary learning for integrative, multimodal and scalable single-cell analysis
Hao, Y., Stuart, T., Kowalski, M. H., Choudhary, S., Hoffman, P., Hartman, A., Srivastava, A., Molla, G., Madad, S., Fernandez-Granda, C., et al. (2024) · Nature Biotechnology · doi:10.1038/s41587-023-01767-y · Cited by 5,631
Hafemeister, C., & Satija, R. (2019) · Genome Biology · doi:10.1186/s13059-019-1874-1 · Cited by 4,479
“Importantly, statistical and deep-learning methods designed for single-cell RNA-seq data often utilize a negative binomial (or zero-inflated negative binomial) error model [10, 15].”
MethodOpportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
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
Metadata
- Authors
- Lopez, R., Regier, J., Cole, M. B., Jordan, M. I., & Yosef, N.
- Affiliations
- University of California, Berkeley (US)
- Ragon Institute of MGH, MIT and Harvard (US)
- Corresponding author
- Yosef, Nir
- Venue
- Nature Methods
- Published
- 2018-11-30
- Volume
- 15
- Issue
- 12
- Pages
- 1053-1058
- ISSN
- 1548-7091 (ISSN-L)
- 1548-7105
- PMC
- PMC6289068
- OpenAlex
- W2901677030
- Cited by
- 2,530
- References
- 55
- Citations by year
- 2026: 588 · 2025: 489 · 2024: 409 · 2023: 311 · 2022: 248 · 2021: 239 · 2020: 155 · 2019: 80 · 2018: 11
- FWCI
- 43.21
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc-nd
- www.springer.com/tdm (tdm)
- Locations
- Nature Methods (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México
- National Institute of Allergy and Infectious Diseases (R38AI140299, U19AI090023)
- 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 › Gene Regulatory Network Analysis
- Keywords
- single-cell transcriptomics, single-cell RNA sequencing, deep generative models, batch effect correction, differential gene expression, cell clustering, uncertainty quantification
- MeSH terms
- Algorithms, Animals, Brain, Hematopoietic Stem Cells, Humans, Leukocytes, Mononuclear, Models, Biological, Genetic Variation, Cluster Analysis, Sequence Analysis, RNA, Computational Biology, Mice, Single-Cell Analysis, High-Throughput Nucleotide Sequencing, Transcriptome
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
