The DOI matches its Crossref record; 77 of the 80 references it cites were found in a registry or an index.
DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning
Open accessPublished version of a preprint
Abstract
Recent technological advances have enabled DNA methylation to be assayed at single-cell resolution. However, current protocols are limited by incomplete CpG coverage and hence methods to predict missing methylation states are critical to enable genome-wide analyses. We report DeepCpG, a computational approach based on deep neural networks to predict methylation states in single cells. We evaluate DeepCpG on single-cell methylation data from five cell types generated using alternative sequencing protocols. DeepCpG yields substantially more accurate predictions than previous methods. Additionally, we show that the model parameters can be interpreted, thereby providing insights into how sequence composition affects methylation variability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
![Fig. 1 DeepCpG model training and applications. a Sparse single-cell CpG profiles as obtained from scBS-seq [5] or scRRBS-seq [6–8]. Methylated CpG sites are denoted by ones, un-methylated CpG sites by zeros, and question marks denote CpG sites with unknown methylation state (missing data). b Modular architecture of DeepCpG. The DNA module consists of two convolutional and pooling layers to identify predictive motifs from the local sequence context and one fully connected layer to model motif interactions. The CpG module scans the CpG neighbourhood of multiple cells (rows in b) using a bidirectional gated recurrent network (GRU) [36], yielding compressed features in a vector of constant size. The Joint module learns interactions between higher-level features derived from the DNA and CpG modules to predict methylation states in all cells. c, d The trained DeepCpG model can be used for different downstream analyses, including genome-wide imputation of missing CpG sites (c) and the discovery of DNA sequence motifs that are associated with DNA methylation levels or cell-to-cell variability (d)](https://figures.cochat.ai/paper-figures/c8d0305c11cd486e9fe8d46d590d7332/deepcpg-accurate-prediction-of-single-cell-dna-methylation-states-using-deep-figure-1.jpg)
![Fig. 2 DeepCpG accurately predicts single-cell CpG methylation states. a Genome-wide prediction performance for imputing CpG sites in 18 serum-grown mouse embryonic stem cells (mESCs) profiled using scBS-seq [5]. Performance is measured by the area under the receiver-operating characteristic curve (AUC), using holdout validation. Considered were DeepCpG and random forest classifiers trained either using DNA sequence and CpG features (RF) or using additional annotations from corresponding cell types (RF Zhang [12]). Additionally, two baseline methods were considered, which estimate methylation states by averaging observed methylation states, either across consecutive 3-kbp regions within individual cells (WinAvg [5]) or across cells at a single CpG site (CpGAvg). b Performance breakdown of DeepCpG and RF, comparing the full models to models trained using either only methylation features (DeepCpG CpG, RF CpG) or only DNA features (DeepCpG DNA, RF DNA). c AUC of the methods as in (a) stratified by genomic contexts with increasing CpG coverage across cells. Trend lines were fit using local polynomial regression (LOESS [72]); shaded areas denote 95% confidence intervals. d AUC for alternative sequence contexts with All corresponding to genome-wide performance as in (a). e Genome-wide prediction performance on 12 2i-grown mESCs profiled using scBS-seq [5], as well as three cell types profiled using scRRBS-seq [8], including 25 human hepatocellular carcinoma cells (HCC), six HepG2 cells, and six additional mESCs. CGI CpG island, LMR low-methylated region, TSS transcription start site](https://figures.cochat.ai/paper-figures/10aab17512ee47c288002824ad541a83/deepcpg-accurate-prediction-of-single-cell-dna-methylation-states-using-deep-figure-2.jpg)
![Fig. 3 Discovered sequence motifs associated with DNA methylation. Clustering of 128 motifs discovered by DeepCpG. Shown are the first two principal components of the motif occurrence frequencies in sequence windows (activity). Triangles denote motifs with significant (FDR <0.05) similarity to annotated motifs in the CIS-BP [42] or UniPROPE [43] databases. Marker size indicates the average activity; the estimated motif effect on methylation level is shown by colour. Sequence logos are shown for representative motifs with larger effects, including ten annotated motifs](https://figures.cochat.ai/paper-figures/e73e22be19b148fa8d9ab56806071a5e/deepcpg-accurate-prediction-of-single-cell-dna-methylation-states-using-deep-figure-3.jpg)


Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“They showed that regions with increased methylation variability associate significantly more strongly to gene expression, indicating functional relevance.”
From Mapping gene regulatory networks from single-cell omics data (2018) · cites this paper as [75]
In the citing paper
“One possible way to deal with technical dropouts is proposed by Angermueller et al. [75] by developing DeepCpG, a computational approach based on deep neural networks, to predict missing methylation states and link methylation states to motifs.”
From Mapping gene regulatory networks from single-cell omics data (2018) · cites this paper as [75]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Additionally, we compared DeepCpG to random forest classifiers [37] trained on individual cells using the DNA sequence information and neighbouring CpG states as input ( RF ).”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“The learning rate was adapted by Adam [65] and decayed by a factor of 0.”
MethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2014) · Cited by 33,419
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 1×
“RNNs have been successfully used for modelling long-range dependencies in natural language [58, 59], acoustic signals [60] and, more recently, genomic sequences [61, 62].”
Method(2010) · Cited by 14,134
WebLogo: A Sequence Logo Generator: Figure 1
Crooks, G. E., Hon, G., Chandonia, J.-M., & Brenner, S. E. (2004) · Genome Research · doi:10.1101/gr.849004 · Cited by 12,386 · cited 2×
“Selected sequence windows were aligned and visualised as sequence motifs using WebLogo [69] version 3.”
MethodInfluentialBackpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 1×
“Here, we report DeepCpG, a computational method based on deep neural networks [17 – 19] for predicting single-cell methylation states and for modelling the sources of DNA methylation variability.”
MethodRobust Locally Weighted Regression and Smoothing Scatterplots
Cleveland, W. S. (1979) · Journal of the American Statistical Association · doi:10.1080/01621459.1979.10481038 · Cited by 11,594 · cited 1×
“Trend lines were fit using local polynomial regression (LOESS [72]); shaded areas denote 95%”
Method
Research works printed but not linked: 1
- Denas O, Taylor J. Deep modeling of gene expression regulation in an erythropoiesis model. Represent. Learn. ICML Workshop. 2013
Cited by
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
A guide to deep learning in healthcare
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
Opportunities 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
“[216] trained a neural network to predict the .”
BackgroundDeep Learning for Health Informatics
Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., & Yang, G.-Z. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2636665 · Cited by 2,000
Metadata
- Authors
- Angermueller, C., Lee, H. J., Reik, W., & Stegle, O.
- Affiliations
- European Bioinformatics Institute (GB)
- Babraham Institute (GB)
- Corresponding author
- Angermueller, Christof
- Stegle, Oliver
- Venue
- Genome Biology
- Published
- 2017-04-11
- Volume
- 18
- Issue
- 1
- Pages
- 67-67
- ISSN
- 1465-6906 (ISSN-L)
- 1474-760X
- PMC
- PMC5387360
- OpenAlex
- W2952935243
- Cited by
- 536
- References
- 80
- Citations by year
- 2026: 28 · 2025: 51 · 2024: 50 · 2023: 54 · 2022: 52 · 2021: 88 · 2020: 69 · 2019: 66 · 2018: 53 · 2017: 23
- FWCI
- 24.45
- Type
- journal article
- Language
- en
- Update notices
- correction (2017-05-12)
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Genome biology (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, other-oa)
- Apollo (cc-by)
- Funders
- Wellcome Trust
- European Molecular Biology Laboratory
- European Commission
- Biotechnology and Biological Sciences Research Council (BBS/E/B/0000S266, BBS/E/B/0000H334, BBS/E/B/000C0403)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Epigenetics and DNA Methylation
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
- Keywords
- single-cell DNA methylation, deep neural network, model interpretability, sequence composition
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. https://app.cochat.ai/papers/10.1186/s13059-017-1189-z
- The paper
- Angermueller, C., Lee, H. J., Reik, W., & Stegle, O. (2017). DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. Genome Biology. https://doi.org/10.1186/s13059-017-1189-z
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.