Tracing human stem cell lineage during development using DNA methylation

Salas, Lucas A.; Wiencke, John K.; Koestler, Devin C.; Zhang, Ze; Christensen, Brock C.; Kelsey, Karl T.

doi:10.1101/gr.233213.117

Cited by 31 publications

(45 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MethylNet methodology presents alternative framework to uncover functional gene regulation that accounts for biological age acceleration and goes beyond the limited set of features used to predict methylation age in Horvath, Hannum, and other DNA methylation clocks. As the biology of these clocks are still being discovered [41] and due to the non-linear relationship with both chronological age [42] and other biomarkers of cell epigenetic cell maturation [43], further examination of age acceleration and biology should be done through neural networks.…”

Section: Discussionmentioning

confidence: 99%

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background: DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision. Results: The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences. Conclusion: The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.

show abstract

Section: Discussionmentioning

confidence: 99%

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…MethylNet methodology presents alternative framework to uncover functional gene regulation that accounts for biological age acceleration and goes beyond the limited set of features used to predict methylation age in Horvath, Hannum, and other DNA methylation clocks. As the biology of these clocks are still being discovered 38 and due to the non-linear relationship with both chronological age 39 and other biomarkers of cell epigenetic cell maturation 40 , further examination of age acceleration and biology should be done through neural networks.…”

Section: Strengths Limitations and Future Directionsmentioning

confidence: 99%

MethylNet: An Automated and Modular Deep Learning Approach for DNA Methylation Analysis

Levy

Titus

Petersen

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multicollinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity.DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we have developed MethylNet to make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision. The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences. The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes. challenges, many downstream EWAS analyses have focused on reducing the dimensions into a rich feature set to associate with outcomes. By limiting the number of features through dimensionality reduction and feature selection, analyses become more computationally tractable and the burden of correcting for multiple comparisons is reduced.An important advancement to methylation-based deep learning analyses was the application of Variational Auto-encoders (VAE). Initial deep learning approaches for DNAm data focused on estimating methylation status and imputation, performing classification and regression tasks, and performing embeddings of CpG methylation states to extract biologically meaningful lower-dimensional features [15][16][17][18][19][20][21][22] . VAEs embed the methylation profiles in a way that represents the original data with high fidelity while revealing nuances 4,5,23 . Thereafter, researchers attempted to develop similar frameworks for extracting features for downstream prediction tasks and identify meaningful relationships revealed by VAE latent representations 24 . However, VAE models are sensitive to the selection of hyperparameters 25 and have not been optimized for synthetic data generation, latent space exploration, and prediction tasks. Many autoencoder approaches represent the data using an encoder, and then utilize a non-neural network model (e.g. support vector machine) to finalize the predictions. Presently, to the best of our knowledge there is no end-to-end training approach that both extracts biologically meaningful features through latent encoding and performs predictions using the derived features. Further, existing frameworks do not output predictions for multi-target regression tasks, such as cell-type deconvolution and subject age prediction.Here, we leverage deep learning latent space regression and classification tasks through the development of a modular framework that is ...

show abstract

“…However, the unbiased organism-wide profiling of single-cell whole genomes is currently impractical. In the future, the signal from these somatic mutations could be combined with orthogonal lineage information from mitochondrial ATAC-seq reads or DNA methylation marks (Ludwig et al, 2019; Walther and Alison, 2016; Xu et al, 2019; Salas et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Recording development with single cell dynamic lineage tracing

2019

View full text Add to dashboard Cite

Every animal grows from a single fertilized egg into an intricate network of cell types and organ systems. This process is captured in a lineage tree: a diagram of every cell's ancestry back to the founding zygote. Biologists have long sought to trace this cell lineage tree in individual organisms and have developed a variety of technologies to map the progeny of specific cells. However, there are billions to trillions of cells in complex organisms, and conventional approaches can only map a limited number of clonal populations per experiment. A new generation of tools that use molecular recording methods integrated with single cell profiling technologies may provide a solution. Here, we summarize recent breakthroughs in these technologies, outline experimental and computational challenges, and discuss biological questions that can be addressed using single cell dynamic lineage tracing.

show abstract

Tracing human stem cell lineage during development using DNA methylation

Cited by 31 publications

References 95 publications

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

MethylNet: An Automated and Modular Deep Learning Approach for DNA Methylation Analysis

Recording development with single cell dynamic lineage tracing

Contact Info

Product

Resources

About