Predicting Methylation from Sequence and Gene Expression Using Deep Learning with Attention

Levy-Jurgenson, Alona; Tekpli, Xavier; Kristensen, Vessela N.; Yakhini, Zohar

doi:10.1007/978-3-030-18174-1_13

Cited by 4 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Levy-Jurgenson et al . [ 79 ] use DNA sequence and gene expression data to predict DNA methylation. Their DNN architecture is modified with an attention mechanism to gain insights into the model.…”

Section: Resultsmentioning

confidence: 99%

Explainable artificial intelligence for omics data: a systematic mapping study

Toussaint,

Leiser,

Thiebes

et al. 2023

Briefings in Bioinformatics

View full text Add to dashboard Cite

Researchers increasingly turn to explainable artificial intelligence (XAI) to analyze omics data and gain insights into the underlying biological processes. Yet, given the interdisciplinary nature of the field, many findings have only been shared in their respective research community. An overview of XAI for omics data is needed to highlight promising approaches and help detect common issues. Toward this end, we conducted a systematic mapping study. To identify relevant literature, we queried Scopus, PubMed, Web of Science, BioRxiv, MedRxiv and arXiv. Based on keywording, we developed a coding scheme with 10 facets regarding the studies’ AI methods, explainability methods and omics data. Our mapping study resulted in 405 included papers published between 2010 and 2023. The inspected papers analyze DNA-based (mostly genomic), transcriptomic, proteomic or metabolomic data by means of neural networks, tree-based methods, statistical methods and further AI methods. The preferred post-hoc explainability methods are feature relevance (n = 166) and visual explanation (n = 52), while papers using interpretable approaches often resort to the use of transparent models (n = 83) or architecture modifications (n = 72). With many research gaps still apparent for XAI for omics data, we deduced eight research directions and discuss their potential for the field. We also provide exemplary research questions for each direction. Many problems with the adoption of XAI for omics data in clinical practice are yet to be resolved. This systematic mapping study outlines extant research on the topic and provides research directions for researchers and practitioners.

show abstract

Section: Resultsmentioning

confidence: 99%

Explainable artificial intelligence for omics data: a systematic mapping study

Toussaint,

Leiser,

Thiebes

et al. 2023

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…The third category consists of methods that leverage both sequence features and functional chromatin states to varying extent, including methylation state of neighboring CpGs. There are methods relying on hand-crafted DNA sequence features similar to those approaches developed for predicting methylation level of CpG islands (Zhang et al, 2015;Jiang et al, 2019), but with the majority employing DNNs to derive features that are unbiased (Wang et al, 2016;Sharma et al, 2017;Fu et al, 2019;Levy-Jurgenson et al, 2019;De Waele et al, 2022). Notably, methods using DNNs generally perform better than those not when there is no additional input beyond the methylation profile of the target sample (Sharma et al, 2017;De Waele et al, 2022).…”

Section: Background and Related Workmentioning

confidence: 99%

Completing Single-Cell DNA Methylome Profiles via Transfer Learning Together With KL-Divergence

2022

View full text Add to dashboard Cite

The high level of sparsity in methylome profiles obtained using whole-genome bisulfite sequencing in the case of low biological material amount limits its value in the study of systems in which large samples are difficult to assemble, such as mammalian preimplantation embryonic development. The recently developed computational methods for addressing the sparsity by imputing missing have their limits when the required minimum data coverage or profiles of the same tissue in other modalities are not available. In this study, we explored the use of transfer learning together with Kullback-Leibler (KL) divergence to train predictive models for completing methylome profiles with very low coverage (below 2%). Transfer learning was used to leverage less sparse profiles that are typically available for different tissues for the same species, while KL divergence was employed to maximize the usage of information carried in the input data. A deep neural network was adopted to extract both DNA sequence and local methylation patterns for imputation. Our study of training models for completing methylome profiles of bovine oocytes and early embryos demonstrates the effectiveness of transfer learning and KL divergence, with individual increase of 29.98 and 29.43%, respectively, in prediction performance and 38.70% increase when the two were used together. The drastically increased data coverage (43.80–73.6%) after imputation powers downstream analyses involving methylomes that cannot be effectively done using the very low coverage profiles (0.06–1.47%) before imputation.

show abstract

“…When the methylation states of sequentially neighboring regions are unknown, the accuracy was almost 85%. Levy-Jurgenson et al (83) developed a general model to predict DNA methylation for a given sample in any CpG position based solely on the sample's gene expression profile and the sequence surrounding the CpG. Depending on gene-CpG proximity, the model attained a Spearman correlation of up to 0.84 for thousands of CpG sites on two separate test sets of CpG positions and subjects (cancer and healthy samples).…”

Section: Predicting Methylation In Single-nucleotide Resolutionmentioning

confidence: 99%

Identifying Regulatory Elements via Deep Learning

Barshai

Tripto

Orenstein

2020

Annu. Rev. Biomed. Data Sci.

View full text Add to dashboard Cite

Deep neural networks have been revolutionizing the field of machine learning for the past several years. They have been applied with great success in many domains of the biomedical data sciences and are outperforming extant methods by a large margin. The ability of deep neural networks to pick up local image features and model the interactions between them makes them highly applicable to regulatory genomics. Instead of an image, the networks analyze DNA and RNA sequences and additional epigenomic data. In this review, we survey the successes of deep learning in the field of regulatory genomics. We first describe the fundamental building blocks of deep neural networks, popular architectures used in regulatory genomics, and their training process on molecular sequence data. We then review several key methods in different gene regulation domains. We start with the pioneering method DeepBind and its successors, which were developed to predict protein–DNA binding. We then review methods developed to predict and model epigenetic information, such as histone marks and nucleosome occupancy. Following epigenomics, we review methods to predict protein–RNA binding with its unique challenge of incorporating RNA structure information. Finally, we provide our overall view of the strengths and weaknesses of deep neural networks and prospects for future developments.

show abstract

Predicting Methylation from Sequence and Gene Expression Using Deep Learning with Attention

Cited by 4 publications

References 24 publications

Explainable artificial intelligence for omics data: a systematic mapping study

Explainable artificial intelligence for omics data: a systematic mapping study

Completing Single-Cell DNA Methylome Profiles via Transfer Learning Together With KL-Divergence

Identifying Regulatory Elements via Deep Learning

Contact Info

Product

Resources

About