Application of deep learning in cancer epigenetics through DNA methylation analysis

Abstract

DNA methylation is a fundamental epigenetic modification involved in various biological processes and diseases. Analysis of DNA methylation data at a genome-wide and high-throughput level can provide insights into diseases influenced by epigenetics, such as cancer. Recent technological advances have led to the development of high-throughput approaches, such as genome-scale profiling, that allow for computational analysis of epigenetics. Deep learning (DL) methods are essential in facilitating computational studies in epigenetics for DNA methylation analysis. In this systematic review, we assessed the various applications of DL applied to DNA methylation data or multi-omics data to discover cancer biomarkers, perform classification, imputation and survival analysis. The review first introduces state-of-the-art DL architectures and highlights their usefulness in addressing challenges related to cancer epigenetics. Finally, the review discusses potential limitations and future research directions in this field.

Exploring Potential Epigenetic Biomarkers for Colorectal Cancer Metastasis

“…Integrated multiomics analyses, which combine data from multiple omics levels such as genomics, epigenomics, transcriptomics, proteomics, and metabolomics, enable a more thorough understanding of the complex biological mechanisms driving CRC metastasis. The application of deep learning and artificial intelligence analysis approaches further enhances the ability to detect and utilise novel markers of cancer metastasis [149]. This comprehensive approach helps identify interconnected molecular pathways, biomarkers, and potential therapeutic targets that would otherwise be missed when studying individual omics data.…”

DNA Methylome and Transcriptome Maps of Primary Colorectal Cancer and Matched Liver Metastasis

“…Our data are critical to understanding these changes and regulatory mechanisms involved in the development of CRC liver metastases; they can be used as an independent cohort for future studies and validation. Further, deep learning methods could be applied in future work on these datasets to reveal novel patterns of tumours [47]. The integration of multi-omics data sets in paired samples provides a great opportunity to understand the complex dynamics of tumour progression, treatment response and the identification of novel biomarkers for early detection and diagnosis of CRC metastasis in the future.…”

Methods in DNA methylation array dataset analysis: A review

“…Despite the preferable usage of SVM and Naïve Bayes, random forest (RF) outperformed most algorithms. It handled complex feature interactions and provided high accuracy, stability, and predictive power [144] , [154] . Considering this robust classification done by RF models, Tu et al, 2022 effectively used the LASSO as a feature selection mechanism and RF model construction for the selection of the significant methylation features, allowing the accurate prediction of the samples for the occurrence of cervical cancer and supporting the stratification of the patients’ samples into low-risk and high-risk groups [155] .…”