Artificial Intelligence in Epigenetic Studies: Shedding Light on Rare Diseases

Abstract

More than 7,000 rare diseases (RDs) exist worldwide, affecting approximately 350 million people, out of which only 5% have treatment. The development of novel genome sequencing techniques has accelerated the discovery and diagnosis in RDs. However, most patients remain undiagnosed. Epigenetics has emerged as a promise for diagnosis and therapies in common disorders (e.g., cancer) with several epimarkers and epidrugs already approved and used in clinical practice. Hence, it may also become an opportunity to uncover new disease mechanisms and therapeutic targets in RDs. In this “big data” age, the amount of information generated, collected, and managed in (bio)medicine is increasing, leading to the need for its rapid and efficient collection, analysis, and characterization. Artificial intelligence (AI), particularly deep learning, is already being successfully applied to analyze genomic information in basic research, diagnosis, and drug discovery and is gaining momentum in the epigenetic field. The application of deep learning to epigenomic studies in RDs could significantly boost discovery and therapy development. This review aims to collect and summarize the application of AI tools in the epigenomic field of RDs. The lower number of studies found, specific for RDs, indicate that this is a field open to expansion, following the results obtained for other more common disorders.

Analyzing Modern Biomolecules: The Revolution of Nucleic-Acid Sequencing – Review

“…Computational, statistical and bioinformatics tools are also needed to fully analyze epigenetics. In this scenario, as reported for transcriptomics, epigenetics has also been linked to rare diseases using ML, and particularly DL, approaches [176].…”

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

“…Nevertheless, these works focused on biological mechanisms and model structures rather than clinical outcomes of human diseases. In the same manner, previous reviews targeting cancer and rare diseases highlighted the promising ability of DL to elucidate the involvement of epigenomics in pathophysiology of human diseases, fostering novel diagnostic tools as well as therapeutic avenues [ 13 , 14 , 17 , 18 , 19 ]. Rauschert et al [ 15 ] and Holder et al [ 16 ] emphasized potential clinical applications of epigenetics and ML; however, the former only reviewed DNA methylation data, and the latter only provided a list of diseases or medical conditions without a comprehensive discussion.…”

“…Although there have been a number of review papers regarding DL and epigenomics, only a limited number of review papers mentioned applicability of DL and epigenomics to clinical practices. In the last five years, ten comprehensive review articles have been published to shed the light on applications of DL to epigenomics [ 3 , 4 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ] as presented in Table 1 . Zhang et al [ 3 ] and Min et al [ 4 ] provided a useful guideline which allows researchers from various backgrounds to understand and utilize DL to solve omics-related problems, whereas Talukder et al [ 12 ] attempted to unbox the black-box nature of DL, increasing the interpretability of DL in epigenomics.…”

Predicting High Blood Pressure Using DNA Methylome-Based Machine Learning Models

“…Many researchers have applied ML to DNA data [ 19 , 20 , 21 , 22 ]. In particular, several applications of ML in epigenomics have assisted medical professionals and researchers to perform human disease-related tasks such as disease detection, subtype classification, prognosis, and treatment response prediction [ 23 , 24 , 25 , 26 , 27 , 28 ]. Given the success of existing ML models for detecting breast cancer [ 29 , 30 ], lung cancer [ 31 ], coarctation [ 32 ], concussion [ 33 ], and schizophrenia [ 34 ], we proposed DNA methylome-based predictive models using three common ML algorithms including deep learning (DL), random forest (RF), and support vector machine (SVM) for high BP prediction in this study.…”