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.

Background Congenital disorders of glycosylation (CDG) are a large family of rare genetic diseases for which therapies are virtually nonexistent. However, CDG therapeutic research has been expanding, thanks to the continuous efforts of the CDG medical/scientific and patient communities. Hence, CDG drug development is a popular research topic. The main aim of this study was to understand current and steer future CDG drug development and approval by collecting and analysing the views and experiences of the CDG community, encompassing professionals and families. An electronic (e-)survey was developed and distributed to achieve this goal. Results A total of 128 respondents (46 CDG professionals and 82 family members), mainly from Europe and the USA, participated in this study. Most professionals (95.0%) were relatively familiar with drug development and approval processes, while CDG families revealed low familiarity levels, with 8.5% admitting to never having heard about drug development. However, both stakeholder groups agreed that patients and families make significant contributions to drug development and approval. Regarding their perceptions of and experiences with specific drug development and approval tools, namely biobanks, disease models, patient registries, natural history studies (NHS) and clinical trials (CT), the CDG community stakeholders described low use and participation, as well as variable familiarity. Additionally, CDG professionals and families shared conflicting views about CT patient engagement and related information sharing. Families reported lower levels of involvement in CT design (25.0% declared ever being involved) and information (60.0% stated having been informed) compared to professionals (60.0% and 85.7%, respectively). These contrasting perceptions were further extended to their insights and experiences with patient-centric research. Finally, the CDG community (67.4% of professionals and 54.0% of families) reported a positive vision of artificial intelligence (AI) as a drug development tool. Nevertheless, despite the high AI awareness among CDG families (76.8%), professionals described limited AI use in their research (23.9%). Conclusions This community-centric study sheds new light on CDG drug development and approval. It identifies educational, communication and research gaps and opportunities for CDG professionals and families that could improve and accelerate CDG therapy development.

Background and aim Congenital disorders of glycosylation (CDG) are a large heterogeneous group of about 170 rare inherited metabolic disorders due to defective protein and lipid glycosylation. This study aimed to assemble and summarise available data on the epidemiology of CDG. Methods A set of keywords related to epidemiology and CDG was defined. The keywords were combined through a custom Python script, search through the MEDLINE database, using PubMed as the search engine. The script retrieved the correspondent MEDLINE data from each article, and the relevant information was exported. Next, inclusion and exclusion criteria were set and applied during the selection phase. Finally, epidemiology-related information was extracted and compiled. Results One hundred sixty-five papers on CDG epidemiology were included in this literature review. Most of them reported on the frequency of symptoms in CDG patients followed in cohort studies, on pathogenic variant allelic frequency, and on the prevalence of the disorder in populations. According to this review, the most reported CDG was phosphomannomutase-2 deficiency (PMM2-CDG) followed in descending order by FKTN-CDG, EXT1/EXT2-CDG, ALG6-CDG, and PIGA-CDG. Conclusions We provide an overview on epidemiological data regarding 93 CDG by compiling information from the literature. Generating epidemiological data on CDG is important to appropriately target resources for CDG research and drug development and to support public health decision-making.