Branchpoints (BPs) are essential sequence elements of ribonucleic acids (RNAs) in splicing, which is the process of creating a messenger RNA (mRNA) that is translated into proteins. This study proposes to develop deep neural networks for BP prediction. Extensive previous studies have shown that the existence of BP sites depends on sequence patterns called motifs; hence, the prediction model must accurately explain its decisions in terms of motifs. Existing approaches utilized either handcrafted features for interpretable, though less accurate, predictions or deep neural networks that were accurate but difficult to explain. To address the aforementioned difficulties, the proposed method incorporates 1) generative adversarial networks (GANs) to learn the latent structure of RNA sequences, and 2) an attention mechanism to learn sequence-positional long-term dependency for accurate prediction and interpretation. Our method achieves highly satisfying results in various performance metrics with adequate interpretability. We demonstrated that, without any prior biological knowledge, BP prediction by the proposed method is closely related to three motifs, the consensus sequence surrounding BPs, polypyrimidine tract, and 3' splice site, that are well-established in molecular biology. INDEX TERMS Branchpoint prediction, deep neural networks, generative adversarial networks, interpretability.
BackgroundVitiligo is a common acquired skin depigmentation disorder and is associated with various other autoimmune diseases which include thyroid disease and rheumatoid arthritis. Similarly, adenotonsillar disease (ATD) may induce inflammatory or autoimmune diseases in other organs which include the skin. However, the influence of ATD on the development of vitiligo has not been studied.ObjectivesTo determine the association between ATD and adenotonsillectomy, and the development of vitiligo.Design and methodsUsing data from the National Health Insurance Service database, patients diagnosed with ATD between 2008 and 2010 were included in the study. We performed two rounds of 1:1 propensity score matching in the ATD and adenotonsillectomy groups. The ATD and non-ATD groups both included 206,514 individuals. Among the ATD group, the adenotonsillectomy and non-adenotonsillectomy groups both included 23,354 individuals. Each individual was monitored until 2019. The primary end point was the risk of vitiligo. Using the Cox Proportional Hazards model, the incidence of vitiligo and the hazard ratio (HR) were calculated.ResultsThe incidence of vitiligo was 1.16-fold higher in the ATD group than in the non-ATD group [adjusted HR (aHR), 1.16; 95% confidence interval (CI), 1.09–1.24] and 0.82-fold lower in the adenotonsillectomy group than in the non-adenotonsillectomy group (aHR, 0.82; 95% CI, 0.68–0.99). Additionally, the other risk factors for developing vitiligo included thyroid disease (aHR, 1.48; 95% CI, 1.11–1.98), age younger than 30 years (aHR, 1.18; 95% CI, 1.09–1.27), and age over 60 years (aHR, 1.22; 95% CI, 1.06–1.41), whereas factors including rural residency (aHR, 0.91; 95% CI, 0.85–0.98) and low economic status (aHR 0.87; 95% CI, 0.82–0.93) were associated with decreased incidence of vitiligo.ConclusionIn this study, ATD increases the risk of vitiligo and adenotonsillectomy attenuates its development. Clinicians should consider ATD as a pathogenic factor for vitiligo and the potential effect of adenotonsillectomy in its management.
We examined the associations of clinical characteristics and cause-of-death patterns with mortality in children and young adults (<30 years) with diabetes. We analyzed a nationwide cohort sample from the KNHIS database using propensity score matching from a sample of 1 million people from 2002 to 2013. There were 10,006 individuals in the diabetes mellitus (DM) group and 10,006 in the control (no DM) group. The numbers of deaths were 77 in the DM group and 20 in the control group. The deaths of patients in the DM Group were 3.74 (95% confidence interval (CI) = 2.25–6.21) times higher than in the control group. Type 1 DM, type 2 DM and unspecified DM were 4.52 (95% CI = 1.89–10.82) times, 3.25 (95% CI = 1.95–5.43) times and 10.20 (95% CI = 5.24–20.18) times higher, respectively. Mental disorders were 2.08 times higher in the risk of death (95% CI = 1.27–3.40). Mortality rates have increased in children and young adults with diabetes alone. Therefore, in the future, it is necessary to identify the cause of the increased mortality rate among young diabetic people and select vulnerable groups among them so that early prevention can be achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.