Enhancer Prediction with Histone Modification Marks Using a Hybrid Neural Network Model
Publication date: Available online 21 March 2019Source: MethodsAuthor(s): A. Lim, S. Lim, S. KimAbstractEnhancer is a DNA sequence of a genome that controls transcription of downstream target genes. Enhancers are known to be associated with certain epigenetic signatures. Machine learning tools, such as CSI-ANN, ChromHMM, and RFECS, were developed for predicting enhancers using various epigenetic features. However, predictions by different tools vary widely and quite a significant portion of enhancer predictions does not agree. Thus, computational methods for enhancer prediction should be further developed. In this paper, a hybrid neural network called Enhancer-CRNN, a convolutional neural network (CNN) followed by a recurrent neural network (RNN), was developed and they were used to predict enhancer regions with histone modification marks as input. The CNN in our model is to reflect local characteristics and the RNN is to learn sequential dependencies among the histone marks. Hybridization of both neural networks outperformed existing prediction tools in experiments with GM12878, H1hesc, HeLaS3, and HepG2 cell lines. On average, 13 to 17 percent of the enhancers predicted by our method were cell type-specific. With the trained model, optimized virtual input histone marks was generated to provide a deeper insight into how histone modification marks can represent enhancer regions in which histone marks indicate active or repressed enhancers. In summary, our model produced accur...
Publication date: Available online 24 April 2019Source: Journal of Critical CareAuthor(s): Philippe Montravers, Ignacio Martin-Loeches
Publication date: Available online 25 April 2019Source: European Annals of Otorhinolaryngology, Head and Neck DiseasesAuthor(s): G. Dumas, H. Tan, L. Dumas, P. Perrin, A. Lion, S. SchmerberAbstractObjectiveTo establish optimum stimulus frequency and location of bone conducted vibration provoking a skull vibration induced nystagmus (SVIN) in superior semi-circular canal dehiscences.MethodsSVIN 3D components in 40 patients with semi-circular canal dehiscence (27 unilateral and 13 bilateral) were compared with a group of 18 patients with severe unilateral vestibular loss and a control group of 11 volunteers.ResultsIn unilater...
Conclusion: The high IGF-II/IGFBP-3 molar ratio was not the cause of the sustained high growth velocity, due to the low affinity of IGF-II for IGF type 1 receptor. The key finding was theHESX1 mutation, as similar cases have been described before, suggesting a common mechanism for growth without GH. However, the variable penetrance of this variant in heterozygous relatives suggests that modifier genes or mechanisms involving combinations with mutations of other genes involved in intracellular signaling pathways might be responsible.Horm Res Paediatr
Publication date: Available online 24 April 2019Source: The Lancet Diabetes &EndocrinologyAuthor(s): Stuart W Flint
Publication date: Available online 24 April 2019Source: The Lancet Diabetes &EndocrinologyAuthor(s): Peter H Bennett
Publication date: Available online 13 April 2019Source: Molecular and Cellular EndocrinologyAuthor(s): Matti Poutanen, Trevor M. Penning
ConclusionSGLT2 inhibitors have relatively safe profiles and can efficiently decrease HbA1c as well as fasting and postprandial glucose levels. Furthermore, SGLT2 inhibitors administrations are not associated with significant hypoglycemic episodes or weight gain. Thus, combination of SGLT2 inhibitors and other less harmful anti-diabetic medicines could be considered if there is no any contraindication.
ConclusionDiabetes was correlated significantly with dyslipidemia and atherogenic risk in parallel with an increase in IFN-γ production and hematological inflammatory biomarkers; leukocytes, neutrophil/lymphocyte and platelet/lymphocyte ratios, MPV and PDW values. The amelioration in inflammatory biomarkers was associated with improvement in glycemic control.