Adap-BDCM: Adaptive Bilinear Dynamic Cascade Model for Classification Tasks on CNV Datasets.

Copy number variation (CNV) is an essential genetic driving factor of cancer formation and progression, making intelligent classification based on CNV feasible. However, there are a few challenges in the current machine learning and deep learning methods, such as the design of base classifier combination schemes in ensemble methods and the selection of layers of neural networks, which often result in low accuracy. Therefore, an adaptive bilinear dynamic cascade model (Adap-BDCM) is developed to further enhance the accuracy and applicability of these methods for intelligent classification on CNV datasets. In this model, a feature selection module is introduced to mitigate the interference of redundant information, and a bilinear model based on the gated attention mechanism is proposed to extract more beneficial deep fusion features. Furthermore, an adaptive base classifier selection scheme is designed to overcome the difficulty of manually designing base classifier combinations and enhance the applicability of the model. Lastly, a novel feature fusion scheme with an attribute recall submodule is constructed, effectively avoiding getting stuck in local solutions and missing some valuable information. Numerous experiments have demonstrated that our Adap-BDCM model exhibits optimal performance in cancer classification, stage prediction, and recurrence on CNV datasets. This study can assist physicians in making diagnoses faster and better.

Differential methylation patterns from clusters associated with glucose metabolism: evidence from a Shanghai twin study.

Aim: To assess the associations between genome-wide DNA methylation (DNAm) and glucose metabolism among a Chinese population, in particular the multisite correlation. Materials & methods: Epigenome-wide associations with fasting plasma glucose (FPG) and hemoglobin A1c (HbA1c) were analyzed among 100 Shanghai monozygotic (MZ) twin pairs using the Infinium HumanMethylationEPIC v2.0 BeadChip. We conducted a Pearson's correlation test, hierarchical cluster and pairwise analysis to examine the differential methylation patterns from clusters. Results: Cg01358804 (TXNIP) was identified as the most significant site associated with FPG and HbA1c. Two clusters with hypermethylated and hypomethylated patterns were observed for both FPG and HbA1c. Conclusion: Differential methylation patterns from clusters may provide new clues for epigenetic changes and biological mechanisms in glucose metabolism.

Long noncoding RNA Gm20319, acting as competing endogenous RNA, regulated GNE expression by sponging miR-7240-5p to involve in deoxynivalenol-induced liver damage in vitro.

The regulatory effects of competing endogenous RNA (ceRNA) network have been highlighted on the occurrence and development of diseases. However, the effect of ceRNA network in liver with subchronic deoxynivalenol (DON) exposure has remained unclear so far. Here, lncRNA Gm20319-miR-7240-5p-GNE (glucosamine UDP-N-acetyl-2-epimerase/N-acetylmannosamine kinase) network was identified in DON exposed-liver tissues after DON exposure for 90 days. Subchronic DON exposure induced the mild inflammation in liver tissues. In DON-treated liver tissues and Hepa 1-6 cell line, the expression of Gm20319 and GNE were both downregulated while miR-7240-5p expression was upregulated. The gain- and loss-of-function expression in vitro revealed there was a mutual repression between Gm20319 and miR-7240-5p, and they regulated GNE expression in an opposite direction. Dual luciferase reporter assays showed miR-7240-5p inhibited Gm20319 and GNE expression by directly binding. Co-transfection experiment in vitro revealed Gm20319 and miR-7240-5p could indirectly regulate sialic acid level by directly modulating GNE expression, thereby also influencing the expression of SOD1 and IL-1ß. This study revealed Gm20319-miR-7240-5p-GNE network reduced sialic acid level to influence the expression of SOD1 and IL-1ß in liver, which might involve in liver damage induced by DON. Gm20319 might be a potential research molecular target for DON-induced liver damage.