Prediction of Long Non-Coding RNAs Based on Deep Learning.

With the rapid development of high-throughput sequencing technology, a large number of transcript sequences have been discovered, and how to identify long non-coding RNAs (lncRNAs) from transcripts is a challenging task. The identification and inclusion of lncRNAs not only can more clearly help us to understand life activities themselves, but can also help humans further explore and study the disease at the molecular level. At present, the detection of lncRNAs mainly includes two forms of calculation and experiment. Due to the limitations of bio sequencing technology and ineluctable errors in sequencing processes, the detection effect of these methods is  not very satisfactory. In this paper, we constructed a deep-learning model to effectively distinguish lncRNAs from mRNAs. We used k-mer embedding vectors obtained through training the GloVe algorithm as input features and set up the deep learning framework to include a bidirectional long short-term memory model (BLSTM) layer and a convolutional neural network (CNN) layer with three additional hidden layers. By testing our model, we have found that it obtained the best values of 97.9%, 96.4% and 99.0% in F1score, accuracy and auROC, respectively, which showed better classification performance than the traditional PLEK, CNCI and CPC methods for identifying lncRNAs. We hope that our model will provide effective help in distinguishing mature mRNAs from lncRNAs, and become a potential tool to help humans understand and detect the diseases associated with lncRNAs.

Decreased MiR-155 Level in the Peripheral Blood of Non-Alcoholic Fatty Liver Disease Patients may Serve as a Biomarker and may Influence LXR Activity.

BACKGROUND: Obesity is now a common risk factor for non-alcoholic fatty liver disease (NAFLD). Thus, it is important to explore its underlying mechanisms. METHODS: Total RNA was extracted from peripheral whole blood samples from 50 NAFLD patients and 50 healthy controls. In addition, human liver specimens were obtained through liver biopsies from NAFLD patients and healthy controls. The level of miRNA was studied using real-time PCR. The expression of lipogenic genes was analyzed using western blot, and a dual luciferase reporter assay was conducted to identify the possible target gene. Adenovirus vectors were injected into the tail vein of the high fat diet (HFD)-fed mice to study the role of miR-155 on lipid accumulation in vivo. RESULTS: The level of miR-155 was markedly reduced in the livers and peripheral blood of NAFLD patients compared with healthy controls. Upregulation of miR-155 decreased intracellular lipid content and the SREBP1 and FAS protein levels, while inhibition of miR-155 enhanced the intracellular lipid content. The dual luciferase reporter assay showed that Liver X receptor (LXR)α was the target gene of miR-155, and silencing miR-155 reduced the expression of SREBP1 and FAS. An in vivo study showed that upregulation of miR-155 decreased the hepatic lipid accumulation mainly by suppressing the LXRα-dependent lipogenic signaling pathway. CONCLUSIONS: In summary, decreased expression of miR-155 in the peripheral blood may be utilized as a potential novel biomarker for NAFLD screening mainly by targeting LXRα.

Pseudogene PTENP1 Functions as a Competing Endogenous RNA (ceRNA) to Regulate PTEN Expression by Sponging miR-499-5p.

Increasing evidence has shown that pseudogenes can widely regulate gene expression. However, little is known about the specific role of PTENP1 and miR-499-5p in insulin resistance. The relative transcription level of PTENP1 was examined in db/db mice and high fat diet (HFD)-fed mice by real-time PCR. To explore the effect of PTENP1 on insulin resistance, adenovirus overexpressing or inhibiting vectors were injected through the tail vein. Bioinformatics predictions and a luciferase reporter assay were used to explore the interaction between PTENP1 and miR-499-5p. The relative transcription level of PTENP1 was largely enhanced in db/db mice and HFD-fed mice. Furthermore, the overexpression of PTENP1 resulted in impaired Akt/GSK activation as well as glycogen synthesis, while PTENP1 inhibition led to the improved activation of Akt/GSK and enhanced glycogen contents. More importantly, PTENP1 could directly bind miR-499-5p, thereby becoming a sink for miR-499-5p. PTENP1 overexpression results in the impairment of the insulin-signaling pathway and may function as a competing endogenous RNA for miR-499-5p, thereby contributing to insulin resistance.