Convolution Neural Networks Using Deep Matrix Factorization for Predicting Circrna-Disease Association

CircPCBL: Identification of Plant CircRNAs with a CNN-BiGRU-GLT Model

Circular RNAs (circRNAs), which are produced post-splicing of pre-mRNAs, are strongly linked to the emergence of several tumor types. The initial stage in conducting follow-up studies involves identifying circRNAs. Currently, animals are the primary target of most established circRNA recognition technologies. However, the sequence features of plant circRNAs differ from those of animal circRNAs, making it impossible to detect plant circRNAs. For example, there are non-GT/AG splicing signals at circRNA junction sites and few reverse complementary sequences and repetitive elements in the flanking intron sequences of plant circRNAs. In addition, there have been few studies on circRNAs in plants, and thus it is urgent to create a plant-specific method for identifying circRNAs. In this study, we propose CircPCBL, a deep-learning approach that only uses raw sequences to distinguish between circRNAs found in plants and other lncRNAs. CircPCBL comprises two separate detectors: a CNN-BiGRU detector and a GLT detector. The CNN-BiGRU detector takes in the one-hot encoding of the RNA sequence as the input, while the GLT detector uses k-mer (k = 1 - 4) features. The output matrices of the two submodels are then concatenated and ultimately pass through a fully connected layer to produce the final output. To verify the generalization performance of the model, we evaluated CircPCBL using several datasets, and the results revealed that it had an F1 of 85.40% on the validation dataset composed of six different plants species and 85.88%, 75.87%, and 86.83% on the three cross-species independent test sets composed of Cucumis sativus, Populus trichocarpa, and Gossypium raimondii, respectively. With an accuracy of 90.9% and 90%, respectively, CircPCBL successfully predicted ten of the eleven circRNAs of experimentally reported Poncirus trifoliata and nine of the ten lncRNAs of rice on the real set. CircPCBL could potentially contribute to the identification of circRNAs in plants. In addition, it is remarkable that CircPCBL also achieved an average accuracy of 94.08% on the human datasets, which is also an excellent result, implying its potential application in animal datasets. Ultimately, CircPCBL is available as a web server, from which the data and source code can also be downloaded free of charge.

miR-22 alleviates sepsis-induced acute kidney injury via targeting the HMGB1/TLR4/NF-κB signaling pathway

BACKGROUND

Acute kidney injury (AKI) is a severe complication of sepsis, and is strongly correlated with MicroRNAs (miRNAs). However, the mechanism of miR-22 on sepsis-induced AKI is not clearly understood. The study aimed to explore the role and mechanism of miR-22 on AKI.

METHODS

The AKI models were established by cecal ligation and puncture (CLP) surgery in SD rats and lipopolysaccharide (LPS) induction in HBZY-1 cells. In AKI rats, the content of serum creatinine (SCr) and blood urea nitrogen (BUN) were detected. Kidney tissues were pathologically examined by H&E and PAS staining. The LPS-induced HBZY-1 cells were transfected with mimics miR-22, si-HMGB1, or oe-HMGB1. miR-22 and HMGB1 expression was detected in vivo and in vitro. In transfected cells, HMGB1/TLR4/NF-κB pathway-related protein expressions were measured by Western blot. The relationship between miR-22 and HMGB1 was assessed by a dual-luciferase gene report. Inflammatory cytokine levels in serum and cells were assessed by ELISA.

RESULTS

In AKI rats, kidney injury was observed, accompanied by the down-regulated miR-122 expression and up-regulated HMBG1 expression. The dual-luciferase report found miR-22-3p could targetly regulate HMBG1. Furthermore, both in vitro and in vivo experiments revealed that the releases of inflammatory cytokine were increased after AKI modeling, but the situation was reversed by mimics miR-22 or si-HMGB1 in vitro. In HBZY-1 cells, mimics miR-22 could suppress LPS-induced overexpression of HMGB1/TLR4/NF-κB signaling pathway-related proteins. However, the oe-HMGB1 addition reversed the effect of mimics miR-22.

CONCLUSION

miR-22 can inhibit the inflammatory response, target the HMGB1, and inhibit the HMGB1/TLR4/NF-kB pathway, to attenuate the sepsis-induced AKI, which indicates that miR-22 may serve as a potential treatment target in sepsis-induced AKI.

MIMRDA: A Method Incorporating the miRNA and mRNA Expression Profiles for Predicting miRNA-Disease Associations to Identify Key miRNAs (microRNAs)

Identifying cancer-related miRNAs (or microRNAs) that precisely target mRNAs is important for diagnosis and treatment of cancer. Creating novel methods to identify candidate miRNAs becomes an imminent Frontier of researches in the field. One major obstacle lies in the integration of the state-of-the-art databases. Here, we introduce a novel method, MIMRDA, which incorporates the miRNA and mRNA expression profiles for predicting miRNA-disease associations to identify key miRNAs. As a proof-of-principle study, we use the MIMRDA method to analyze TCGA datasets of 20 types (BLCA, BRCA, CESE, CHOL, COAD, ESCA, HNSC, KICH, KIRC, KIRP, LIHC, LUAD, LUSC, PAAD, PRAD, READ, SKCM, STAD, THCA and UCEC) of cancer, which identified hundreds of top-ranked miRNAs. Some (as Category 1) of them are endorsed by public databases including TCGA, miRTarBase, miR2Disease, HMDD, MISIM, ncDR and mTD; others (as Category 2) are supported by literature evidences. miR-21 (representing Category 1) and miR-1258 (representing Category 2) display the excellent characteristics of biomarkers in multi-dimensional assessments focusing on the function similarity analysis, overall survival analysis, and anti-cancer drugs’ sensitivity or resistance analysis. We compare the performance of the MIMRDA method over the Limma and SPIA packages, and estimate the accuracy of the MIMRDA method in classifying top-ranked miRNAs via the Random Forest simulation test. Our results indicate the superiority and effectiveness of the MIMRDA method, and recommend some top-ranked key miRNAs be potential biomarkers that warrant experimental validations.