Network-Based Methods and Other Approaches for Predicting lncRNA Functions and Disease Associations

From diagnosis to therapy: The transformative role of lncRNAs in eye cancer management

The genomic era has brought about a transformative shift in our comprehension of cancer, unveiling the intricate molecular landscape underlying disease development. Eye cancers (ECs), encompassing diverse malignancies affecting ocular tissues, pose distinctive challenges in diagnosis and management. Long non-coding RNAs (lncRNAs), an emerging category of non-coding RNAs, are pivotal actors in the genomic intricacies of eye cancers. LncRNAs have garnered recognition for their multifaceted roles in gene expression regulation and influence on many cellular processes. Many studies support that the lncRNAs have a role in developing various cancers. Recent investigations have pinpointed specific lncRNAs associated with ECs, including retinoblastoma and uveal melanoma. These lncRNAs exert control over critical pathways governing tumor initiation, progression, and metastasis, endowing them with the ability to function as evaluation, predictive, and therapeutic indicators. The article aims to synthesize the existing information concerning the functions of lncRNAs in ECs, elucidating their regulatory mechanisms and clinical significance. By delving into the lncRNAs' expanding relevance in the modulation of oncogenic and tumor-suppressive networks, we gain a deeper understanding of the molecular complexities intrinsic to these diseases. In our exploration of the genomic intricacies of ECs, lncRNAs introduce a fresh perspective, providing an opportunity to function as clinical and therapeutic indicators, and they also have therapeutic benefits that show promise for advancing the treatment of ECs. This comprehensive review bridges the intricate relationship between lncRNAs and ECs within the context of the genomic era.

HEGANLDA: A Computational Model for Predicting Potential Lncrna-Disease Associations Based On Multiple Heterogeneous Networks

Long non-coding RNAs (lncRNAs) play vital regulatory roles in many human complex diseases, however, the number of validated lncRNA-disease associations is notable rare so far. How to predict potential lncRNA-disease associations precisely through computational methods remains challenging. In this study, we proposed a novel method, LDVCHN (LncRNA-Disease Vector Calculation Heterogeneous Networks), and also developed the corresponding model, HEGANLDA (Heterogeneous Embedding Generative Adversarial Networks LncRNA-Disease Association), for predicting potential lncRNA-disease associations. In HEGANLDA, the graph embedding algorithm (HeGAN) was introduced for mapping all nodes in the lncRNA-miRNA-disease heterogeneous network into the low-dimensional vectors which severed as the inputs of LDVCHN. HEGANLDA effectively adopted the XGBoost (eXtreme Gradient Boosting) classifier, which was trained by the low-dimensional vectors, to predict potential lncRNA-disease associations. The 10-fold cross-validation method was utilized to evaluate the performance of our model, our model finally achieved an area under the ROC curve of 0.983. According to the experiment results, HEGANLDA outperformed any one of five current state-of-the-art methods. To further evaluate the effectiveness of HEGANLDA in predicting potential lncRNA-disease associations, both case studies and robustness tests were performed and the results confirmed its effectiveness and robustness. The source code and data of HEGANLDA are available at https://github.com/HEGANLDA/HEGANLDA.

Dual Attention Mechanisms and Feature Fusion Networks Based Method for Predicting LncRNA-Disease Associations

LncRNAs play a part in numerous momentous processes of biology such as disease diagnoses, preventions and treatments. The associations between various diseases and lncRNAs are one of the crucial approaches to learn the role and status of lncRNAs in human diseases. With the researches on lncRNA and diseases, multiple methods based on neural network have been employed to predict these associations. However, the deep and complicated characteristic representations of lncRNA-disease associations were failed to be extracted, and the discriminative contributions of the interactions, correlations, and similarities among miRNAs diseases, and lncRNAs for the correlation predictions were ignored. In this paper, based on the multibiology premise of lncRNAs, miRNAs, and diseases, a dual attention network was proposed to predict the model of lncRNA-disease associations for miRNAs, the disease characteristic matrix, and lncRNAs. Through two attention modules, we enable the model to learn the nonlinear, more complex and useful features of lncRNA, miRNA, and disease characteristic matrix. For the feature embedding matrix composed of lncRNA-disease, the connection between lncRNA-disease feature embedding matrix and lncRNA, miRNA, and disease characteristic matrix was enhanced through deconvolution and feature fusion layer. Compared with several latest methods, the method proposed in this paper can produce better performance. Researches on the cases of osteosarcoma, lung cancer, and gastric cancer have confirmed the effective recognition of potential lncRNA-disease associations.

Epigenetic Differences in Long Non-coding RNA Expression in Finnish and Russian Karelia Teenagers With Contrasting Risk of Allergy and Asthma

Background

Previously, we investigated skin microbiota and blood cell gene expression in Finnish and Russian teenagers with contrasting incidence of allergic conditions. The microbiota and transcriptomic signatures were distinctly different, with high Acinetobacter abundance and suppression of genes regulating innate immune response in healthy subjects.

Objective

Here, we investigated long non-coding RNA (lncRNA) expression profiles of blood mononuclear cells (PBMC) from healthy and allergic subjects, to identify lncRNAs that act at the interphase of microbiome-mediated immune homeostasis in allergy/asthma.

Methods

Genome-wide co-expression network analyses of blood cell lncRNA/mRNA expression was integrated with skin microbiota profiles of Finnish (69) and Russian (75) subjects. Selected lncRNAs were validated by stimulation of cohort-derived PBMCs and a macrophage cell model with birch pollen allergen (Betv1) or lipopolysaccharide, respectively.

Results

Finnish and Russian PBMCs were differentiated by 3,818 lncRNA transcripts. In the Finnish subjects with high prevalence of allergy and asthma, a subset of 37 downregulated lncRNAs (including, FAM155A-IT1 and LOC400958) were identified. They were part of a co-expression network with 20 genes known to be related to asthma and allergic rhinitis (R > 0.95). Incidentally, all these 20 genes were also components of pathways corresponding to cellular response to bacterium. The Finnish and Russian samples were also differentiated by the abundance of 176 bacterial OTU (operational taxonomic units). The subset of 37 lncRNAs, associated with allergy, was most correlated with the abundance of Acinetobacter (R > +0.5), Jeotgalicoccus (R > +0.5), Corynebacterium (R < −0.5) and Micrococcus (R < −0.5).

Conclusion

In Finnish and Russian teenagers with contrasting allergy and asthma prevalence, epigenetic differences in lncRNA expression appear to be important components of the underlying microbiota-immune interactions. Unraveling the functions of the 37 differing lncRNAs may be the key to understanding microbiome-immune crosstalk, and to develop clinically relevant biomarkers.

LncRNA LEGLTBC Functions as a ceRNA to Antagonize the Effects of miR-34a on the Downregulation of SIRT1 in Glucolipotoxicity-Induced INS-1 Beta Cell Oxidative Stress and Apoptosis

Type 2 diabetes mellitus is a chronic metabolic disorder characterized by elevated blood glucose and/or high serum free fatty acids. Chronic hyperlipidemia causes the dysfunction of pancreatic beta cells, which is aggravated in the presence of hyperglycemia (glucolipotoxicity). Long noncoding RNAs (lncRNAs) have been suggested to play key roles in type 1 diabetes mellitus development. However, their roles in glucolipotoxicity-induced beta cell dysfunction are not fully understood. In the present study, we identified the differentially expressed lncRNAs in INS-1 cells exposed to high glucose and palmitate (HG/PA). Among the dysregulated lncRNAs, NONRATT003679.2 (low expression in glucolipotoxicity-treated beta cells (LEGLTBC)) was involved in glucolipotoxicity-evoked rat islet beta cell damage. LEGLTBC functioned as a molecular sponge of miR-34a in INS-1 cells. Additionally, SIRT1 was identified as a target of miR-34a and LEGLTBC promoted SIRT1 expression by sponging miR-34a. The upregulation of LEGLTBC attenuated HG/PA-induced INS-1 cell injury through the promotion of SIRT1-mediated suppression of ROS accumulation and apoptosis. This is the first study to comprehensively identify the lncRNA expression profiling of HG/PA-treated INS-1 beta cells and to demonstrate that LEGLTBC functions as a competing endogenous RNA and regulates miR-34a/SIRT1-mediated oxidative stress and apoptosis in INS-1 cells undergoing glucolipotoxicity.