Common Features in lncRNA Annotation and Classification: A Survey

A Comprehensive Review on RNA Subcellular Localization Prediction

The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critical role in determining their biological functions. For instance, lncRNAs are predominantly associated with chromatin and act as regulators of gene transcription and chromatin structure, while mRNAs are distributed across the nucleus and cytoplasm, facilitating the transport of genetic information for protein synthesis. Understanding RNA localization sheds light on processes like gene expression regulation with spatial and temporal precision. However, traditional wet lab methods for determining RNA localization, such as in situ hybridization, are often time-consuming, resource-demanding, and costly. To overcome these challenges, computational methods leveraging artificial intelligence (AI) and machine learning (ML) have emerged as powerful alternatives, enabling large-scale prediction of RNA subcellular localization. This paper provides a comprehensive review of the latest advancements in AI-based approaches for RNA subcellular localization prediction, covering various RNA types and focusing on sequence-based, image-based, and hybrid methodologies that combine both data types. We highlight the potential of these methods to accelerate RNA research, uncover molecular pathways, and guide targeted disease treatments. Furthermore, we critically discuss the challenges in AI/ML approaches for RNA subcellular localization, such as data scarcity and lack of benchmarks, and opportunities to address them. This review aims to serve as a valuable resource for researchers seeking to develop innovative solutions in the field of RNA subcellular localization and beyond.

Mitigating off-target effects of small RNAs: conventional approaches, network theory and artificial intelligence

Three types of highly promising small RNA therapeutics, namely, small interfering RNAs (siRNAs), microRNAs (miRNAs) and the RNA subtype of antisense oligonucleotides (ASOs), offer advantages over small-molecule drugs. These small RNAs can target any gene product, opening up new avenues of effective and safe therapeutic approaches for a wide range of diseases. In preclinical research, synthetic small RNAs play an essential role in the investigation of physiological and pathological pathways as silencers of specific genes, facilitating discovery and validation of drug targets in different conditions. Off-target effects of small RNAs, however, could make it difficult to interpret experimental results in the preclinical phase and may contribute to adverse events of small RNA therapeutics. Out of the two major types of off-target effects we focused on the hybridization-dependent, especially on the miRNA-like off-target effects. Our main aim was to discuss several approaches, including sequence design, chemical modifications and target prediction, to reduce hybridization-dependent off-target effects that should be considered even at the early development phase of small RNA therapy. Because there is no standard way of predicting hybridization-dependent off-target effects, this review provides an overview of all major state-of-the-art computational methods and proposes new approaches, such as the possible inclusion of network theory and artificial intelligence (AI) in the prediction workflows. Case studies and a concise survey of experimental methods for validating in silico predictions are also presented. These methods could contribute to interpret experimental results, to minimize off-target effects and hopefully to avoid off-target-related adverse events of small RNA therapeutics. LINKED ARTICLES: This article is part of a themed issue Non-coding RNA Therapeutics. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v182.2/issuetoc.

lncRNAs'p potential roles in the pathogenesis of cancer via interacting with signaling pathways; special focus on lncRNA-mediated signaling dysregulation in lung cancer

Lung cancer ranks among the most lethal types of cancer globally, with a high occurrence and fatality rate. The spread of cancer to other parts of the body, known as metastasis, is the primary cause of treatment failure and death in lung cancer cases. Current approaches for treating advanced lung cancer typically involve a combination of chemotherapy and targeted therapy. However, the majority of patients ultimately develop resistance to these treatments, leading to a worsened prognosis. In recent years, cancer biology research has predominantly focused on the role of protein-encoding genes in cancer development. Long non-coding RNAs (lncRNAs) are transcripts over 200 nucleotides in length that do not encode proteins but are crucial RNA molecules involved in numerous biological functions. While many functions of lncRNAs remain unknown, some have been linked to human diseases, including cancer. Studies have demonstrated that lncRNAs interact with other large molecules in the cell, such as proteins, DNA, and RNA, influencing various critical aspects of cancer. LncRNAs play a significant role in regulating gene expression and have a crucial function in the transcriptional regulation of cancer cells. They mediate various biological and clinical processes such as invasion, metastasis, apoptosis, and cell proliferation. Dysregulation of lncRNAs has been found to impact the process of carcinogenesis through advanced technologies like RNA sequencing and microarrays. Collectively, these long non-coding RNAs hold promise as potential biomarkers and therapeutic targets for human cancers. In this segment, we provide a comprehensive summary of the literature on the characteristics and formation of lncRNAs, along with an overview of their current known roles in lung cancer.

NEAT1 and CHROMR lncRNAs: a promising diagnostic tool for diffuse large B-cell lymphoma especially in elderly patients

Background: Long non-coding (lnc) RNAs have crucial regulatory roles in molecular pathways, and their dysregulation is associated with the pathogenesis of malignancies such as Diffuse large B-cell lymphoma (DLBCL). Therefore, we aimed to study the NEAT1 and CHROMR expression in DLBCL and explore their association with clinicopathological characteristics.Methods & materials: DLBCL and non-tumor lymph node specimens were obtained to assess the expression levels.Results: NEAT1 and CHROMR expressions were significantly increased in DLBCL, and were linked with the age of DLBCL patients (aged >60). NEAT1 and CHROMR overexpression may serve as moderate-to-good diagnostic biomarkers, with NEAT1 and CHROMR exhibiting area under the curve values of 0.781 and 0.831, respectively.

Recent progress and the emerging role of lncRNAs in cancer drug resistance; focusing on signaling pathways

It is becoming more and more apparent that many of the genetic alterations associated with cancer are located in areas that do not encode proteins. lncRNAs are a class of RNAs that do not code for proteins but play a crucial role in maintaining cell function and regulating various cellular processes. By doing this, they have recently introduced what may be a brand-new and essential layer of biological control. These have more than 200 nucleotides and are linked to several diseases; as a result, they have become potential tools for therapeutic intervention. Emerging technologies suggest the presence of mutations on genomic loci that give rise to lncRNAs rather than proteins in a disease as complex as cancer. These lncRNAs play essential parts in gene regulation, which impacts several cellular homeostasis processes, including proliferation, survival, migration, and genomic stability. The leading cause of death in the world today is cancer. Delays in diagnosis and a lack of standard and efficient treatments are the leading causes of the high death rate. Clinically, surgery is frequently used successfully to remove cancers that have not spread, but it is less successful in treating metastatic cancer, which has a drastically lower chance of survival. Chemotherapeutic drugs are a typical therapy to treat the cancer that has spread to other organs. Drug resistance to chemotherapy, however, presents a significant challenge to achieving positive outcomes and is frequently the cause of treatment failure. A substantial barrier to progress in medical oncology is cancer drug resistance. Resistance can develop clinically either before or after cancer treatment. According to this study, lncRNAs influence drug resistance through several different methods. LncRNAs often impact drug resistance by controlling the expression of a few intermediary regulatory variables rather than by directly affecting drug resistance. Additionally, lncRNAs have a variety of roles in cancer medication resistance. Most lncRNAs induce drug resistance when overexpressed; however, other lncRNAs have inhibitory effects. This study provides an overview of the current understanding of lncRNAs, relevance to cancer, and potential therapeutic applications.

Tailored machine learning models for functional RNA detection in genome-wide screens

The in silico prediction of non-coding and protein-coding genetic loci has received considerable attention in comparative genomics aiming in particular at the identification of properties of nucleotide sequences that are informative of their biological role in the cell. We present here a software framework for the alignment-based training, evaluation and application of machine learning models with user-defined parameters. Instead of focusing on the one-size-fits-all approach of pervasive in silico annotation pipelines, we offer a framework for the structured generation and evaluation of models based on arbitrary features and input data, focusing on stable and explainable results. Furthermore, we showcase the usage of our software package in a full-genome screen of Drosophila melanogaster and evaluate our results against the well-known but much less flexible program RNAz.

Transcriptome Screening of Long Noncoding RNAs and Their Target Protein-Coding Genes Unmasks a Dynamic Portrait of Seed Coat Coloration Associated with Anthocyanins in Tibetan Hulless Barley

Many plants have the capability to accumulate anthocyanins for coloration, and anthocyanins are advantageous to human health. In the case of hulless barley (Hordeum vulgare L. var. nudum), investigation into the mechanism of anthocyanin formation is limited to the level of protein-coding genes (PCGs). Here, we conducted a comprehensive bioinformatics analysis to identify a total of 9414 long noncoding RNAs (lncRNAs) in the seed coats of purple and white hulless barley along a developmental gradient. Transcriptome-wide profiles of lncRNAs documented several properties, including GC content fluctuation, uneven length, a diverse range of exon numbers, and a wide variety of transcript classifications. We found that certain lncRNAs in hulless barley possess detectable sequence conservation with Hordeum vulgare and other monocots. Furthermore, both differentially expressed lncRNAs (DElncRNAs) and PCGs (DEPCGs) were concentrated in the later seed development stages. On the one hand, DElncRNAs could potentially cis-regulate DEPCGs associated with multiple metabolic pathways, including flavonoid and anthocyanin biosynthesis in the late milk and soft dough stages. On the other hand, there was an opportunity for trans-regulated lncRNAs in the color-forming module to affect seed coat color by upregulating PCGs in the anthocyanin pathway. In addition, the interweaving of hulless barley lncRNAs and diverse TFs may function in seed coat coloration. Notably, we depicted a dynamic portrait of the anthocyanin synthesis pathway containing hulless barley lncRNAs. Therefore, this work provides valuable gene resources and more insights into the molecular mechanisms underlying anthocyanin accumulation in hulless barley from the perspective of lncRNAs, which facilitate the development of molecular design breeding in crops.

T2DB: A Web Database for Long Non-Coding RNA Genes in Type II Diabetes

Type II diabetes (T2D) is a growing health problem worldwide due to increased levels of obesity and can lead to other life-threatening diseases, such as cardiovascular and kidney diseases. As the number of individuals diagnosed with T2D rises, there is an urgent need to understand the pathogenesis of the disease in order to prevent further harm to the body caused by elevated blood glucose levels. Recent advances in long non-coding RNA (lncRNA) research may provide insights into the pathogenesis of T2D. Although lncRNAs can be readily detected in RNA sequencing (RNA-seq) data, most published datasets of T2D patients compared to healthy donors focus only on protein-coding genes, leaving lncRNAs to be undiscovered and understudied. To address this knowledge gap, we performed a secondary analysis of published RNA-seq data of T2D patients and of patients with related health complications to systematically analyze the expression changes of lncRNA genes in relation to the protein-coding genes. Since immune cells play important roles in T2D, we conducted loss-of-function experiments to provide functional data on the T2D-related lncRNA USP30-AS1, using an in vitro model of pro-inflammatory macrophage activation. To facilitate lncRNA research in T2D, we developed a web application, T2DB, to provide a one-stop-shop for expression profiling of protein-coding and lncRNA genes in T2D patients compared to healthy donors or subjects without T2D.

ASLncR: a novel computational tool for prediction of abiotic stress-responsive long non-coding RNAs in plants

Abiotic stresses are detrimental to plant growth and development and have a major negative impact on crop yields. A growing body of evidence indicates that a large number of long non-coding RNAs (lncRNAs) are key to many abiotic stress responses. Thus, identifying abiotic stress-responsive lncRNAs is essential in crop breeding programs in order to develop crop cultivars resistant to abiotic stresses. In this study, we have developed the first machine learning-based computational model for predicting abiotic stress-responsive lncRNAs. The lncRNA sequences which were responsive and non-responsive to abiotic stresses served as the two classes of the dataset for binary classification using the machine learning algorithms. The training dataset was created using 263 stress-responsive and 263 non-stress-responsive sequences, whereas the independent test set consists of 101 sequences from both classes. As the machine learning model can adopt only the numeric data, the Kmer features ranging from sizes 1 to 6 were utilized to represent lncRNAs in numeric form. To select important features, four different feature selection strategies were utilized. Among the seven learning algorithms, the support vector machine (SVM) achieved the highest cross-validation accuracy with the selected feature sets. The observed 5-fold cross-validation accuracy, AU-ROC, and AU-PRC were found to be 68.84, 72.78, and 75.86%, respectively. Furthermore, the robustness of the developed model (SVM with the selected feature) was evaluated using an independent test dataset, where the overall accuracy, AU-ROC, and AU-PRC were found to be 76.23, 87.71, and 88.49%, respectively. The developed computational approach was also implemented in an online prediction tool ASLncR accessible at https://iasri-sg.icar.gov.in/aslncr/ . The proposed computational model and the developed prediction tool are believed to supplement the existing effort for the identification of abiotic stress-responsive lncRNAs in plants.

An integrative analysis of an lncRNA-mRNA competing endogenous RNA network to identify functional lncRNAs in uterine leiomyomas with RNA sequencing

Objective: To explore the functions of mRNAs and lncRNAs in the occurrence of uterine leiomyomas (ULs) and further clarify the pathogenesis of UL by detecting the differential expression of mRNAs and lncRNAs in 10 cases of UL tissues and surrounding normal myometrial tissues by high-throughput RNA sequencing. Methods: The tissue samples of 10 patients who underwent hysterectomy for UL in Lianyungang Maternal and Child Health Hospital from January 2016 to December 2021 were collected. The differentially expressed mRNAs (DEmRNAs) and lncRNAs (DElncRNAs) were identified and further analyzed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. The protein-protein interaction network (PPI) was constructed in Cytoscape software. Functional annotation of the nearby target cis-DEmRNAs of DElncRNAs was performed with the Database for Annotation, Visualization, and Integrated Discovery (DAVID) (https://david.ncifcrf.gov/). Meanwhile, the co-expression network of DElncRNA-DEmRNA was constructed in Cytoscape software. Results: A total of 553 DElncRNAs (283 upregulated DElncRNAs and 270 downregulated DElncRNAs) and 3,293 DEmRNAs (1,632 upregulated DEmRNAs and 1,661 downregulated DEmRNAs) were obtained. GO pathway enrichment analysis revealed that several important pathways were significantly enriched in UL such as blood vessel development, regulation of ion transport, and external encapsulating structure organization. In addition, cytokine-cytokine receptor interaction, neuroactive ligand-receptor interaction, and complement and coagulation cascades were significantly enriched in KEGG pathway enrichment analysis. A total of 409 DElncRNAs-nearby-targeted DEmRNA pairs were detected, which included 118 DElncRNAs and 136 DEmRNAs. Finally, we found that the top two DElncRNAs with the most nearby DEmRNAs were BISPR and AC012531.1. Conclusion: These results suggested that 3,293 DEmRNAs and 553 DElncRNAs were differentially expressed in UL tissue and normal myometrium tissue, which might be candidate-identified therapeutic and prognostic targets for UL and be considered as offering several possible mechanisms and pathogenesis of UL in the future.

LINC01296 promotes proliferation of cutaneous malignant melanoma by regulating miR-324-3p/MAPK1 axis

OBJECTIVE

To investigate the functions and potential molecular mechanism of LINC01296 regarding the progression of cutaneous malignant melanoma (CMM) by the regulation of miR-324-3p/MAPK1 axis.

METHODS

The candidate differential lncRNAs of CMM were selected from GEPIA database, and quantitative real-time PCR (qRT-PCR) was utilized to assess the expression level of LINC01296 in human CMM tissues and cell lines. Cell proliferation assay, Colony formation assay, Ethynyl-2'-deoxyuridine (EDU) assay in vitro and tumorigenicity assays in nude mice in vivo were performed to examine the functions of LINC01296. Bioinformatics analysis, luciferase reporter assay and rescue experiments were also gained an insight into the underlying mechanisms of LINC01296 in CMM cell lines by miR-324-3p/MAPK1 axis.

RESULTS

In this study, the up-regulation of LINC01296 was found in CMM tissues and cell lines. Functionally, the over-expression of LINC01296 promoted the proliferation in CMM cell lines. In addition, immunochemistry analysis confirmed that the levels of MAPK1 and Ki-67 in sh-LINC01296-xenografted tumors was weaker than that in sh-NC-xenografted tumors. Then, bioinformatics analysis confirmed that LINC01296 interacted with miR-324-3p. Further investigations showed that MAPK1, which collected from the potential related genes of LINC01296, was the conjugated mRNA of miR-324-3p by luciferase reporter assay. Finally, the rescue experiments suggested the positive regulatory association among LINC01296 and MAPK1, which showed that MAPK1 could reverse the promoting-effect of LINC01296 in CMM cells in vitro.

CONCLUSIONS

Therefore, our findings provided insight into the mechanisms of LINC01296 via miR-324-3p/MAPK1 axis in CMM, and revealed an alternative target for the diagnosis and treatment of CMM.

A large-scale benchmark study of tools for the classification of protein-coding and non-coding RNAs

Identification of protein-coding and non-coding transcripts is paramount for understanding their biological roles. Computational approaches have been addressing this task for over a decade; however, generalized and high-performance models are still unreliable. This benchmark study assessed the performance of 24 tools producing >55 models on the datasets covering a wide range of species. We have collected 135 small and large transcriptomic datasets from existing studies for comparison and identified the potential bottlenecks hampering the performance of current tools. The key insights of this study include lack of standardized training sets, reliance on homogeneous training data, gradual changes in annotated data, lack of augmentation with homology searches, the presence of false positives and negatives in datasets and the lower performance of end-to-end deep learning models. We also derived a new dataset, RNAChallenge, from the benchmark considering hard instances that may include potential false alarms. The best and least well performing models under- and overfit the dataset, respectively, thereby serving a dual purpose. For computational approaches, it will be valuable to develop accurate and unbiased models. The identification of false alarms will be of interest for genome annotators, and experimental study of hard RNAs will help to untangle the complexity of the RNA world.

Glycation-Associated Diabetic Nephropathy and the Role of Long Noncoding RNAs

The glycation of various biomolecules is the root cause of many pathological conditions associated with diabetic nephropathy and end-stage kidney disease. Glycation imbalances metabolism and increases renal cell injury. Numerous therapeutic measures have narrowed down the adverse effects of endogenous glycation, but efficient and potent measures are miles away. Recent advances in the identification and characterization of noncoding RNAs, especially the long noncoding RNAs (lncRNAs), have opened a mammon of new biology to explore the mitigations for glycation-associated diabetic nephropathy. Furthermore, tissue-specific distribution and condition-specific expression make lncRNA a promising key for second-generation therapeutic interventions. Though the techniques to identify and exemplify noncoding RNAs are rapidly evolving, the lncRNA study encounters multiple methodological constraints. This review will discuss lncRNAs and their possible involvement in glycation and advanced glycation end products (AGEs) signaling pathways. We further highlight the possible approaches for lncRNA-based therapeutics and their working mechanism for perturbing glycation and conclude our review with lncRNAs biology-related future opportunities.

Information Theory for Biological Sequence Classification: A Novel Feature Extraction Technique Based on Tsallis Entropy

In recent years, there has been an exponential growth in sequencing projects due to accelerated technological advances, leading to a significant increase in the amount of data and resulting in new challenges for biological sequence analysis. Consequently, the use of techniques capable of analyzing large amounts of data has been explored, such as machine learning (ML) algorithms. ML algorithms are being used to analyze and classify biological sequences, despite the intrinsic difficulty in extracting and finding representative biological sequence methods suitable for them. Thereby, extracting numerical features to represent sequences makes it statistically feasible to use universal concepts from Information Theory, such as Tsallis and Shannon entropy. In this study, we propose a novel Tsallis entropy-based feature extractor to provide useful information to classify biological sequences. To assess its relevance, we prepared five case studies: (1) an analysis of the entropic index q; (2) performance testing of the best entropic indices on new datasets; (3) a comparison made with Shannon entropy and (4) generalized entropies; (5) an investigation of the Tsallis entropy in the context of dimensionality reduction. As a result, our proposal proved to be effective, being superior to Shannon entropy and robust in terms of generalization, and also potentially representative for collecting information in fewer dimensions compared with methods such as Singular Value Decomposition and Uniform Manifold Approximation and Projection.