Prediction of LncRNA Subcellular Localization with Deep Learning from Sequence Features

MIAT LncRNA: A multifunctional key player in non-oncological pathological conditions

The discovery of non-coding RNAs (ncRNAs) has unveiled a wide range of transcripts that do not encode proteins but play key roles in several cellular and molecular processes. Long noncoding RNAs (lncRNAs) are specific class of ncRNAs that are longer than 200 nucleotides and have gained significant attention due to their diverse mechanisms of action and potential involvement in various pathological conditions. In the current review, the authors focus on the role of lncRNAs, specifically highlighting the Myocardial Infarction Associated Transcript (MIAT), in non-oncological context. MIAT is a nuclear lncRNA that has been directly linked to myocardial infarction and is reported to control post-transcriptional processes as a competitive endogenous RNA (ceRNA) molecule. It interacts with microRNAs (miRNAs), thereby limiting the translation and expression of their respective target messenger RNA (mRNA) and regulating protein expression. Yet, MIAT has been implicated in other numerous pathological conditions such as other cardiovascular diseases, autoimmune disease, neurodegenerative diseases, metabolic diseases, and many others. In this review, the authors emphasize that MIAT exhibits distinct expression patterns and functions across different pathological conditions and is emerging as potential diagnostic, prognostic, and therapeutic agent. Additionally, the authors highlight the regulatory role of MIAT and shed light on the involvement of lncRNAs and specifically MIAT in various non-oncological pathological conditions.

The regulatory mechanism of garlic skin improving the growth performance of fattening sheep through metabolism and immunity

Objective

Garlic skin (GAS) has been proven to improve the growth performance of fattening sheep. However, the mechanism by which GAS affects fattening sheep is not yet clear. The aim of this study is to investigate the effects of adding GAS to feed on the growth performance, rumen and fecal microbiota, serum and urine metabolism, and transcriptomics of rumen epithelial cells in fattening sheep.

Methods

GAS with 80 g/kg dry matter (DM) was added to the diet of fattening sheep to study the effects of GAS on gut microbiota, serum and urine metabolism, and transcriptome of rumen epithelial tissue in fattening sheep. Twelve Hu sheep (body weights; BW, 23.0 ± 2.3 kg and ages 120 ± 3.5 d) were randomly divided into two groups. The CON group was the basal diet, while the GAS group was supplemented with GAS in the basal diet. The trial period was 10 weeks, with the first 2 weeks being the pre-trial period.

Results

The daily average weight gain of fattening sheep in the GAS group was significantly higher than that in the CON group (p < 0.05), and the serum GSH-Px of the GAS group fattening sheep was significantly increased, while MDA was significantly reduced (p < 0.05). Based on the genus classification level, the addition of garlic peel in the diet changed the intestinal microbial composition, and the relative abundance was significantly upregulated by Metanobrevibater (p < 0.05), while significantly downregulated by Akkermansia, Parasutterella, and Guggenheimella (p < 0.05). Metabolomics analysis found that there were 166 significantly different metabolites in serum and 68 significantly different metabolites in urine between the GAS and CON groups (p < 0.05). GAS had an impact on amino acid metabolism, pyrimidine metabolism, methane metabolism, riboflavin metabolism, and unsaturated fatty acid synthesis pathways (p < 0.05). Transcriptome sequencing showed that differentially expressed genes were mainly enriched in immune regulatory function, improving the health of fattening sheep.

Conclusion

Adding GAS can improve the energy metabolism and immune function of fattening sheep by altering gut microbiota, metabolome, and transcriptome, thereby improving the growth performance of fattening sheep.

Pivotal functions and impact of long con-coding RNAs on cellular processes and genome integrity

Recent advances in uncovering the mysteries of the human genome suggest that long non-coding RNAs (lncRNAs) are important regulatory components. Although lncRNAs are known to affect gene transcription, their mechanisms and biological implications are still unclear. Experimental research has shown that lncRNA synthesis, subcellular localization, and interactions with macromolecules like DNA, other RNAs, or proteins can all have an impact on gene expression in various biological processes. In this review, we highlight and discuss the major mechanisms through which lncRNAs function as master regulators of the human genome. Specifically, the objective of our review is to examine how lncRNAs regulate different processes like cell division, cell cycle, and immune responses, and unravel their roles in maintaining genomic architecture and integrity.

Multifaced roles of the long non-coding RNA DRAIC in cancer progression

Long non-coding RNAs (lncRNA) are functional RNAs, with over 200 nucleotides in length and lacking protein-coding potential. Studies have indicated that lncRNAs are important gene regulators under physiological conditions. Aberrant lncRNA expression is associated with the initiation and progression of various diseases, including cancers. High-throughput transcriptome analyses have revealed thousands of lncRNAs as putative tumor suppressors or promoters in various cancers, but the detailed molecular mechanisms of each lncRNA remain unclear. Downregulated RNA In Cancer, inhibitor of cell invasion and migration (DRAIC) (also known as LOC145837 and RP11-279F6.1) is a lncRNA that inhibits or promotes cancer progression with several modes of action. DRAIC was originally identified as a tumor-suppressive lncRNA in prostate adenocarcinoma. Subsequent studies also revealed that it has an anti-tumor role in glioblastoma, triple-negative breast cancer, and stomach adenocarcinoma. However, DRAIC exhibits oncogenic functions in other malignancies, such as lung adenocarcinoma and esophageal carcinoma, indicating its highly context-dependent effects on cancer progression and clinical outcomes. DRAIC and its associated pathways regulate various biological processes, including proliferation, invasion, metastasis, autophagy, and neuroendocrine function. This review introduces the multifaceted roles of DRAIC, particularly in cancer progression, and discusses its biological significance and clinical implications.

A comprehensive survey on deep learning-based identification and predicting the interaction mechanism of long non-coding RNAs

Long noncoding RNAs (lncRNAs) have been discovered to be extensively involved in eukaryotic epigenetic, transcriptional, and post-transcriptional regulatory processes with the advancements in sequencing technology and genomics research. Therefore, they play crucial roles in the body's normal physiology and various disease outcomes. Presently, numerous unknown lncRNA sequencing data require exploration. Establishing deep learning-based prediction models for lncRNAs provides valuable insights for researchers, substantially reducing time and costs associated with trial and error and facilitating the disease-relevant lncRNA identification for prognosis analysis and targeted drug development as the era of artificial intelligence progresses. However, most lncRNA-related researchers lack awareness of the latest advancements in deep learning models and model selection and application in functional research on lncRNAs. Thus, we elucidate the concept of deep learning models, explore several prevalent deep learning algorithms and their data preferences, conduct a comprehensive review of recent literature studies with exemplary predictive performance over the past 5 years in conjunction with diverse prediction functions, critically analyze and discuss the merits and limitations of current deep learning models and solutions, while also proposing prospects based on cutting-edge advancements in lncRNA research.

A BERT-based model for the prediction of lncRNA subcellular localization in Homo sapiens

Understanding the subcellular localization of lncRNAs is crucial for comprehending their regulation activities. The conventional detection of lncRNA subcellular location usually uses in situ detection techniques, which are resource intensive. Some machine learning-based algorithms have been proposed for lncRNA subcellular location prediction in mammals. However, due to the low level of conservation of lncRNA sequence, the performance of cross-species models remains unsatisfactory. In this study, we curated a novel dataset containing subcellular location information of lncRNAs in Homo sapiens. Subsequently, based on the BERT pre-trained language algorithm, we developed a model for lncRNA subcellular location prediction. Our model achieved a micro-average area under the receiver operating characteristic (AUROC) of 0.791 on the training set and an AUROC of 0.700 on the testing nucleus set. Additionally, we conducted cross-species validation and motif discovery to further investigate underlying patterns. In summary, our study provides valuable guidance and computational analysis tools for exploring the mechanisms of lncRNA subcellular localization and the dynamic spatial changes of RNA in abnormal physiological states.

Seq-RBPPred: Predicting RNA-Binding Proteins from Sequence

RNA-binding proteins (RBPs) can interact with RNAs to regulate RNA translation, modification, splicing, and other important biological processes. The accurate identification of RBPs is of paramount importance for gaining insights into the intricate mechanisms underlying organismal life activities. Traditional experimental methods to predict RBPs require a lot of time and money, so it is important to develop computational methods to predict RBPs. However, the existing approaches for RBP prediction still require further improvement due to unidentified RBPs in many species. In this study, we present Seq-RBPPred (predicting RBPs from sequence), a novel method that utilizes a comprehensive feature representation encompassing both biophysical properties and hidden-state features derived from protein sequences. In the results, comprehensive performance evaluations of Seq-RBPPred its superiority compare with state-of-the-art methods, yielding impressive performance including 0.922 for overall accuracy, 0.926 for sensitivity, 0.903 for specificity, and Matthew's correlation coefficient (MCC) of 0.757 as ascertained from the evaluation of the testing set. The data and code of Seq-RBPPred are available at https://github.com/yaoyao-11/Seq-RBPPred.

Exploration for Blood Biomarkers of Human Long Non-coding RNAs Predicting Oxaliplatin-Induced Chronic Neuropathy Through iPS Cell-Derived Sensory Neuron Analysis

Oxaliplatin, a platinum-based chemotherapeutic agent, frequently causes acute and chronic peripheral sensory neuropathy, for which no effective treatment has been established. In particular, chronic neuropathy can persist for years even after treatment completion, thus worsening patients' quality of life. To avoid the development of intractable adverse effects, a predictive biomarker early in treatment is awaited. In this study, we explored extracellular long non-coding RNAs (lncRNAs) released from primary sensory neurons as biomarker candidates for oxaliplatin-induced peripheral neuropathy. Because many human-specific lncRNA genes exist, we induced peripheral sensory neurons from human induced pluripotent stem cells. Oxaliplatin treatment changed the levels of many lncRNAs in extracellular vesicles (EVs) released from cultured primary sensory neurons. Among them, the levels of release of lncRNAs that were considered to be selectively expressed in dorsal root ganglia were correlated with those of lncRNAs in plasma EV obtained from healthy individuals. Several lncRNAs in plasma EVs early after the initiation of treatment showed greater changes in patients who did not develop chronic neuropathy that persisted for more than 1 year than in those who did. Therefore, these extracellular lncRNAs in plasma EVs may represent predictive biomarkers for the development of chronic peripheral neuropathy induced by oxaliplatin.

Comprehensive landscape and future perspective of long noncoding RNAs in non-small cell lung cancer: it takes a village

Long noncoding RNAs (lncRNAs) are a distinct subtype of RNA that lack protein-coding capacity but exert significant influence on various cellular processes. In non-small cell lung cancer (NSCLC), dysregulated lncRNAs act as either oncogenes or tumor suppressors, contributing to tumorigenesis and tumor progression. LncRNAs directly modulate gene expression, act as competitive endogenous RNAs by interacting with microRNAs or proteins, and associate with RNA binding proteins. Moreover, lncRNAs can reshape the tumor immune microenvironment and influence cellular metabolism, cancer cell stemness, and angiogenesis by engaging various signaling pathways. Notably, lncRNAs have shown great potential as diagnostic or prognostic biomarkers in liquid biopsies and therapeutic strategies for NSCLC. This comprehensive review elucidates the significant roles and diverse mechanisms of lncRNAs in NSCLC. Furthermore, we provide insights into the clinical relevance, current research progress, limitations, innovative research approaches, and future perspectives for targeting lncRNAs in NSCLC. By summarizing the existing knowledge and advancements, we aim to enhance the understanding of the pivotal roles played by lncRNAs in NSCLC and stimulate further research in this field. Ultimately, unraveling the complex network of lncRNA-mediated regulatory mechanisms in NSCLC could potentially lead to the development of novel diagnostic tools and therapeutic strategies.

LncLocFormer: a Transformer-based deep learning model for multi-label lncRNA subcellular localization prediction by using localization-specific attention mechanism

MOTIVATION

There is mounting evidence that the subcellular localization of lncRNAs can provide valuable insights into their biological functions. In the real world of transcriptomes, lncRNAs are usually localized in multiple subcellular localizations. Furthermore, lncRNAs have specific localization patterns for different subcellular localizations. Although several computational methods have been developed to predict the subcellular localization of lncRNAs, few of them are designed for lncRNAs that have multiple subcellular localizations, and none of them take motif specificity into consideration.

RESULTS

In this study, we proposed a novel deep learning model, called LncLocFormer, which uses only lncRNA sequences to predict multi-label lncRNA subcellular localization. LncLocFormer utilizes eight Transformer blocks to model long-range dependencies within the lncRNA sequence and shares information across the lncRNA sequence. To exploit the relationship between different subcellular localizations and find distinct localization patterns for different subcellular localizations, LncLocFormer employs a localization-specific attention mechanism. The results demonstrate that LncLocFormer outperforms existing state-of-the-art predictors on the hold-out test set. Furthermore, we conducted a motif analysis and found LncLocFormer can capture known motifs. Ablation studies confirmed the contribution of the localization-specific attention mechanism in improving the prediction performance.

AVAILABILITY AND IMPLEMENTATION

The LncLocFormer web server is available at http://csuligroup.com:9000/LncLocFormer. The source code can be obtained from https://github.com/CSUBioGroup/LncLocFormer.

DlncRNALoc: A discrete wavelet transform-based model for predicting lncRNA subcellular localization

The prediction of long non-coding RNA (lncRNA) subcellular localization is essential to the understanding of its function and involvement in cellular regulation. Traditional biological experimental methods are costly and time-consuming, making computational methods the preferred approach for predicting lncRNA subcellular localization (LSL). However, existing computational methods have limitations due to the structural characteristics of lncRNAs and the uneven distribution of data across subcellular compartments. We propose a discrete wavelet transform (DWT)-based model for predicting LSL, called DlncRNALoc. We construct a physicochemical property matrix of a 2-tuple bases based on lncRNA sequences, and we introduce a DWT lncRNA feature extraction method. We use the Synthetic Minority Over-sampling Technique (SMOTE) for oversampling and the local fisher discriminant analysis (LFDA) algorithm to optimize feature information. The optimized feature vectors are fed into support vector machine (SVM) to construct a predictive model. DlncRNALoc has been applied for a five-fold cross-validation on the three sets of benchmark datasets. Extensive experiments have demonstrated the superiority and effectiveness of the DlncRNALoc model in predicting LSL.

Genome-wide measurement of RNA dissociation from chromatin classifies transcripts by their dynamics and reveals rapid dissociation of enhancer lncRNAs

Long non-coding RNAs (lncRNAs) are involved in gene expression regulation in cis. Although enriched in the cell chromatin fraction, to what degree this defines their regulatory potential remains unclear. Furthermore, the factors underlying lncRNA chromatin tethering, as well as the molecular basis of efficient lncRNA chromatin dissociation and its impact on enhancer activity and target gene expression, remain to be resolved. Here, we developed chrTT-seq, which combines the pulse-chase metabolic labeling of nascent RNA with chromatin fractionation and transient transcriptome sequencing to follow nascent RNA transcripts from their transcription on chromatin to release and allows the quantification of dissociation dynamics. By incorporating genomic, transcriptomic, and epigenetic metrics, as well as RNA-binding protein propensities, in machine learning models, we identify features that define transcript groups of different chromatin dissociation dynamics. Notably, lncRNAs transcribed from enhancers display reduced chromatin retention, suggesting that, in addition to splicing, their chromatin dissociation may shape enhancer activity.

RNA trafficking and subcellular localization-a review of mechanisms, experimental and predictive methodologies

RNA localization is essential for regulating spatial translation, where RNAs are trafficked to their target locations via various biological mechanisms. In this review, we discuss RNA localization in the context of molecular mechanisms, experimental techniques and machine learning-based prediction tools. Three main types of molecular mechanisms that control the localization of RNA to distinct cellular compartments are reviewed, including directed transport, protection from mRNA degradation, as well as diffusion and local entrapment. Advances in experimental methods, both image and sequence based, provide substantial data resources, which allow for the design of powerful machine learning models to predict RNA localizations. We review the publicly available predictive tools to serve as a guide for users and inspire developers to build more effective prediction models. Finally, we provide an overview of multimodal learning, which may provide a new avenue for the prediction of RNA localization.

NN-RNALoc: Neural network-based model for prediction of mRNA sub-cellular localization using distance-based sub-sequence profiles

The localization of messenger RNAs (mRNAs) is a frequently observed phenomenon and a crucial aspect of gene expression regulation. It is also a mechanism for targeting proteins to a specific cellular region. Moreover, prior research and studies have shown the significance of intracellular RNA positioning during embryonic and neural dendrite formation. Incorrect RNA localization, which can be caused by a variety of factors, such as mutations in trans-regulatory elements, has been linked to the development of certain neuromuscular diseases and cancer. In this study, we introduced NN-RNALoc, a neural network-based method for predicting the cellular location of mRNA using novel features extracted from mRNA sequence data and protein interaction patterns. In fact, we developed a distance-based subsequence profile for RNA sequence representation that is more memory and time-efficient than well-known k-mer sequence representation. Combining protein-protein interaction data, which is essential for numerous biological processes, with our novel distance-based subsequence profiles of mRNA sequences produces more accurate features. On two benchmark datasets, CeFra-Seq and RNALocate, the performance of NN-RNALoc is compared to powerful predictive models proposed in previous works (mRNALoc, RNATracker, mLoc-mRNA, DM3Loc, iLoc-mRNA, and EL-RMLocNet), and a ground neural (DNN5-mer) network. Compared to the previous methods, NN-RNALoc significantly reduces computation time and also outperforms them in terms of accuracy. This study's source code and datasets are freely accessible at https://github.com/NeginBabaiha/NN-RNALoc.

Review and perspective on bioinformatics tools using machine learning and deep learning for predicting antiviral peptides

Viruses constitute a constant threat to global health and have caused millions of human and animal deaths throughout human history. Despite advances in the discovery of antiviral compounds that help fight these pathogens, finding a solution to this problem continues to be a task that consumes time and financial resources. Currently, artificial intelligence (AI) has revolutionized many areas of the biological sciences, making it possible to decipher patterns in amino acid sequences that encode different functions and activities. Within the field of AI, machine learning, and deep learning algorithms have been used to discover antimicrobial peptides. Due to their effectiveness and specificity, antimicrobial peptides (AMPs) hold excellent promise for treating various infections caused by pathogens. Antiviral peptides (AVPs) are a specific type of AMPs that have activity against certain viruses. Unlike the research focused on the development of tools and methods for the prediction of antimicrobial peptides, those related to the prediction of AVPs are still scarce. Given the significance of AVPs as potential pharmaceutical options for human and animal health and the ongoing AI revolution, we have reviewed and summarized the current machine learning and deep learning-based tools and methods available for predicting these types of peptides.

Investigation into the Role of Long-Non-Coding RNA MIAT in Leukemia

Myocardial Infarction Associated Transcript (MIAT) is a nuclear long non-coding RNA (LncRNA) with four different splicing variants. MIAT dysregulation is associated with carcinogenesis, mainly acting as an oncogene regulating cellular growth, invasion, and metastasis. The aim of the current study is to investigate the role of MIAT in the regulation of T and chronic myeloid leukemic cell survival. To this end, MIAT was silenced using MIAT-specific siRNAs in leukemic cell lines, and functional assays were performed thereafter. This investigation also aims to investigate the effects of MIAT silencing on the expression of core genes involved in cancer. Functional studies and gene expression determination confirm that MIAT knockdown not only affects short- and long-term survival and the apoptosis of leukemic cells but also plays a pivotal role in the alteration of key genes involved in cancer, including c-MYC and HIF-1A. Our observations suggest that MIAT could act as an oncogene and it has the potential to be used not only as a reliable biomarker for leukemia, but also be employed for prognostic and therapeutic purposes.

DAmiRLocGNet: miRNA subcellular localization prediction by combining miRNA-disease associations and graph convolutional networks

MicroRNAs (miRNAs) are human post-transcriptional regulators in humans, which are involved in regulating various physiological processes by regulating the gene expression. The subcellular localization of miRNAs plays a crucial role in the discovery of their biological functions. Although several computational methods based on miRNA functional similarity networks have been presented to identify the subcellular localization of miRNAs, it remains difficult for these approaches to effectively extract well-referenced miRNA functional representations due to insufficient miRNA-disease association representation and disease semantic representation. Currently, there has been a significant amount of research on miRNA-disease associations, making it possible to address the issue of insufficient miRNA functional representation. In this work, a novel model is established, named DAmiRLocGNet, based on graph convolutional network (GCN) and autoencoder (AE) for identifying the subcellular localizations of miRNA. The DAmiRLocGNet constructs the features based on miRNA sequence information, miRNA-disease association information and disease semantic information. GCN is utilized to gather the information of neighboring nodes and capture the implicit information of network structures from miRNA-disease association information and disease semantic information. AE is employed to capture sequence semantics from sequence similarity networks. The evaluation demonstrates that the performance of DAmiRLocGNet is superior to other competing computational approaches, benefiting from implicit features captured by using GCNs. The DAmiRLocGNet has the potential to be applied to the identification of subcellular localization of other non-coding RNAs. Moreover, it can facilitate further investigation into the functional mechanisms underlying miRNA localization. The source code and datasets are accessed at http://bliulab.net/DAmiRLocGNet.

A review from biological mapping to computation-based subcellular localization

Subcellular localization is crucial to the study of virus and diseases. Specifically, research on protein subcellular localization can help identify clues between virus and host cells that can aid in the design of targeted drugs. Research on RNA subcellular localization is significant for human diseases (such as Alzheimer's disease, colon cancer, etc.). To date, only reviews addressing subcellular localization of proteins have been published, which are outdated for reference, and reviews of RNA subcellular localization are not comprehensive. Therefore, we collated (the most up-to-date) literature on protein and RNA subcellular localization to help researchers understand changes in the field of protein and RNA subcellular localization. Extensive and complete methods for constructing subcellular localization models have also been summarized, which can help readers understand the changes in application of biotechnology and computer science in subcellular localization research and explore how to use biological data to construct improved subcellular localization models. This paper is the first review to cover both protein subcellular localization and RNA subcellular localization. We urge researchers from biology and computational biology to jointly pay attention to transformation patterns, interrelationships, differences, and causality of protein subcellular localization and RNA subcellular localization.

Aid or Antagonize: Nuclear Long Noncoding RNAs Regulate Host Responses and Outcomes of Viral Infections

Long noncoding RNAs (lncRNAs) are transcripts measuring >200 bp in length and devoid of protein-coding potential. LncRNAs exceed the number of protein-coding mRNAs and regulate cellular, developmental, and immune pathways through diverse molecular mechanisms. In recent years, lncRNAs have emerged as epigenetic regulators with prominent roles in health and disease. Many lncRNAs, either host or virus-encoded, have been implicated in critical cellular defense processes, such as cytokine and antiviral gene expression, the regulation of cell signaling pathways, and the activation of transcription factors. In addition, cellular and viral lncRNAs regulate virus gene expression. Viral infections and associated immune responses alter the expression of host lncRNAs regulating immune responses, host metabolism, and viral replication. The influence of lncRNAs on the pathogenesis and outcomes of viral infections is being widely explored because virus-induced lncRNAs can serve as diagnostic and therapeutic targets. Future studies should focus on thoroughly characterizing lncRNA expressions in virus-infected primary cells, investigating their role in disease prognosis, and developing biologically relevant animal or organoid models to determine their suitability for specific therapeutic targeting. Many cellular and viral lncRNAs localize in the nucleus and epigenetically modulate viral transcription, latency, and host responses to infection. In this review, we provide an overview of the role of nuclear lncRNAs in the pathogenesis and outcomes of viral infections, such as the Influenza A virus, Sendai Virus, Respiratory Syncytial Virus, Hepatitis C virus, Human Immunodeficiency Virus, and Herpes Simplex Virus. We also address significant advances and barriers in characterizing lncRNA function and explore the potential of lncRNAs as therapeutic targets.

GM-lncLoc: LncRNAs subcellular localization prediction based on graph neural network with meta-learning

In recent years, a large number of studies have shown that the subcellular localization of long non-coding RNAs (lncRNAs) can bring crucial information to the recognition of lncRNAs function. Therefore, it is of great significance to establish a computational method to accurately predict the subcellular localization of lncRNA. Previous prediction models are based on low-level sequences information and are troubled by the few samples problem. In this study, we propose a new prediction model, GM-lncLoc, which is based on the initial information extracted from the lncRNA sequence, and also combines the graph structure information to extract high level features of lncRNA. In addition, the training mode of meta-learning is introduced to obtain meta-parameters by training a series of tasks. With the meta-parameters, the final parameters of other similar tasks can be learned quickly, so as to solve the problem of few samples in lncRNA subcellular localization. Compared with the previous methods, GM-lncLoc achieved the best results with an accuracy of 93.4 and 94.2% in the benchmark datasets of 5 and 4 subcellular compartments, respectively. Furthermore, the prediction performance of GM-lncLoc was also better on the independent dataset. It shows the effectiveness and great potential of our proposed method for lncRNA subcellular localization prediction. The datasets and source code are freely available at https://github.com/JunzheCai/GM-lncLoc .

GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding lncRNA functions. Most of existing lncRNA subcellular localization prediction methods use k-mer frequency features to encode lncRNA sequences. However, k-mer frequency features lose sequence order information and fail to capture sequence patterns and motifs of different lengths. In this paper, we proposed GraphLncLoc, a graph convolutional network-based deep learning model, for predicting lncRNA subcellular localization. Unlike previous studies encoding lncRNA sequences by using k-mer frequency features, GraphLncLoc transforms lncRNA sequences into de Bruijn graphs, which transforms the sequence classification problem into a graph classification problem. To extract the high-level features from the de Bruijn graph, GraphLncLoc employs graph convolutional networks to learn latent representations. Then, the high-level feature vectors derived from de Bruijn graph are fed into a fully connected layer to perform the prediction task. Extensive experiments show that GraphLncLoc achieves better performance than traditional machine learning models and existing predictors. In addition, our analyses show that transforming sequences into graphs has more distinguishable features and is more robust than k-mer frequency features. The case study shows that GraphLncLoc can uncover important motifs for nucleus subcellular localization. GraphLncLoc web server is available at http://csuligroup.com:8000/GraphLncLoc/.

De novo genes with an lncRNA origin encode unique human brain developmental functionality

Human de novo genes can originate from neutral long non-coding RNA (lncRNA) loci and are evolutionarily significant in general, yet how and why this all-or-nothing transition to functionality happens remains unclear. Here, in 74 human/hominoid-specific de novo genes, we identified distinctive U1 elements and RNA splice-related sequences accounting for RNA nuclear export, differentiating mRNAs from lncRNAs, and driving the origin of de novo genes from lncRNA loci. The polymorphic sites facilitating the lncRNA-mRNA conversion through regulating nuclear export are selectively constrained, maintaining a boundary that differentiates mRNAs from lncRNAs. The functional new genes actively passing through it thus showed a mode of pre-adaptive origin, in that they acquire functions along with the achievement of their coding potential. As a proof of concept, we verified the regulations of splicing and U1 recognition on the nuclear export efficiency of one of these genes, the ENSG00000205704, in human neural progenitor cells. Notably, knock-out or over-expression of this gene in human embryonic stem cells accelerates or delays the neuronal maturation of cortical organoids, respectively. The transgenic mice with ectopically expressed ENSG00000205704 showed enlarged brains with cortical expansion. We thus demonstrate the key roles of nuclear export in de novo gene origin. These newly originated genes should reflect the novel uniqueness of human brain development.

RNAlight: a machine learning model to identify nucleotide features determining RNA subcellular localization

Different RNAs have distinct subcellular localizations. However, nucleotide features that determine these distinct distributions of lncRNAs and mRNAs have yet to be fully addressed. Here, we develop RNAlight, a machine learning model based on LightGBM, to identify nucleotide k-mers contributing to the subcellular localizations of mRNAs and lncRNAs. With the Tree SHAP algorithm, RNAlight extracts nucleotide features for cytoplasmic or nuclear localization of RNAs, indicating the sequence basis for distinct RNA subcellular localizations. By assembling k-mers to sequence features and subsequently mapping to known RBP-associated motifs, different types of sequence features and their associated RBPs were additionally uncovered for lncRNAs and mRNAs with distinct subcellular localizations. Finally, we extended RNAlight to precisely predict the subcellular localizations of other types of RNAs, including snRNAs, snoRNAs and different circular RNA transcripts, suggesting the generality of using RNAlight for RNA subcellular localization prediction.

High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging

Resolving the spatial distribution of RNA and protein in tissues at subcellular resolution is a challenge in the field of spatial biology. We describe spatial molecular imaging, a system that measures RNAs and proteins in intact biological samples at subcellular resolution by performing multiple cycles of nucleic acid hybridization of fluorescent molecular barcodes. We demonstrate that spatial molecular imaging has high sensitivity (one or two copies per cell) and very low error rate (0.0092 false calls per cell) and background (~0.04 counts per cell). The imaging system generates three-dimensional, super-resolution localization of analytes at ~2 million cells per sample. Cell segmentation is morphology based using antibodies, compatible with formalin-fixed, paraffin-embedded samples. We measured multiomic data (980 RNAs and 108 proteins) at subcellular resolution in formalin-fixed, paraffin-embedded tissues (nonsmall cell lung and breast cancer) and identified >18 distinct cell types, ten unique tumor microenvironments and 100 pairwise ligand-receptor interactions. Data on >800,000 single cells and ~260 million transcripts can be accessed at http://nanostring.com/CosMx-dataset .

Genome-Wide Analysis of Human Long Noncoding RNAs: A Provocative Review

Do long noncoding RNAs (lncRNAs) contribute little or substantively to human biology? To address how lncRNA loci and their transcripts, structures, interactions, and functions contribute to human traits and disease, we adopt a genome-wide perspective. We intend to provoke alternative interpretation of questionable evidence and thorough inquiry into unsubstantiated claims. We discuss pitfalls of lncRNA experimental and computational methods as well as opposing interpretations of their results. The majority of evidence, we argue, indicates that most lncRNA transcript models reflect transcriptional noise or provide minor regulatory roles, leaving relatively few human lncRNAs that contribute centrally to human development, physiology, or behavior. These important few tend to be spliced and better conserved but lack a simple syntax relating sequence to structure and mechanism, and so resist simple categorization. This genome-wide view should help investigators prioritize individual lncRNAs based on their likely contribution to human biology.

Prediction of Synaptically Localized RNAs in Human Neurons Using Developmental Brain Gene Expression Data

In the nervous system, synapses are special and pervasive structures between axonal and dendritic terminals, which facilitate electrical and chemical communications among neurons. Extensive studies have been conducted in mice and rats to explore the RNA pool at synapses and investigate RNA transport, local protein synthesis, and synaptic plasticity. However, owing to the experimental difficulties of studying human synaptic transcriptomes, the full pool of human synaptic RNAs remains largely unclear. We developed a new machine learning method, called PredSynRNA, to predict the synaptic localization of human RNAs. Training instances of dendritically localized RNAs were compiled from previous rodent studies, overcoming the shortage of empirical instances of human synaptic RNAs. Using RNA sequence and gene expression data as features, various models with different learning algorithms were constructed and evaluated. Strikingly, the models using the developmental brain gene expression features achieved superior performance for predicting synaptically localized RNAs. We examined the relevant expression features learned by PredSynRNA and used an independent test dataset to further validate the model performance. PredSynRNA models were then applied to the prediction and prioritization of candidate RNAs localized to human synapses, providing valuable targets for experimental investigations into neuronal mechanisms and brain disorders.

Circ-LocNet: A Computational Framework for Circular RNA Sub-Cellular Localization Prediction

Circular ribonucleic acids (circRNAs) are novel non-coding RNAs that emanate from alternative splicing of precursor mRNA in reversed order across exons. Despite the abundant presence of circRNAs in human genes and their involvement in diverse physiological processes, the functionality of most circRNAs remains a mystery. Like other non-coding RNAs, sub-cellular localization knowledge of circRNAs has the aptitude to demystify the influence of circRNAs on protein synthesis, degradation, destination, their association with different diseases, and potential for drug development. To date, wet experimental approaches are being used to detect sub-cellular locations of circular RNAs. These approaches help to elucidate the role of circRNAs as protein scaffolds, RNA-binding protein (RBP) sponges, micro-RNA (miRNA) sponges, parental gene expression modifiers, alternative splicing regulators, and transcription regulators. To complement wet-lab experiments, considering the progress made by machine learning approaches for the determination of sub-cellular localization of other non-coding RNAs, the paper in hand develops a computational framework, Circ-LocNet, to precisely detect circRNA sub-cellular localization. Circ-LocNet performs comprehensive extrinsic evaluation of 7 residue frequency-based, residue order and frequency-based, and physio-chemical property-based sequence descriptors using the five most widely used machine learning classifiers. Further, it explores the performance impact of K-order sequence descriptor fusion where it ensembles similar as well dissimilar genres of statistical representation learning approaches to reap the combined benefits. Considering the diversity of statistical representation learning schemes, it assesses the performance of second-order, third-order, and going all the way up to seventh-order sequence descriptor fusion. A comprehensive empirical evaluation of Circ-LocNet over a newly developed benchmark dataset using different settings reveals that standalone residue frequency-based sequence descriptors and tree-based classifiers are more suitable to predict sub-cellular localization of circular RNAs. Further, K-order heterogeneous sequence descriptors fusion in combination with tree-based classifiers most accurately predict sub-cellular localization of circular RNAs. We anticipate this study will act as a rich baseline and push the development of robust computational methodologies for the accurate sub-cellular localization determination of novel circRNAs.

Discovering functional motifs in long noncoding RNAs

Long noncoding RNAs (lncRNAs) are products of pervasive transcription that closely resemble messenger RNAs on the molecular level, yet function through largely unknown modes of action. The current model is that the function of lncRNAs often relies on specific, typically short, conserved elements, connected by linkers in which specific sequences and/or structures are less important. This notion has fueled the development of both computational and experimental methods focused on the discovery of functional elements within lncRNA genes, based on diverse signals such as evolutionary conservation, predicted structural elements, or the ability to rescue loss-of-function phenotypes. In this review, we outline the main challenges that the different methods need to overcome, describe the recently developed approaches, and discuss their respective limitations. This article is categorized under: RNA Evolution and Genomics > Computational Analyses of RNA RNA Interactions with Proteins and Other Molecules > Protein-RNA Interactions: Functional Implications Regulatory RNAs/RNAi/Riboswitches > Regulatory RNAs.

TACOS: a novel approach for accurate prediction of cell-specific long noncoding RNAs subcellular localization

Long noncoding RNAs (lncRNAs) are primarily regulated by their cellular localization, which is responsible for their molecular functions, including cell cycle regulation and genome rearrangements. Accurately identifying the subcellular location of lncRNAs from sequence information is crucial for a better understanding of their biological functions and mechanisms. In contrast to traditional experimental methods, bioinformatics or computational methods can be applied for the annotation of lncRNA subcellular locations in humans more effectively. In the past, several machine learning-based methods have been developed to identify lncRNA subcellular localization, but relevant work for identifying cell-specific localization of human lncRNA remains limited. In this study, we present the first application of the tree-based stacking approach, TACOS, which allows users to identify the subcellular localization of human lncRNA in 10 different cell types. Specifically, we conducted comprehensive evaluations of six tree-based classifiers with 10 different feature descriptors, using a newly constructed balanced training dataset for each cell type. Subsequently, the strengths of the AdaBoost baseline models were integrated via a stacking approach, with an appropriate tree-based classifier for the final prediction. TACOS displayed consistent performance in both the cross-validation and independent assessments compared with the other two approaches employed in this study. The user-friendly online TACOS web server can be accessed at https://balalab-skku.org/TACOS.

Identification of LOC101927355 as a Novel Biomarker for Preeclampsia

Preeclampsia, a disorder with a heterogeneous physiopathology, can be attributed to maternal, fetal, and/or placental factors. Long non-coding RNAs (lncRNAs) refer to a class of non-coding RNAs, the essential regulators of biological processes; their differential expression has been associated with the pathogenesis of multiple diseases. The study aimed to identify lncRNAs, expressed in the placentas and plasma of patients who presented with preeclampsia, as potential putative biomarkers of the disease. In silico analysis was performed to determine lncRNAs differentially expressed in the placentas of patients with preeclampsia, using a previously published RNA-Seq dataset. Seven placentas and maternal plasma samples collected at delivery from preterm preeclamptic patients (≤37 gestational weeks of gestation), and controls were used to validate the expression of lncRNAs by qRT-PCR. Six lncRNAs were validated and differentially expressed (p < 0.05) in the preeclampsia and control placentas: UCA1 and HCG4 were found upregulated, and LOC101927355, LINC00551, PART1, and NRAD1 downregulated. Two of these lncRNAs, HCG4 and LOC101927355, were also detected in maternal plasma, the latter showing a significant decrease (p = 0.03) in preeclamptic patients compared to the control group. In silico analyses showed the cytoplasmic location of LOC101927355, which suggests a role in post-transcriptional gene regulation. The detection of LOC101927355 in the placenta and plasma opens new possibilities for understanding the pathogenesis of preeclampsia and for its potential use as a biomarker.

Comprehensive Analysis of lncRNA Expression Profile and the Potential Role of ENST00000604491 in Graves’ Disease

Background. Graves’ disease (GD) is one of the most common autoimmune diseases worldwide and develops in 20 to 50 cases per 100,000 persons annually. Long noncoding RNAs (lncRNAs) are widely expressed in multiple human diseases and have pivotal functions in gene regulation. This study is aimed at determining the lncRNA profile in peripheral blood mononuclear cells (PBMCs) from GD patients and investigating the role of ENST00000604491 in GD. Methods. A total of 31 GD patients and 32 normal controls were enrolled in the study. Next-generation sequencing was performed to identify the dysregulated lncRNAs in the PBMCs from the 5 GD patients and 5 normal controls, and 26 GD patients and 27 controls were used to verify the selected lncRNAs. The relative expression of verified lncRNAs, forkhead box P1 (FOXP1), and IKAROS family zinc finger 3 (IKZF3) from these samples was detected by quantitative real-time PCR. The potential biomarker value was assessed by using receiver operating characteristic (ROC) curve analysis. Results. A total of 37,683 dysregulated expressed lncRNAs were indicated, of which 5 lncRNAs were significantly upregulated and 83 lncRNAs were remarkably downregulated in the GD patients compared with healthy subjects. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses showed that abnormally expressed lncRNAs were mainly enriched in immune system-related signalling pathways. Among the selected lncRNAs, the relative expression of ENST00000604491 was significantly downregulated and negatively correlated with the serum levels of thyroid-stimulating hormone receptor antibodies (TRAb) in GD patients. Further studies confirmed that decreased FOXP1 expression was inversely correlated with serum TRAb levels in GD patients. Moreover, there was a notably positive correlation between ENST00000604491 expression and FOXP1 transcript levels in GD. The area under the ROC curve of ENST00000604491 was up to 0.74 (95% confidence interval: 0.60-0.87, $p<0.01$ ), and the sensitivity and specificity were 53.85% and 88.89%, respectively. Conclusion. The present study identifies ENST00000604491 as a significantly attenuated lncRNA in GD patients, which may contribute to the pathogenesis of GD by regulating FOXP1 and represent a potential biomarker for GD.

Long Non-Coding RNAs in Pancreatic Cancer: Biologic Functions, Mechanisms, and Clinical Significance

Despite tremendous efforts devoted to research in pancreatic cancer (PC), the mechanism underlying the tumorigenesis and progression of PC is still not completely clear. Additionally, ideal biomarkers and satisfactory therapeutic strategies for clinical application in PC are still lacking. Accumulating evidence suggests that long non-coding RNAs (lncRNAs) might participate in the pathogenesis of diverse cancers, including PC. The abnormal expression of lncRNAs in PC is considered a vital factor during tumorigenesis that affects tumor cell proliferation, migration, invasion, apoptosis, angiogenesis, and drug resistance. With this review of relevant articles published in recent years, we aimed to summarize the biogenesis mechanism, classifications, and modes of action of lncRNAs and to review the functions and mechanisms of lncRNAs in PC. Additionally, the clinical significance of lncRNAs in PC was discussed. Finally, we pointed out the questions remaining from recent studies and anticipated that further investigations would address these gaps in knowledge in this field.

Prediction of RNA-protein interactions using a nucleotide language model

Motivation

The accumulation of sequencing data has enabled researchers to predict the interactions between RNA sequences and RNA-binding proteins (RBPs) using novel machine learning techniques. However, existing models are often difficult to interpret and require additional information to sequences. Bidirectional encoder representations from transformer (BERT) is a language-based deep learning model that is highly interpretable. Therefore, a model based on BERT architecture can potentially overcome such limitations.

Results

Here, we propose BERT-RBP as a model to predict RNA-RBP interactions by adapting the BERT architecture pretrained on a human reference genome. Our model outperformed state-of-the-art prediction models using the eCLIP-seq data of 154 RBPs. The detailed analysis further revealed that BERT-RBP could recognize both the transcript region type and RNA secondary structure only based on sequence information. Overall, the results provide insights into the fine-tuning mechanism of BERT in biological contexts and provide evidence of the applicability of the model to other RNA-related problems.

Availability and implementation

Python source codes are freely available at https://github.com/kkyamada/bert-rbp. The datasets underlying this article were derived from sources in the public domain: [RBPsuite (http://www.csbio.sjtu.edu.cn/bioinf/RBPsuite/), Ensembl Biomart (http://asia.ensembl.org/biomart/martview/)].

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Machine and Deep Learning for Prediction of Subcellular Localization

Protein subcellular localization prediction (PSLP), which plays an important role in the field of computational biology, identifies the position and function of proteins in cells without expensive cost and laborious effort. In the past few decades, various methods with different algorithms have been proposed in solving the problem of subcellular localization prediction; machine learning and deep learning constitute a large portion among those proposed methods. In order to provide an overview about those methods, the first part of this article will be a brief review of several state-of-the-art machine learning methods on subcellular localization prediction; then the materials used by subcellular localization prediction is described and a simple prediction method, that takes protein sequences as input and utilizes a convolutional neural network as the classifier, is introduced. At last, a list of notes is provided to indicate the major problems that may occur with this method.

Illuminating lncRNA Function Through Target Prediction

Most of the transcribed human genome codes for noncoding RNAs (ncRNAs), and long noncoding RNAs (lncRNAs) make for the lion's share of the human ncRNA space. Despite growing interest in lncRNAs, because there are so many of them, and because of their tissue specialization and, often, lower abundance, their catalog remains incomplete and there are multiple ongoing efforts to improve it. Consequently, the number of human lncRNA genes may be lower than 10,000 or higher than 200,000. A key open challenge for lncRNA research, now that so many lncRNA species have been identified, is the characterization of lncRNA function and the interpretation of the roles of genetic and epigenetic alterations at their loci. After all, the most important human genes to catalog and study are those that contribute to important cellular functions-that affect development or cell differentiation and whose dysregulation may play a role in the genesis and progression of human diseases. Multiple efforts have used screens based on RNA-mediated interference (RNAi), antisense oligonucleotide (ASO), and CRISPR screens to identify the consequences of lncRNA dysregulation and predict lncRNA function in select contexts, but these approaches have unresolved scalability and accuracy challenges. Instead-as was the case for better-studied ncRNAs in the past-researchers often focus on characterizing lncRNA interactions and investigating their effects on genes and pathways with known functions. Here, we focus most of our review on computational methods to identify lncRNA interactions and to predict the effects of their alterations and dysregulation on human disease pathways.

RT-qPCR as a screening platform for mutational and small molecule impacts on structural stability of RNA tertiary structures

The exponential increase in the discovery and characterization of RNA tertiary structures has highlighted their active role in a variety of human diseases, yet often their interactome and specific function remain unknown. Small molecules offer opportunities to both decode these cellular roles and develop therapeutics, however there are few examples of small molecules that target biologically relevant RNA tertiary structures. While RNA triple helices are a particularly attractive target, discovery of triple helix modulators has been hindered by the lack of correlation between small molecule affinity and effect on structural modulation, thereby limiting the utility of affinity-based screening as a primary filtering method. To address this challenge, we developed a high-throughput RT-qPCR screening platform that reports on the effect of mutations and additives, such as small molecules, on the stability of triple helices. Using the 3′-end of the oncogenic long non-coding RNA MALAT1 as a proof-of-concept, we demonstrated the applicability of both a two-step and a one-pot method to assess the impact of mutations and small molecules on the stability of the triple helix. We demonstrated the adaptability of the assay to diverse RNA tertiary structures by applying it to the SARS-CoV-2 pseudoknot, a key viral RNA structure recently identified as an attractive therapeutic target for the development of antivirals. Employment of a functional high-throughput assay as a primary screen will significantly expedite the discovery of probes that modulate the structural landscape of RNA structures and, consequently, help gain insight into the roles of these pervasive structures.

RT-qPCR can be harnessed as a small molecule screening platform to read out the effect of small molecules on the structural stability of a variety of RNA targets.

Class similarity network for coding and long non-coding RNA classification

BACKGROUND

Long non-coding RNAs (lncRNAs) play significant roles in varieties of physiological and pathological processes.The premise of the lncRNA functional study is that the lncRNAs are identified correctly. Recently, deep learning method like convolutional neural network (CNN) has been successfully applied to identify the lncRNAs. However, the traditional CNN considers little relationships among samples via an indirect way.

RESULTS

Inspired by the Siamese Neural Network (SNN), here we propose a novel network named Class Similarity Network in coding RNA and lncRNA classification. Class Similarity Network considers more relationships among input samples in a direct way. It focuses on exploring the potential relationships between input samples and samples from both the same class and the different classes. To achieve this, Class Similarity Network trains the parameters specific to each class to obtain the high-level features and represents the general similarity to each class in a node. The comparison results on the validation dataset under the same conditions illustrate the superiority of our Class Similarity Network to the baseline CNN. Besides, our method performs effectively and achieves state-of-the-art performances on two test datasets.

CONCLUSIONS

We construct Class Similarity Network in coding RNA and lncRNA classification, which is shown to work effectively on two different datasets by achieving accuracy, precision, and F1-score as 98.43%, 0.9247, 0.9374, and 97.54%, 0.9990, 0.9860, respectively.

Prediction of RNA subcellular localization: Learning from heterogeneous data sources

RNA subcellular localization has recently emerged as a widespread phenomenon, which may apply to the majority of RNAs. The two main sources of data for characterization of RNA localization are sequence features and microscopy images, such as obtained from single-molecule fluorescent in situ hybridization-based techniques. Although such imaging data are ideal for characterization of RNA distribution, these techniques remain costly, time-consuming, and technically challenging. Given these limitations, imaging data exist only for a limited number of RNAs. We argue that the field of RNA localization would greatly benefit from complementary techniques able to characterize location of RNA. Here we discuss the importance of RNA localization and the current methodology in the field, followed by an introduction on prediction of location of molecules. We then suggest a machine learning approach based on the integration between imaging localization data and sequence-based data to assist in characterization of RNA localization on a transcriptome level.

Predicting subcellular location of protein with evolution information and sequence-based deep learning

BACKGROUND

Protein subcellular localization prediction plays an important role in biology research. Since traditional methods are laborious and time-consuming, many machine learning-based prediction methods have been proposed. However, most of the proposed methods ignore the evolution information of proteins. In order to improve the prediction accuracy, we present a deep learning-based method to predict protein subcellular locations.

RESULTS

Our method utilizes not only amino acid compositions sequence but also evolution matrices of proteins. Our method uses a bidirectional long short-term memory network that processes the entire protein sequence and a convolutional neural network that extracts features from protein sequences. The position specific scoring matrix is used as a supplement to protein sequences. Our method was trained and tested on two benchmark datasets. The experiment results show that our method yields accurate results on the two datasets with an average precision of 0.7901, ranking loss of 0.0758 and coverage of 1.2848.

CONCLUSION

The experiment results show that our method outperforms five methods currently available. According to those experiments, we can see that our method is an acceptable alternative to predict protein subcellular location.

DeepLncLoc: a deep learning framework for long non-coding RNA subcellular localization prediction based on subsequence embedding

Long non-coding RNAs (lncRNAs) are a class of RNA molecules with more than 200 nucleotides. A growing amount of evidence reveals that subcellular localization of lncRNAs can provide valuable insights into their biological functions. Existing computational methods for predicting lncRNA subcellular localization use k-mer features to encode lncRNA sequences. However, the sequence order information is lost by using only k-mer features. We proposed a deep learning framework, DeepLncLoc, to predict lncRNA subcellular localization. In DeepLncLoc, we introduced a new subsequence embedding method that keeps the order information of lncRNA sequences. The subsequence embedding method first divides a sequence into some consecutive subsequences and then extracts the patterns of each subsequence, last combines these patterns to obtain a complete representation of the lncRNA sequence. After that, a text convolutional neural network is employed to learn high-level features and perform the prediction task. Compared with traditional machine learning models, popular representation methods and existing predictors, DeepLncLoc achieved better performance, which shows that DeepLncLoc could effectively predict lncRNA subcellular localization. Our study not only presented a novel computational model for predicting lncRNA subcellular localization but also introduced a new subsequence embedding method which is expected to be applied in other sequence-based prediction tasks. The DeepLncLoc web server is freely accessible at http://bioinformatics.csu.edu.cn/DeepLncLoc/, and source code and datasets can be downloaded from https://github.com/CSUBioGroup/DeepLncLoc.

Advances in Computational Methodologies for Classification and Sub-Cellular Locality Prediction of Non-Coding RNAs

Apart from protein-coding Ribonucleic acids (RNAs), there exists a variety of non-coding RNAs (ncRNAs) which regulate complex cellular and molecular processes. High-throughput sequencing technologies and bioinformatics approaches have largely promoted the exploration of ncRNAs which revealed their crucial roles in gene regulation, miRNA binding, protein interactions, and splicing. Furthermore, ncRNAs are involved in the development of complicated diseases like cancer. Categorization of ncRNAs is essential to understand the mechanisms of diseases and to develop effective treatments. Sub-cellular localization information of ncRNAs demystifies diverse functionalities of ncRNAs. To date, several computational methodologies have been proposed to precisely identify the class as well as sub-cellular localization patterns of RNAs). This paper discusses different types of ncRNAs, reviews computational approaches proposed in the last 10 years to distinguish coding-RNA from ncRNA, to identify sub-types of ncRNAs such as piwi-associated RNA, micro RNA, long ncRNA, and circular RNA, and to determine sub-cellular localization of distinct ncRNAs and RNAs. Furthermore, it summarizes diverse ncRNA classification and sub-cellular localization determination datasets along with benchmark performance to aid the development and evaluation of novel computational methodologies. It identifies research gaps, heterogeneity, and challenges in the development of computational approaches for RNA sequence analysis. We consider that our expert analysis will assist Artificial Intelligence researchers with knowing state-of-the-art performance, model selection for various tasks on one platform, dominantly used sequence descriptors, neural architectures, and interpreting inter-species and intra-species performance deviation.

LINC00473 downregulation facilitates trophoblast cell migration and invasion via the miR-15a-5p/LITAF axis in pre-eclampsia

More and more evidence has identified that long non-coding RNAs (lncRNAs) are involved in various biological process of numerous diseases. It has been reported that long intergenic non-protein coding RNA 473 (LINC00473) was associated with pre-eclampsia (PE) development. However, role and molecular mechanism of LINC00473 in PE remains elusive. Therefore, we designed this research to figure out the specific biological function of LINC00473 in trophoblasts. Firstly, we testified expressions of LINC00473 in trophoblasts of PE with RT-qPCR analysis. Then, to probe biological function of LINC00473 in trophoblasts of PE, CCK-8 assay, trans-well assays and western blot analysis were conducted in Wish and JAR cells. As for verifying interaction of microRNA-15a-5p (miR-15a-5p) and LINC00473 or lipopolysaccharide induced TNF factor (LITAF), RNA pull-down and luciferase reporter assays were carried out. Finally, rescue experiments were conducted to probe regulatory pattern of the LINC00473/miR-15a-5p/LITAF axis in trophoblasts of PE. As a result, LINC00473 presented a significant upregulation in trophoblasts of PE. Moreover, LINC00473 knockdown induced trophoblast viability, migration, invasion, and epithelial-to-mesenchymal transition (EMT) in trophoblasts. Additionally, miR-15a-5p interacted with LINC00473 and miR-15a-5p was negatively regulated by LINC00473 in trophoblasts. Simultaneously, miR-15a-5p negatively modulated LITAF in trophoblasts. Moreover, LITAF overexpression or miR-15a-5p downregulation reversed the promotive impact of silenced LINC00473 on trophoblast viability, migration, invasion and EMT. In conclusion, LINC00473 regulated migration and invasion in trophoblasts via the miR-15a-5p/LITAF axis. Our study may provide a novel insight for clinical treatment of PE.

Role of mammalian long non-coding RNAs in normal and neuro oncological disorders

Long non-coding RNAs (lncRNAs) are expressed at lower levels than protein-coding genes but have a crucial role in gene regulation. LncRNA is distinct, they are being transcribed using RNA polymerase II, and their functionality depends on subcellular localization. Depending on their niche, they specifically interact with DNA, RNA, and proteins and modify chromatin function, regulate transcription at various stages, forms nuclear condensation bodies and nucleolar organization. lncRNAs may also change the stability and translation of cytoplasmic mRNAs and hamper signaling pathways. Thus, lncRNAs affect the physio-pathological states and lead to the development of various disorders, immune responses, and cancer. To date, ~40% of lncRNAs have been reported in the nervous system (NS) and are involved in the early development/differentiation of the NS to synaptogenesis. LncRNA expression patterns in the most common adult and pediatric tumor suggest them as potential biomarkers and provide a rationale for targeting them pharmaceutically. Here, we discuss the mechanisms of lncRNA synthesis, localization, and functions in transcriptional, post-transcriptional, and other forms of gene regulation, methods of lncRNA identification, and their potential therapeutic applications in neuro oncological disorders as explained by molecular mechanisms in other malignant disorders.

GLIDR promotes the progression of glioma by regulating the miR-4677-3p/MAGI2 axis

Gliomas are the most common and fatal primary brain tumors. Growing evidence suggests that long non-coding RNAs (lncRNAs) constitute novel and potential therapeutic targets for glioma. However, the biological role of glioblastoma down-regulated RNA (GLIDR) in glioma remains largely elusive. In the current study, we used quantitative real-time polymerase chain reaction (qRT-PCR) to detect GLIDR expression in glioma cells. Cell counting kit 8 (CCK-8) assay, colony formation assay, JC-1 staining, and flow cytometry were used to evaluate the role of GLIDR in proliferation and apoptosis of glioma cells. Western blotting was performed to assess the effect of GLIDR on the level of apoptosis-related proteins. In addition, bioinformatics prediction, RNA immunoprecipitation (RIP), RNA pull-down, and luciferase reporter gene assays were used to study the regulatory mechanisms of GLIDR in glioma. GLIDR was found to be highly expressed in glioma cells and silencing of GLIDR inhibited cell proliferation and promoted apoptosis. Functionally, GLIDR bound to miR-4677-3p that directly targeted membrane-associated guanylate kinase, WW, and PDZ domain-containing protein 2 (MAGI2). Our data showed that GLIDR affects the proliferation and apoptosis of glioma cells by targeting miR-4677-3p to regulate the expression of MAGI2. In conclusion, our study determined the oncogenic role of GLIDR in glioma, which may provide a new perspective for the treatment of glioma.

Oocyte specific lncRNA variant Rose influences oocyte and embryo development

Fully grown mammalian oocytes store a large amount of RNA synthesized during the transcriptionally active growth stage. A large part of the stored RNA belongs to the long non-coding class which contain either transcriptional noise or important contributors to cellular physiology. Despite the expanding number of studies related to lncRNAs, their influence on oocyte physiology remains enigmatic. We found an oocyte specific antisense, long non-coding RNA, "Rose" (lncRNA in Oocyte Specifically Expressed) expressed in two variants containing two and three non-coding exons, respectively. Rose is localized in the nucleus of transcriptionally active oocyte and in embryo with polysomal occupancy in the cytoplasm. Experimental overexpression of Rose in fully grown oocyte did not show any differences in meiotic maturation. However, knocking down Rose resulted in abnormalities in oocyte cytokinesis and impaired preimplantation embryo development. In conclusion, we have identified an oocyte-specific maternal lncRNA that is essential for successful mammalian oocyte and embryo development.

Long Non-Coding RNA (lncRNA) Roles in Cell Biology, Neurodevelopment and Neurological Disorders

Development is a complex process regulated both by genetic and epigenetic and environmental clues. Recently, long non-coding RNAs (lncRNAs) have emerged as key regulators of gene expression in several tissues including the brain. Altered expression of lncRNAs has been linked to several neurodegenerative, neurodevelopmental and mental disorders. The identification and characterization of lncRNAs that are deregulated or mutated in neurodevelopmental and mental health diseases are fundamental to understanding the complex transcriptional processes in brain function. Crucially, lncRNAs can be exploited as a novel target for treating neurological disorders. In our review, we first summarize the recent advances in our understanding of lncRNA functions in the context of cell biology and then discussing their association with selected neuronal development and neurological disorders.

A novel lincRNA identified in buffalo oocytes with protein binding characteristics could hold the key for oocyte competence

Studying the maternal oocyte-specific genes, in farm animals is a significant step towards delineating the underlying mechanisms that regulate oocyte quality, early embryonic development and survival. With the creation of buffalo oocyte-specific subtracted cDNA library, it has raised new questions which need to be answered. The present study has characterized one of the ESTs selected from the library and highlighted its importance in the oocyte quality. The selected EST was made full length by RLM-RACE and four transcript variants were identified. Bioinformatics analysis indicated the novelty of full-length transcript along with conserved intergenic nature. The largest transcript was identified as long intergenic noncoding RNA based upon coding potential calculator output. The expression analysis at different hours of oocyte maturation showed a significant variation in developmentally competent oocytes to that of incompetent ones. Along with this, the transcript was also found to have protein binding ability which was confirmed by RNA electrophoretic mobility shift assay. The protein used in the experiment was isolated from oocyte and cumulus cells via sonication. A novel lincRNA has been reported here that might have an important role in maturation of oocytes, inferred from its relative gene expression study and protein binding characteristics.

Cis-acting: A pattern of lncRNAs for gene regulation in induced pluripotent stem cells from patients with Down syndrome determined by integrative analysis of lncRNA and mRNA profiling data

Down syndrome (DS), caused by the trisomy of chromosome 21, is one of the common chromosomal disorders, the main clinical manifestations of which are delayed nervous development and intellectual disability. Long non-coding RNAs (lncRNAs) have critical roles in various biological processes, including cell growth, cell cycle regulation and differentiation. The roles of abnormally expressed lncRNAs have been previously reported; however, the biological functions and regulatory patterns of lncRNAs in DS have remained largely elusive. The aim of the present study was to perform a whole-genome-wide identification of lncRNAs and mRNAs associated with DS. In addition, global expression profiling analysis of DS-induced pluripotent stem cells was performed and differentially expressed (DE) lncRNAs and mRNAs were screened. Furthermore, the target genes and functions of the DE lncRNAs were predicted using Gene Ontology annotation and Kyoto Encyclopedia of Genes and Genomes signaling pathway enrichment analysis. The results revealed that the majority of the lncRNAs exerted functions in DS via cis-acting target genes. In addition, the results of the enrichment analysis indicated that these target genes were mainly involved in nervous and muscle development in DS. In conclusion, this integrative analysis using lncRNA and mRNA profiling provided novel insight into the pathogenesis of DS and it may promote the diagnosis and development of novel therapeutics for this disease.