The lncLocator: a subcellular localization predictor for long non-coding RNAs based on a stacked ensemble classifier

An ensemble learning method combined with multiple feature representation strategies to predict lncRNA subcellular localizations

Long non-coding RNAs (lncRNAs) are strongly associated with cellular physiological mechanisms and implicated in the numerous diseases. By exploring the subcellular localizations of lncRNAs, we can not only gain crucial insights into the molecular mechanisms of lncRNA-related biological processes but also make valuable contributions towards the diagnosis, prevention, and treatment of various human diseases. However, conventional experimental techniques tend to be laborious and time-intensive. In this context, computational methods are in increased demand. The focus of this paper is the development of an innovative ensemble method that incorporates hybrid features to accurately predict the subcellular localizations of lncRNAs. To address the issue of incomplete reflection of inherent correlation with the intended target using singular source features, the utilization of heterogeneous multi-source features is implemented by introducing information on sequence composition, physicochemical properties, and structure. To address the issue of the imbalance classes in the benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is employed. Finally, the resulting predictor termed lncSLPre is developed by integrating the outputs of the individual classifiers. Experimental findings suggest that the complementarity of multi-source heterogeneous features improves prediction performance. Additionally, it is demonstrated that the application of SMOTE is effective in mitigating the issue of the imbalanced dataset, while the feature selection approach is critical in eliminating extraneous and redundant features. Compared with existing advanced methods, lncSLPre achieves better performance with an overall accuracy improvement of 13.13%, 2.15%, and 3.23%, respectively, indicating that lncSLPre can effectively predict lncRNA subcellular localizations.

Decoding subcellular RNA localization one molecule at a time

Eukaryotic cells are highly structured and composed of multiple membrane-bound and membraneless organelles. Subcellular RNA localization is a critical regulator of RNA function, influencing various biological processes. At any given moment, RNAs must accurately navigate the three-dimensional subcellular environment to ensure proper localization and function, governed by numerous factors, including splicing, RNA stability, modifications, and localizing sequences. Aberrant RNA localization can contribute to the development of numerous diseases. Here, we explore diverse RNA localization mechanisms and summarize advancements in methods for determining subcellular RNA localization, highlighting imaging techniques transforming our ability to study RNA dynamics at the single-molecule level.

CFPLncLoc: A multi-label lncRNA subcellular localization prediction based on Chaos game representation and centralized feature pyramid

There is increasing evidence that the subcellular localization of long noncoding RNAs (lncRNAs) can provide valuable insights into their biological functions. In terms of transcriptomes, lncRNAs were usually found in multiple subcellular localizations. Although several computational methods have been developed to predict the subcellular localization of lncRNAs, few of them were designed for lncRNAs that have multiple subcellular localizations. In this study, we propose a novel deep learning model, called CFPLncLoc, which uses chaos game representation (CGR) images of lncRNA sequences to predict multi-label lncRNA subcellular localization. CFPLncLoc utilizes image update strategy (IUS) to enhance the relative feature representation of the CGR images. To extract higher-level features from CGR images, CFPLncLoc introduces the multi-scale feature fusion (MFF) model, centralized feature pyramid (CFP), from the field of computer vision (CV). Ablation studies confirmed the contribution of the IUS and CFP in improving the prediction performance. Statistical test results verify that CFPLncLoc outperforms existing state-of-the-art predictors under the evaluation metric MaAUC on the hold-out/independent test set. The source code can be obtained from https://github.com/ShengWang-XTU/CFPLncLoc.

Pan-cancer analysis of Methyltransferase-like 16 (METTL16) and validated in colorectal cancer

Human Methyltransferase-like 16(METTL16) is an independent N6-methyladenosine (m6A) methyltransferase. Previous studies have proven METTL16 been linked with some types of cancers. However, comparative studies of the relevance of METTL16 across diverse tumors remain sparse. We comprehensively investigated the effect of METTL16 expression on tumor prognosis across human malignancies by analyzing multiple cancer-related databases like Tumor Immune Estimation Resource (TIMER) and human protein atlas (HPA). Bioinformatics data indicated that METTL16 was overexpressed in most of these human malignancies and was significantly associated with the prognosis of patients with cancer, especially in colorectal cancer (CRC). Subsequently, In vitro experiments, the utility of METTL16 that downregulation of its expression could result in reduced proliferation and migration of CRC cells. Our findings reveal novel insights into METTL16 expression and its biological functions in diverse cancer types, indicating that METTL16 could serve as a prognostic biomarker and plays an important role in colorectal cancer.

An ensemble deep learning framework for multi-class LncRNA subcellular localization with innovative encoding strategy

BACKGROUND

Long non-coding RNA (LncRNA) play pivotal roles in various cellular processes, and elucidating their subcellular localization can offer crucial insights into their functional significance. Accurate prediction of lncRNA subcellular localization is of paramount importance. Despite numerous computational methods developed for this purpose, existing approaches still encounter challenges stemming from the complexity of data representation and the difficulty in capturing nucleotide distribution information within sequences.

RESULTS

In this study, we propose a novel deep learning-based model, termed MGBLncLoc, which incorporates a unique multi-class encoding technique known as generalized encoding based on the Distribution Density of Multi-Class Nucleotide Groups (MCD-ND). This encoding approach enables more precise reflection of nucleotide distributions, distinguishing between constant and discriminative regions within sequences, thereby enhancing prediction performance. Additionally, our deep learning model integrates advanced neural network modules, including Multi-Dconv Head Transposed Attention, Gated-Dconv Feed-forward Network, Convolutional Neural Network, and Bidirectional Gated Recurrent Unit, to comprehensively exploit sequence features of lncRNA.

CONCLUSIONS

Comparative analysis against commonly used sequence feature encoding methods and existing prediction models validates the effectiveness of MGBLncLoc, demonstrating superior performance. This research offers novel insights and effective solutions for predicting lncRNA subcellular localization, thereby providing valuable support for related biological investigations.

Circular RNA encoded by PPARG in the peripheral blood and a lipopolysaccharide-induced cardiomyocyte inflammation model is identified as a marker of fulminant myocarditis

BACKGROUND

Fulminant myocarditis (FM), a critical cardiac disease, is characterised by atypical initial symptoms and rapid progression and tends to lead to cardiomyocyte degeneration or necrosis. Reliable biological markers for FM screening remain lacking. Circular RNAs (circRNAs) are highly stable in peripheral blood due to their special closed-loop structure, and reports have described their involvement in regulating inflammatory responses and cell injury in cardiomyocytes. This study attempted to identify the abnormal expression of circRNAs in the peripheral blood of patients with FM and to evaluate the potential diagnostic value.

METHODS

Peripheral blood was collected from 5 children with FM and 5 sex- and age-matched healthy controls; total RNA was extracted from each sample, and the extracted RNA from each group was pooled. After RNase R treatment, high-throughput sequencing was performed to screen for differentially expressed circRNAs in the peripheral blood of patients. Biological function classification and enrichment analysis were used to explore the main action pathways involving differentially expressed circRNAs. A lipopolysaccharide (LPS)-induced cardiomyocyte inflammation model was used to explore the effect of inflammation on the expression of these dysregulated circRNAs. Receiver operating characteristic (ROC) curves were used to evaluate the potential clinical value of FM-related circRNAs as biomarkers in a large sample of patients.

RESULTS

CircRNA expression profiling of peripheral blood samples from patients revealed 6,435 and 3,678 circRNAs with upregulated and downregulated expression, respectively, compared with healthy controls. The expression of 1,749 circRNAs did not significantly differ between the groups. GO and KEGG analysis revealed that the genes encoding the dysregulated circRNAs were associated with various biological functions related to the risk of FM development, including infectious diseases, the immune system, and signal transduction. The high expression of hsa_circ_0064338 (circ_PPARG) was confirmed in both the myocardial cell inflammation model and peripheral blood from a large sample of FM patients. ROC curve analysis showed that the level of circ_PPARG in peripheral blood had a good ability to distinguish patients with FM from healthy controls.

CONCLUSIONS

Large numbers of abnormally regulated circRNAs were identified in peripheral blood from patients with FM; among these, the highly expressed circ_PPARG could distinguish patients from healthy controls to a certain extent. It is expected to become a potential clinical biomarker of FM in the future.

Regulatory mechanism of LncRNA GAS5 in cognitive dysfunction induced by sevoflurane anesthesia in neonatal rats

BACKGROUND AND OBJECTIVES

Sevoflurane (Sev) exposure may provoke deleterious effects on cognitive function. This study explores the mechanism of long non-coding RNA growth arrest specific transcript 5 (LncRNA GAS5) in Sev-induced cognitive dysfunction in neonatal rats.

METHODS

Cognitive dysfunction was induced by Sev anesthesia in 7-day-old Sprague-Dawley rats, followed by open field test, novel object recognition, radial arm maze, and Morris water maze to evaluate cognitive function of rats. The subcellular localization of LncRNA GAS5 was detected by nucleocytoplasmic isolation assay, and the binding of miR-137 to LncRNA GAS5 and NKCC1 was detected by RNA pull down and dual-luciferase reporter assay, respectively. Adenovirus-packaged sh-LncRNA GAS5 was injected into the hippocampus of Sev rats. qRT-PCR and Western blot were performed to detect the expressions of LncRNA GAS5, miR-137 and NKCC1 in the hippocampus of rats.

RESULTS

Sev anesthesia led to cognitive dysfunction in neonatal rats. LncRNA GAS5 was highly expressed in Sev rats, and inhibition of LncRNA GAS5 alleviated Sev-induced cognitive dysfunction in rats. LncRNA GAS5 targeted miR-137, and miR-137 inhibited NKCC1 expression. Knockdown of miR-137 or overexpression of NKCC1 reversed the effect of LncRNA GAS5 inhibition on cognitive dysfunction in sev rats.

CONCLUSION

LncRNA GAS5 promotes Sev-induced cognitive dysfunction in neonatal rats via the miR-137/NKCC1 axis.

MVSLLnc: LncRNA subcellular localization prediction based on multi-source features and two-stage voting strategy

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding the function of lncRNAs. Since the traditional biological experimental methods are time-consuming and some existing computational methods rely on high computing power, we are committed to finding a simple and easy-to-implement method to achieve more efficient prediction of the subcellular localization of lncRNAs. In this work, we proposed a model based on multi-source features and two-stage voting strategy for predicting the subcellular localization of lncRNAs (MVSLLnc). The multi-source features include k-mer frequency, features based on the coordinate values of Chaos Game Representation (CGR) and features based on physicochemical property (PhyChe). We feed the multi-source features into the traditional machine learning classifiers RF, SVM and XGBoost, respectively, and perform the final prediction task with two-stage voting strategy. Experimental results on three benchmark datasets show that the accuracy can reach 0.829, 0.793 and 0.968, respectively. The accuracy on three independent test sets is 0.642, 0.737 and 0.518, respectively, which are competitive with the existing methods. Our ablation analyses show that the two-stage voting strategy can make full use of the advantages of multi-source features and multiple classifiers, and obtain more robust results.

Hypoxia induced cellular and exosomal RPPH1 promotes breast cancer angiogenesis and metastasis through stabilizing the IGF2BP2/FGFR2 axis

Metastasis is the major cause of breast cancer mortality, with angiogenesis and tumor-released exosomes playing key roles. However, the communication between breast cancer cells and endothelial cells and its role in tumor metastasis remains unclear. Here, we characterize a long noncoding RNA, RPPH1, which is upregulated in breast cancer tissues and positively associated with poor prognosis. Hypoxia microenvironment upregulates the expression of RPPH1 in breast cancer cells, and promotes its packaging into exosomes through hnRNPA1, leading to the maintenance of stemness and aggressive traits in cancer cells and angiogenesis in endothelial cells. The function of cellular and exosomal RPPH1 was confirmed in the MMTV-PyMT mouse model, in which ASO-RPPH1 therapy effectively inhibited tumor progression and metastasis. Mechanistically, RPPH1 protects IGF2BP2 from ubiquitination-induced degradation, stabilizes N6-methyladenosine (m6A)-modified FGFR2 mRNA, and activates the PI3K/AKT pathway. Our research unveils the role of RPPH1 in breast cancer metastasis and highlights its potential as a therapeutic target.

RNALocate v3.0: Advancing the Repository of RNA Subcellular Localization with Dynamic Analysis and Prediction

Subcellular localization of RNA is a crucial mechanism for regulating diverse biological processes within cells. Dynamic RNA subcellular localizations are essential for maintaining cellular homeostasis; however, their distribution and changes during development and differentiation remain largely unexplored. To elucidate the dynamic patterns of RNA distribution within cells, we have upgraded RNALocate to version 3.0, a repository for RNA-subcellular localization (http://www.rnalocate.org/ or http://www.rna-society.org/rnalocate/). RNALocate v3.0 incorporates and analyzes RNA subcellular localization sequencing data from over 850 samples, with a specific focus on the dynamic changes in subcellular localizations under various conditions. The species coverage has also been expanded to encompass mammals, non-mammals, plants and microbes. Additionally, we provide an integrated prediction algorithm for the subcellular localization of seven RNA types across eleven subcellular compartments, utilizing convolutional neural networks (CNNs) and transformer models. Overall, RNALocate v3.0 contains a total of 1 844 013 RNA-localization entries covering 26 RNA types, 242 species and 177 subcellular localizations. It serves as a comprehensive and readily accessible data resource for RNA-subcellular localization, facilitating the elucidation of cellular function and disease pathogenesis.

The potential of long non-coding RNAs for motor function recovery after spinal cord injury in rodents: A systematic review and meta-analysis

OBJECTIVE

Long non-coding RNAs (LncRNAs) have garnered significant attention in preclinical studies for their potential in treating spinal cord injury (SCI). This meta-analysis aimed to assess the overall efficacy of lncRNA treatments in improving motor function in rodent models of SCI.

METHODS

The Embase, PubMed, Web of Science, and Scopus databases were searched. Meta-analysis was performed using STATA 14.0. The standardized mean difference (SMD) was employed to combine various motor function scores.

RESULTS

A total of 33 studies were included in this review. Key findings indicated that lncRNA treatments could markedly enhance locomotor function in rodents with SCI compared to control groups (SMD = 4.20, 95% CI: 3.35 to 5.05, I2 = 80.0%, P < 0.0001). Furthermore, in male rats with contusion/compression injuries, targeting specific cytosol-enriched lncRNAs to downregulate their expression may significantly improve motor function recovery. Specifically, intrathecal injection of non-viral vectors for lncRNA delivery proved to be the most effective method in this study.

CONCLUSIONS

LncRNA treatments have demonstrated the potential to improve motor function in rodent models with SCI. However, the therapeutic efficacy may be overestimated. Future research should rigorously assess the clinical translational efficacy and safety of lncRNA treatments.

LncRNA MSTRG.14227.1 regulates the morphogenesis of secondary hair follicles in Inner Mongolia cashmere goats via targeting ADAMTS3 by sponging chi-miR-433

The cashmere goat is a type of livestock primarily known for its cashmere. Cashmere has a soft hand feel and good luster. It is a vital raw material in the textile industry, possessing significant economic value. Improving the yield and quality of cashmere can accelerate the development of the cashmere industry and increase the incomes of farmers and herdsmen. The embryonic stage is the main stage of the formation of hair follicle structure, which directly affects the yield and quality of cashmere. With the rapid advancements in modern molecular technology and high-throughput sequencing, many signaling molecules have been identified as playing critical roles in hair follicle development. Long non-coding RNA (lncRNA), which lacks protein-coding ability and exceeds 200 nucleotides in length, has been discovered to play a role in hair follicle development. In this study, the lncRNA MSTRG.14227.1, which is associated with the morphogenesis of secondary hair follicles, was screened and identified based on previously established lncRNA expression profiles derived from skin tissues of cashmere goats at different embryonic stages. This lncRNA has been shown to inhibit the proliferation and migration of dermal fibroblasts. Furthermore, we confirmed through bioinformatics analysis and dual-luciferase reporter assays that lncRNA MSTRG.14227.1 can function as a sponge for chi-miR-433, thereby alleviating the inhibitory effect of chi-miR-433 on its target gene ADAMTS3. In conclusion, the results of this study suggest that lncRNA MSTRG.14227.1 can inhibit the morphogenesis of secondary hair follicles through the chi-miR-433/ADAMTS3 signaling axis.

BiGM-lncLoc: Bi-level Multi-Graph Meta-Learning for Predicting Cell-Specific Long Noncoding RNAs Subcellular Localization

The precise spatiotemporal expression of long noncoding RNAs (lncRNAs) plays a pivotal role in biological regulation, and aberrant expression of lncRNAs in different subcellular localizations has been intricately linked to the onset and progression of a variety of cancers. Computational methods provide effective means for predicting lncRNA subcellular localization, but current studies either ignore cell line and tissue specificity or the correlation and shared information among cell lines. In this study, we propose a novel approach, BiGM-lncLoc, treating the prediction of lncRNA subcellular localization across cell lines as a multi-graph meta-learning task. Our investigation involves two categories of data: the localization data of nucleotide sequences in different cell lines and cell line expression data. BiGM-lncLoc comprises a cell line-specific optimization network learning specific knowledge from cell line expression data and a graph neural network optimized across cell lines. Subsequently, the specific and shared knowledge acquired through bi-level optimization is applied to a new cell-line prediction task without the need for re-training or fine-tuning. Additionally, through key feature analysis of the impact of different nucleotide combinations on the model, we confirm the necessity of cell line-specific studies based on correlation analysis. Finally, experiments conducted on various cell lines with different data sizes indicate that BiGM-lncLoc outperforms other methods in terms of prediction accuracy, with an average accuracy of 97.7%. After removing overlapping samples to ensure data independence for each cell line, the accuracy ranged from 82.4% to 94.7%, still surpassing existing models. Our code can be found at https://github.com/BioCL1/BiGM-lncLoc .

LncSL: A Novel Stacked Ensemble Computing Tool for Subcellular Localization of lncRNA by Amino Acid-Enhanced Features and Two-Stage Automated Selection Strategy

Long non-coding RNA (lncRNA) is a non-coding RNA longer than 200 nucleotides, crucial for functions like cell cycle regulation and gene transcription. Accurate localization prediction from sequence information is vital for understanding lncRNA's biological roles. Computational methods offer an effective alternative to traditional experimental methods for annotating lncRNA subcellular positions. Existing machine learning-based methods are limited and often overlook regions with coding potential that affect the function of lncRNA. Therefore, we propose a new model called LncSL. For feature encoding, both lncRNA sequences and amino acid sequences from open reading frames (ORFs) are employed. And we selected the most suitable features by CatBoost and integrated them into a new feature set. Additionally, a voting process with seven feature selection algorithms identified the higher contributive features for training our final stacked model. Additionally, an automatic model selection strategy is constructed to find a better performance meta-model for assembling LncSL. This study specifically focuses on predicting the subcellular localization of lncRNA in the nucleus and cytoplasm. On two benchmark datasets called S1 and S2 datasets, LncSL outperformed existing methods by 6.3% to 12.3% in the Matthew's correlation coefficient on a balanced test dataset. On an unbalanced independent test dataset sourced from S1, LncSL improved by 4.7% to 18.6% in the Matthew's correlation coefficient, which further demonstrates that LncSL is superior to other compared methods. In all, this study presents an effective method for predicting lncRNA subcellular localization through enhancing sequence information, which is always overlooked by traditional methods, and addressing contributive meta-model selection problems, which can offer new insights for other bioinformatics problems.

Ovine LncRSFD1 Mined from RNA-Seq: Identification, Expression Profile, Promotion of Preadipocyte Differentiation, Promoter Activity, and Its Polymorphisms Related to Phenotypic Traits

Tail fat is essential for sheep survival in extreme environments, yet its significance is often overlooked, leading to the decline of fat-tailed breeds. This study identified a novel lncRNA, lncRSFD1 (TCONS_00054953), through transcriptome sequencing, showing differential expression in the tail adipose tissues of Lanzhou Fat-Tailed (LFT) sheep and Tibetan (TS) sheep. Highly expressed in adipose tissues, lncRSFD1 inhibits preadipocyte proliferation and promotes 3T3-L1 differentiation, suggesting its role in regulating fat deposition. Located in both the cytoplasm and nucleus, lncRSFD1 targets the neighboring gene PDE4DIP and may function as a molecular sponge for conserved miRNAs, including oar-miR-30a-3p, oar-miR-329b-5p, and oar-miR-431, which are known to influence fat and muscle-related physiological processes. Moreover, the core promoter of lncRSFD1 (-2607 bp to -1776 bp) harbors four SNPs (g.-2429G>A, g.-2030T>C, g.-2016C>T, g.-2015G>A) significantly associated with growth traits such as body height in Guiqian Semi-Fine Wool (GSFW) sheep. These findings suggest lncRSFD1 plays a key role in fat deposition and growth regulation, offering new insights into the molecular mechanisms of lncRNAs in sheep. It provides a potential target for genetic improvement and molecular breeding to enhance fat deposition and adaptability in sheep breeds.

Insights into lncRNA-mediated regulatory networks in Hevea brasiliensis under anthracnose stress

In recent years, long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) have emerged as critical regulators in plant biology, governing complex gene regulatory networks. In the context of disease resistance in Hevea brasiliensis, the rubber tree, significant progress has been made in understanding its response to anthracnose disease, a serious threat posed by fungal pathogens impacting global rubber tree cultivation and latex quality. While advances have been achieved in unraveling the genetic and molecular foundations underlying anthracnose resistance, gaps persist in comprehending the regulatory roles of lncRNAs and miRNAs under such stress conditions. The specific contributions of these non-coding RNAs in orchestrating molecular responses against anthracnose in H. brasiliensis remain unclear, necessitating further exploration to uncover strategies that increase disease resistance. Here, we integrate lncRNA sequencing, miRNA sequencing, and degradome sequencing to decipher the regulatory landscape of lncRNAs and miRNAs in H. brasiliensis under anthracnose stress. We investigated the genomic and regulatory profiles of differentially expressed lncRNAs (DE-lncRNAs) and constructed a competitive endogenous RNA (ceRNA) regulatory network in response to pathogenic infection. Additionally, we elucidated the functional roles of HblncRNA29219 and its antisense hbr-miR482a, as well as the miR390-TAS3-ARF pathway, in enhancing anthracnose resistance. These findings provide valuable insights into plant-microbe interactions and hold promising implications for advancing agricultural crop protection strategies. This comprehensive analysis sheds light on non-coding RNA-mediated regulatory mechanisms in H. brasiliensis under pathogen stress, establishing a foundation for innovative approaches aimed at enhancing crop resilience and sustainability in agriculture.

Uncovering the ceRNA Network Related to the Prognosis of Stomach Adenocarcinoma Among 898 Patient Samples

Stomach adenocarcinoma (STAD) patients are often associated with significantly high mortality rates and poor prognoses worldwide. Among STAD patients, competing endogenous RNAs (ceRNAs) play key roles in regulating one another at the post-transcriptional stage by competing for shared miRNAs. In this study, we aimed to elucidate the roles of lncRNAs in the ceRNA network of STAD, uncovering the molecular biomarkers for target therapy and prognosis. Specifically, a multitude of differentially expressed lncRNAs, miRNAs, and mRNAs (i.e., 898 samples in total) was collected and processed from TCGA. Cytoplasmic lncRNAs were kept for evaluating overall survival (OS) time and constructing the ceRNA network. Differentially expressed mRNAs in the ceRNA network were also investigated for functional and pathological insights. Interestingly, we identified one ceRNA network including 13 lncRNAs, 25 miRNAs, and 9 mRNAs. Among them, 13 RNAs were found related to the patient survival time; their individual risk score can be adopted for prognosis inference. Finally, we constructed a comprehensive ceRNA regulatory network for STAD and developed our own risk-scoring system that can predict the OS time of STAD patients by taking into account the above.

GP-HTNLoc: A graph prototype head-tail network-based model for multi-label subcellular localization prediction of ncRNAs

Numerous research results demonstrated that understanding the subcellular localization of non-coding RNAs (ncRNAs) is pivotal in elucidating their roles and regulatory mechanisms in cells. Despite the existence of over ten computational models dedicated to predicting the subcellular localization of ncRNAs, a majority of these models are designed solely for single-label prediction. In reality, ncRNAs often exhibit localization across multiple subcellular compartments. Furthermore, the existing multi-label localization prediction models are insufficient in addressing the challenges posed by the scarcity of training samples and class imbalance in ncRNA dataset. To address these limitations, this study proposes a novel multi-label localization prediction model for ncRNAs, named GP-HTNLoc. To mitigate class imbalance, GP-HTNLoc adopts separate training approaches for head and tail location labels. Additionally, GP-HTNLoc introduces a pioneering graph prototype module to enhance its performance in small-sample, multi-label scenarios. The experimental results based on 10-fold cross-validation on benchmark datasets demonstrate that GP-HTNLoc achieves competitive predictive performance. The average results from 10 rounds of testing on an independent dataset show that GP-HTNLoc outperforms the best existing models on the human lncRNA, human snoRNA, and human miRNA subsets, with average precision improvements of 31.5%, 14.2%, and 5.6%, respectively, reaching 0.685, 0.632, and 0.704. A user-friendly online GP-HTNLoc server is accessible at https://56s8y85390.goho.co.

E74-like factor 4 promotes the proliferation, invasion, and migration of colorectal cancer cells via long non-coding RNA integrin subunit beta 8 antisense RNA 1-mediated histone H3 lysine 27 trimethylation modification

AIM

Colorectal cancer (CRC) is a common malignancy in the gastrointestinal tract. The main objective of this study is to explore the potential mechanisms of E74-like factor 4 (ELF4) in CRC progression, providing a novel therapeutic target for CRC treatment.

METHODS

CRC cells and normal control cells were cultured. Levels of ELF4/long non-coding RNA integrin subunit beta 8 antisense RNA 1 (LncRNA ITGB8-AS1)/claudin-23 (CLDN23) were detected by real-time quantitative polymerase chain reaction or Western blot assay. ELF4 siRNA, ITGB8-AS1 pcDNA3.1, or CLDN23 siRNA were transfected into cells. Cell proliferation, migration, and invasion were evaluated. The enrichment of ELF4 on the ITGB8-AS1 promoter was detected. Dual-luciferase assay was employed to assess the binding between ELF4 and the ITGB8-AS1 promoter. RNA pull-down and RNA immunoprecipitation assays were conducted to investigate the binding between ITGB8-AS1 and enhancer of zeste homolog 2 (EZH2). The binding of EZH2 and histone H3 lysine 27 trimethylation (H3K27me3) to the CLDN23 promoter was detected.

RESULTS

ELF4 and ITGB8-AS1 were upregulated in CRC cells, while CLDN23 was downregulated. Knockdown of ELF4 inhibited cell proliferation, invasion, and migration. Mechanistically, ELF4 transcriptionally activated ITGB8-AS1 and promoted the binding between ITGB8-AS1 and EZH2. EZH2 catalyzed H3K27me3 modification on the CLDN23 promoter, leading to decreased CLDN23 expression. Overexpression of ITGB8-AS1 or downregulation of CLDN23 could reduce the inhibitory effects of silencing ELF4 on CRC cell proliferation, migration, and invasion.

CONCLUSION

ELF4 accelerates CRC progression through the ITGB8-AS1/CLDN23 axis, providing new therapeutic targets for CRC.

Transcriptome Analysis Reveals the lncRNA-mRNA Co-expression Network Regulating the Aestivation of Sea Cucumber

LncRNAs are long non-coding RNAs that are widely recognized as crucial regulators of gene expression and metabolic control, involved in numerous dormancy-related processes. Aestivation is a common hypometabolism strategy of sea cucumber (Apostichopus japonicus) in response to high-temperature conditions and is typically characterized by the degradation of the intestine and respiratory tree. Although the aestivation process has been extensively studied in sea cucumbers, the role of lncRNAs in the context of aestivation states remains a conspicuous knowledge gap. Here, we identified and characterized 14,711 lncRNAs in A. japonicus and analyzed their differential expression patterns during the aestivation process in the intestine and respiratory tree. The results revealed the physiological differences, especially the metabolic processes, between the intestine and respiratory tree during the aestivation. The co-expression network of lncRNA-mRNA suggested the dominant role of lncRNA in regulating the differential response of the intestine and respiratory trees. Differentially co-expressed factors were significantly enriched in the deep-aestivation stage-specific modules. Conserved co-expressed factors included several transcription factors known to be involved in rhythm regulation, such as Klf2 and Egr1. Furthermore, a specific trans-acting lncRNA (lncrna.1393.1) was identified as a potential regulator of Klf2 and Egr1. Overall, the systematic identification, characterization, and expression analysis of lncRNAs in A. japonicus enhanced our knowledge of long non-coding regulation of aestivation in sea cucumber and provided new clues for understanding the common "toolkit" of dormancy regulatory mechanisms.

LncLSTA: a versatile predictor unveiling subcellular localization of lncRNAs through long-short term attention

Motivation

Much evidence suggests that the subcellular localization of long-stranded noncoding RNAs (LncRNAs) provides key insights for the study of their biological function.

Results

This study proposes a novel deep learning framework, LncLSTA, designed for predicting the subcellular localization of LncRNAs. It firstly exploits LncRNA sequence, electron-ion interaction pseudopotentials, and nucleotide chemical property as feature inputs. Departing from conventional k-mer approaches, this model uses a set of 1D convolutional and maxpooling operations for dynamical feature aggregation. Furthermore, LncLSTA integrates a long-short term attention module with a bidirectional long and short term memory network to comprehensively extract sequence information. In addition, it incorporates a TextCNN module to enhance accuracy and robustness in subcellular localization tasks. Experimental results demonstrate the efficacy of LncLSTA, showcasing its superior performance compared to other state-of-the-art methods. Notably, LncLSTA exhibits the transfer learning capability, extending its utility to predict the subcellular localization prediction of mRNAs, while maintaining consistently satisfactory prediction results. This research contributes valuable insights into understanding the biological functions of LncRNAs through subcellular localization, emphasizing the potential of deep learning approaches in advancing RNA-related studies.

Availability and implementation

The source code is publicly available at https://bis.zju.edu.cn/LncLSTA.

Methionine deprivation inhibits glioma proliferation and EMT via the TP53TG1/miR-96-5p/STK17B ceRNA pathway

Recent research highlights the significant impact of methionine metabolism on glioma progression. An increasing amount of compelling evidence bridges long non-coding RNAs to abnormal metabolism in gliomas. However, the specific role of long non-coding RNAs in methionine metabolism regulating glioma progression remains unclear. This study reveals that methionine deprivation inhibits the proliferation, migration, and invasion capabilities of gliomas. Interestingly, the expression of TP53TG1, a long non-coding RNA, is also suppressed. TP53TG1 is highly expressed in gliomas and associated with poor patient outcomes. Subsequently, our data proves that inhibition of TP53TG1 suppresses glioma cell proliferation and the epithelial-mesenchymal transition process both in vitro and in vivo. Ultimately, we found that the underlying mechanism involves a competing endogenous RNA regulating network, in which TP53TG1 modulates the target protein STK17B by competitively binding to miR-96-5p, thus regulating glioma progression. These findings suggest that targeting methionine deprivation could be a promising approach for the clinical treatment of glioma.

Integrated Biochemical and Computational Methods for Deciphering RNA-Processing Codes

RNA processing involves steps such as capping, splicing, polyadenylation, modification, and nuclear export. These steps are essential for transforming genetic information in DNA into proteins and contribute to RNA diversity and complexity. Many biochemical methods have been developed to profile and quantify RNAs, as well as to identify the interactions between RNAs and RNA-binding proteins (RBPs), especially when coupled with high-throughput sequencing technologies. With the rapid accumulation of diverse data, it is crucial to develop computational methods to convert the big data into biological knowledge. In particular, machine learning and deep learning models are commonly utilized to learn the rules or codes governing the transformation from DNA sequences to intriguing RNAs based on manually designed or automatically extracted features. When precise enough, the RNA codes can be incredibly useful for predicting RNA products, decoding the molecular mechanisms, forecasting the impact of disease variants on RNA processing events, and identifying driver mutations. In this review, we systematically summarize the biochemical and computational methods for deciphering five important RNA codes related to alternative splicing, alternative polyadenylation, RNA localization, RNA modifications, and RBP binding. For each code, we review the main types of experimental methods used to generate training data, as well as the key features, strategic model structures, and advantages of representative tools. We also discuss the challenges encountered in developing predictive models using large language models and extensive domain knowledge. Additionally, we highlight useful resources and propose ways to improve computational tools for studying RNA codes.

LncRNA (BCO1-AS) regulate inflammatory responses in bacterial infection through caspase-1 in turbot (Scophthalmus maximus)

LncRNA plays key role in several biological processes, including transcriptional regulation, post transcriptional control and epigenetic regulation. However, research on the functional roles of lncRNAs in teleost species remains limited. Here, we discovered a lncRNA (BCO1-AS) with a critical role in antibacterial responses. Briefly, the full length of BCO1-AS was 2005 bp. Subsequently, BCO1-AS was distributed throughout the nucleus, where it may either trans- or cis-regulate the nearby genes. In addition, BCO1-AS was widely expressed in all the examined tissues with the highest expression level in intestine, while the lowest expression level was detected in muscle. Moreover, following Vibrio anguillarum challenge, BCO1-AS was significantly down-regulated in intestine, and up-regulated in gill and skin. In CHIRP experiment, BCO1-AS could effectively enrich RNA and might interact with several immune-related genes. Furthermore, we found that LPS could induce the expression of BCO1-AS. Finally, BCO1-AS could positively regulate caspase-1 at the mRNA and protein level. The BCO1-AS was speculated to inhibit the synthesis of inflammatory components. In summary, these results showed the roles of BCO1-AS in the regulation of inflammatory in turbot, which provided valuable information for further understanding the immune regulation network of lncRNA in teleost fish.

Role of LncRNA MSTRG.20890.1 in Hair Follicle Development of Cashmere Goats

BACKGROUND

The cashmere goat is a biological resource that mainly produces cashmere. Cashmere has a soft hand feel and good luster, with high economic value. The quality and yield of cashmere are determined by the process of hair follicle development during the embryonic period.

METHODS

In this study, the skin of the Inner Mongolia cashmere goat at different embryonic stages (45, 55, 65, and 75d) was collected, and the differentially expressed lncRNA MSTRG.20890.1 at 75d was obtained by screening. Dual luciferase reporter gene system, qRT-PCR, and EDU experiments were used to verify further the regulatory role and molecular mechanism of the lncRNA in dermal fibroblasts.

RESULTS

Based on the transcriptome database of Inner Mongolia cashmere goat skin at different embryonic stages, which was previously constructed by our group, according to the characteristics of hair follicle development in the embryonic stage, we screened out the lncRNA MSTRG.20890.1 that was down-expressed on the 75-SHFINI day of the embryonic stage. We found that lncRNA MSTRG.20890.1 was mainly located in the cytoplasm of cells, and it could inhibit the proliferation and directional migration of dermal fibroblasts through the chi-miR-24-3p/ADAMTS3 signaling axis, thereby inhibiting the formation of dermal papilla structure at embryonic stage.

CONCLUSIONS

This study revealed that lncRNA MSTRG.20890.1 regulated secondary hair follicle morphogenesis and development in cashmere goats through the chi-miR-24-3p/ADAMTS3 signaling axis.

Dysregulation of the DRAIC/SBK1 Axis Promotes Lung Cancer Progression

Background: Long non-coding RNAs (lncRNAs) are key regulators of cellular processes that underpin cancer development and progression. DRAIC is a migration inhibitor that has been linked with lung adenocarcinoma progression; however, its mechanisms remain to be studied. Methods: Several bioinformatics tools were used to explore the role of DRAIC in lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC). Results: Our bioinformatics analysis illustrates that patients with low expression of DRAIC have poor overall survival outcomes. In addition, the mRNA of SH3 domain-binding kinase 1 (SBK1) was downregulated in this cohort of patients. Mechanistic analysis showed that SBK1 is under the DRAIC competing endogenous RNAs network, potentially through sponging of miRNA-92a. Conclusions: Consistent dysregulation of the DRAIC-SBK1 axis was linked to poor survival outcome in both LUAD and LUSC, suggesting a tumour inhibitor role and providing potential for new diagnostics and therapeutic approaches.

Evaluation of machine learning models that predict lncRNA subcellular localization

The lncATLAS database quantifies the relative cytoplasmic versus nuclear abundance of long non-coding RNAs (lncRNAs) observed in 15 human cell lines. The literature describes several machine learning models trained and evaluated on these and similar datasets. These reports showed moderate performance, e.g. 72-74% accuracy, on test subsets of the data withheld from training. In all these reports, the datasets were filtered to include genes with extreme values while excluding genes with values in the middle range and the filters were applied prior to partitioning the data into training and testing subsets. Using several models and lncATLAS data, we show that this 'middle exclusion' protocol boosts performance metrics without boosting model performance on unfiltered test data. We show that various models achieve only about 60% accuracy when evaluated on unfiltered lncRNA data. We suggest that the problem of predicting lncRNA subcellular localization from nucleotide sequences is more challenging than currently perceived. We provide a basic model and evaluation procedure as a benchmark for future studies of this problem.

Exhaustive Exploitation of Nature-Inspired Computation for Cancer Screening in an Ensemble Manner

Accurate screening of cancer types is crucial for effective cancer detection and precise treatment selection. However, the association between gene expression profiles and tumors is often limited to a small number of biomarker genes. While computational methods using nature-inspired algorithms have shown promise in selecting predictive genes, existing techniques are limited by inefficient search and poor generalization across diverse datasets. This study presents a framework termed Evolutionary Optimized Diverse Ensemble Learning (EODE) to improve ensemble learning for cancer classification from gene expression data. The EODE methodology combines an intelligent grey wolf optimization algorithm for selective feature space reduction, guided random injection modeling for ensemble diversity enhancement, and subset model optimization for synergistic classifier combinations. Extensive experiments were conducted across 35 gene expression benchmark datasets encompassing varied cancer types. Results demonstrated that EODE obtained significantly improved screening accuracy over individual and conventionally aggregated models. The integrated optimization of advanced feature selection, directed specialized modeling, and cooperative classifier ensembles helps address key challenges in current nature-inspired approaches. This provides an effective framework for robust and generalized ensemble learning with gene expression biomarkers.

A Holistic Analysis of Alzheimer's Disease-Associated lncRNA Communities Reveals Enhanced lncRNA-miRNA-RBP Regulatory Triad Formation Within Functionally Segregated Clusters

Recent studies on the regulatory networks implicated in Alzheimer's disease (AD) evince long non-coding RNAs (lncRNAs) as crucial regulatory players, albeit a poor understanding of the mechanism. Analyzing differential gene expression in the RNA-seq data from the post-mortem AD brain hippocampus, we categorized a list of AD-dysregulated lncRNA transcripts into functionally similar communities based on their k-mer profiles. Using machine-learning-based algorithms, their subcellular localizations were mapped. We further explored the functional relevance of each community through AD-dysregulated miRNA, RNA-binding protein (RBP) interactors, and pathway enrichment analyses. Further investigation of the miRNA-lncRNA and RBP-lncRNA networks from each community revealed the top RBPs, miRNAs, and lncRNAs for each cluster. The experimental validation community yielded ELAVL4 and miR-16-5p as the predominant RBP and miRNA, respectively. Five lncRNAs emerged as the top-ranking candidates from the RBP/miRNA-lncRNA networks. Further analyses of these networks revealed the presence of multiple regulatory triads where the RBP-lncRNA interactions could be augmented by the enhanced miRNA-lncRNA interactions. Our results advance the understanding of the mechanism of lncRNA-mediated AD regulation through their interacting partners and demonstrate how these functionally segregated but overlapping regulatory networks can modulate the disease holistically.

StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning

BACKGROUND

Antioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins.

METHODS

In this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model.

RESULTS

Our developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98.

CONCLUSION

Our proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

ARAP1-AS1: a novel long non-coding RNA with a vital regulatory role in human cancer development

Long non-coding RNAs (lncRNAs) have garnered significant attention in biomedical research due to their pivotal roles in gene expression regulation and their association with various human diseases. Among these lncRNAs, ArfGAP With RhoGAP Domain, Ankyrin Repeat, And PH Domain 1 - Antisense RNA 1 (ARAP1-AS1) has recently emerged as an novel oncogenic player. ARAP1-AS1 is prominently overexpressed in numerous solid tumors and wields influence by modulating gene expression and signaling pathways. This regulatory impact is realized through dual mechanisms, involving both competitive interactions with microRNAs and direct protein binding. ARAP1-AS1 assumes an important role in driving tumorigenesis and malignant tumor progression, affecting biological characteristics such as tumor expansion and metastasis. This paper provides a concise review of the regulatory role of ARAP1-AS1 in malignant tumors and discuss its potential clinical applications as a biomarker and therapeutic target. We also address existing knowledge gaps and suggest avenues for future research. ARAP1-AS1 serves as a prototypical example within the burgeoning field of lncRNA studies, offering insights into the broader landscape of non-coding RNA molecules. This investigation enhances our comprehension of the complex mechanisms that govern the progression of cancer.

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.

Puzzling out the role of MIAT LncRNA in hepatocellular carcinoma

A non-negligible part of our DNA has been proven to be transcribed into non-protein coding RNA and its intricate involvement in several physiological processes has been highly evidenced. The significant biological role of non-coding RNAs (ncRNAs), including long non-coding RNAs (lncRNAs) has been variously reported. In the current review, the authors highlight the multifaceted role of myocardial infarction-associated transcript (MIAT), a well-known lncRNA, in hepatocellular carcinoma (HCC). Since its discovery, MIAT has been described as a regulator of carcinogenesis in several malignant tumors and its overexpression predicts poor prognosis in most of them. At the molecular level, MIAT is closely linked to the initiation of metastasis, invasion, cellular migration, and proliferation, as evidenced by several in-vitro and in-vivo models. Thus, MIAT is considered a possible theranostic agent and therapeutic target in several malignancies. In this review, the authors provide a comprehensive overview of the underlying molecular mechanisms of MIAT in terms of its downstream target genes, interaction with other classes of ncRNAs, and potential clinical implications as a diagnostic and/or prognostic biomarker in HCC.

MulStack: An ensemble learning prediction model of multilabel mRNA subcellular localization

Subcellular localization of mRNA is related to protein synthesis, cell polarity, cell movement and other biological regulation mechanisms. The distribution of mRNAs in subcellulars is similar to that of proteins, and most mRNAs are distributed in multiple subcellulars. Recently, some computational methods have been designed to predict the subcellular localization of mRNA. However, these methods only employed a sin-gle level of mRNA features and did not employ the position encoding of nucleotides in mRNA. In this paper, an ensemble learning prediction model is proposed, named MulStack, which is based on random forest and deep learning for multilabel mRNA subcellular localization. The proposed method employs two levels of mRNA features, including sequence-level and residue-level features, and position encoding is employed for the first time in the field of subcellular localization of mRNA. Random forest is employed to learn mRNA sequence-level feature, deep learning is employed to learn mRNA sequence-level feature and mRNA residue-level combined with position encoding. And the outputs of random forest and deep learning model will be weighted sum as the prediction probability. Compared with existing methods, the results show that MulStack is the best in the localization of the nucleus, cytosol and exosome. In addition, position weight matrices (PWMs) are extracted by convolutional neural networks (CNNs) that can be matched with known RNA binding protein motifs. Gene ontology (GO) enrichment analysis shows biological processes, molecular functions and cellular components of mRNA genes. The prediction web server of MulStack is freely accessible at http://bliulab.net/MulStack.

Regulatory roles of long non-coding RNAs in short-term heat stress in adult worker bees

Long non-coding RNAs (lncRNAs) are crucial modulators of post-transcriptional gene expression regulation, cell fate determination, and disease development. However, lncRNA functions during short-term heat stress in adult worker bees are poorly understood. Here, we performed deep sequencing and bioinformatic analyses of honeybee lncRNAs. RNA interference was performed by using siRNA targeting the most highly expressed lncRNA. The silencing effect on lncRNA and the relative expression levels of seven heat shock protein (HSP) genes, were subsequently examined. Overall, 7,842 lncRNAs and 115 differentially expressed lncRNAs (DELs) were identified in adult worker bees following heat stress exposure. Structural analysis revealed that the overall expression abundance, length of transcripts, exon number, and open reading frames of lncRNAs were lower than those of mRNAs. GO analysis revealed that the target genes were mainly involved in "metabolism," "protein folding," "response to stress," and "signal transduction" pathways. KEGG analysis indicated that the "protein processing in endoplasmic reticulum" and "longevity regulating pathway-multiple species" pathways were most enriched. Quantitative real-time polymerase chain reaction (qRT-PCR) detection of the selected DELs confirmed the reliability of the sequencing data. Moreover, the siRNA experiment indicated that feeding siRNA yielded a silencing efficiency of 77.51% for lncRNA MSTRG.9645.5. Upon silencing this lncRNA, the expression levels of three HSP genes were significantly downregulated (p < 0.05), whereas those of three other HSP genes were significantly upregulated (p < 0.05). Our results provide a new perspective for understanding the regulatory mechanisms of lncRNAs in adult worker bees under short-term heat stress.

In silico genome wide identification of long non-coding RNAs differentially expressed during Candida auris host pathogenesis

Candida auris is an invasive fungal pathogen of high concern due to acquired drug tolerance against antifungals used in clinics. The prolonged persistence on biotic and abiotic surfaces can result in onset of hospital outbreaks causing serious health threat. An in depth understanding of pathology of C. auris is highly desirable for development of efficient therapeutics. Non-coding RNAs play crucial role in fungal pathology. However, the information about ncRNAs is scanty to be utilized. Herein our aim is to identify long noncoding RNAs with potent role in pathobiology of C. auris. Thereby, we analyzed the transcriptomics data of C. auris infection in blood for identification of potential lncRNAs with regulatory role in determining invasion, survival or drug tolerance under infection conditions. Interestingly, we found 275 lncRNAs, out of which 253 matched with lncRNAs reported in Candidamine, corroborating for our accurate data analysis pipeline. Nevertheless, we obtained 23 novel lncRNAs not reported earlier. Three lncRNAs were found to be under expressed throughout the course of infection, in the transcriptomics data. 16 of potent lncRNAs were found to be coexpressed with coding genes, emphasizing for their functional role. Noteworthy, these ncRNAs are expressed from intergenic regions of the genes associated with transporters, metabolism, cell wall biogenesis. This study recommends for possible association between lncRNA expression and C. auris pathogenesis.

ESPDHot: An Effective Machine Learning-Based Approach for Predicting Protein-DNA Interaction Hotspots

Protein-DNA interactions are pivotal to various cellular processes. Precise identification of the hotspot residues for protein-DNA interactions holds great significance for revealing the intricate mechanisms in protein-DNA recognition and for providing essential guidance for protein engineering. Aiming at protein-DNA interaction hotspots, this work introduces an effective prediction method, ESPDHot based on a stacked ensemble machine learning framework. Here, the interface residue whose mutation leads to a binding free energy change (ΔΔG) exceeding 2 kcal/mol is defined as a hotspot. To tackle the imbalanced data set issue, the adaptive synthetic sampling (ADASYN), an oversampling technique, is adopted to synthetically generate new minority samples, thereby rectifying data imbalance. As for molecular characteristics, besides traditional features, we introduce three new characteristic types including residue interface preference proposed by us, residue fluctuation dynamics characteristics, and coevolutionary features. Combining the Boruta method with our previously developed Random Grouping strategy, we obtained an optimal set of features. Finally, a stacking classifier is constructed to output prediction results, which integrates three classical predictors, Support Vector Machine (SVM), XGBoost, and Artificial Neural Network (ANN) as the first layer, and Logistic Regression (LR) algorithm as the second one. Notably, ESPDHot outperforms the current state-of-the-art predictors, achieving superior performance on the independent test data set, with F1, MCC, and AUC reaching 0.571, 0.516, and 0.870, respectively.

The SLC19A1-AS/miR-1343/WNT11 axis is a novel positive regulatory ceRNA network governing goat granulosa cell proliferation

Long noncoding RNAs (lncRNAs), as competitive endogenous RNAs (ceRNAs), can directly or indirectly affect the proliferation and apoptosis of granulosa cells by regulating microRNA (miRNA) pathways. A ceRNA network of the SLC19A1-AS-miR-1343-WNT11 axis was constructed via comprehensive transcriptome sequencing of ovaries from goats with various fertility levels to further elucidate the function and regulatory mechanism of SLC19A1-AS in modulating miR-1343 and WNT11 during granulosa cell proliferation and apoptosis. Subsequent validation experiments were conducted in vitro using granulosa cells. In these experiments, we performed RNA immunoprecipitation (RIP) and identified SLC19A1-AS as a ceRNA in goat granulosa cells that promoted proliferation. Through bioinformatics prediction, luciferase reporter gene assays, and RNA pulldown assays, we confirmed that SLC19A1-AS acts as a sponge for miR-1343, preventing its binding to WNT11 mRNA and thereby increasing the expression of WNT11. This interaction also influenced the proliferation and apoptosis of granulosa cells. Our study systematically validated the biological function of the lncRNA-miRNA-mRNA ceRNA network in goat ovaries and revealed the potential regulatory mechanism by which SLC19A1-AS functions as a ceRNA in granulosa cells. These findings are expected to provide an important experimental foundation for further elucidating the physiological regulatory network of the ovary and contributing to reproductive health in goats.

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.

Expression profiles and gene set enrichment analysis of the transcriptomes from the cancer tissue, white adipose tissue and paracancer tissue with colorectal cancer

Background

Colorectal cancer (CRC) is one of the most common cancers worldwide and is related to diet and obesity. Currently, crosstalk between lipid metabolism and CRC has been reported; however, the specific mechanism is not yet understood. In this study, we screened differentially expressed long non-coding RNAs (lncRNAs) and mRNAs from primary cancer, paracancer, and white adipose tissue of CRC patients. We screened and analyzed the genes differentially expressed between primary and paracancer tissue and between paracancer and white adipose tissue but not between primary and white adipose tissue. According to the results of the biological analysis, we speculated a lncRNA (MIR503HG) that may be involved in the crosstalk between CRC and lipid metabolism through exosome delivery.

Methods

We screened differentially expressed long non-coding RNAs (lncRNAs) and mRNAs from primary cancer, paracancer, and white adipose tissue of CRC patients. We screened and analyzed the genes differentially expressed between primary and paracancer tissue and between paracancer and white adipose tissue but not between primary and white adipose tissue.

Results

We speculated a lncRNA (MIR503HG) that may be involved in the crosstalk between CRC and lipid metabolism through exosome delivery.

Conclusions

In this study, the findings raise the possibility of crosstalk between lipid metabolism and CRC through the exosomal delivery of lncRNAs.

Ensemble learning for integrative prediction of genetic values with genomic variants

BACKGROUND

Whole genome variants offer sufficient information for genetic prediction of human disease risk, and prediction of animal and plant breeding values. Many sophisticated statistical methods have been developed for enhancing the predictive ability. However, each method has its own advantages and disadvantages, so far, no one method can beat others.

RESULTS

We herein propose an Ensemble Learning method for Prediction of Genetic Values (ELPGV), which assembles predictions from several basic methods such as GBLUP, BayesA, BayesB and BayesCπ, to produce more accurate predictions. We validated ELPGV with a variety of well-known datasets and a serious of simulated datasets. All revealed that ELPGV was able to significantly enhance the predictive ability than any basic methods, for instance, the comparison p-value of ELPGV over basic methods were varied from 4.853E-118 to 9.640E-20 for WTCCC dataset.

CONCLUSIONS

ELPGV is able to integrate the merit of each method together to produce significantly higher predictive ability than any basic methods and it is simple to implement, fast to run, without using genotype data. is promising for wide application in genetic predictions.

Predicting the incidence of infectious diarrhea with symptom surveillance data using a stacking-based ensembled model

BACKGROUND

Infectious diarrhea remains a major public health problem worldwide. This study used stacking ensemble to developed a predictive model for the incidence of infectious diarrhea, aiming to achieve better prediction performance.

METHODS

Based on the surveillance data of infectious diarrhea cases, relevant symptoms and meteorological factors of Guangzhou from 2016 to 2021, we developed four base prediction models using artificial neural networks (ANN), Long Short-Term Memory networks (LSTM), support vector regression (SVR) and extreme gradient boosting regression trees (XGBoost), which were then ensembled using stacking to obtain the final prediction model. All the models were evaluated with three metrics: mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE).

RESULTS

Base models that incorporated symptom surveillance data and weekly number of infectious diarrhea cases were able to achieve lower RMSEs, MAEs, and MAPEs than models that added meteorological data and weekly number of infectious diarrhea cases. The LSTM had the best prediction performance among the four base models, and its RMSE, MAE, and MAPE were: 84.85, 57.50 and 15.92%, respectively. The stacking ensembled model outperformed the four base models, whose RMSE, MAE, and MAPE were 75.82, 55.93, and 15.70%, respectively.

CONCLUSIONS

The incorporation of symptom surveillance data could improve the predictive accuracy of infectious diarrhea prediction models, and symptom surveillance data was more effective than meteorological data in enhancing model performance. Using stacking to combine multiple prediction models were able to alleviate the difficulty in selecting the optimal model, and could obtain a model with better performance than base models.

LINC00319: Unraveling the spectrum from gene regulation to clinical applications in cancer progression

LncRNAs are RNA transcripts that exceed 200 nucleotides in length and do not encode proteins. LINC00319 is a type of lncRNA that is highly expressed in various cancers and is regulated by CCL18 and MYC. High levels of LINC00319 are associated with poorer prognosis and more malignant clinical features in cancer patients. LINC00319 can regulate the expression of downstream genes, including 2 protein-coding genes and 11 miRNAs. It participates in controlling three signaling pathways and various cellular behaviors. LINC00319 and its downstream genes are potential targets for cancer therapy and are associated with common cancer treatments. This article reviews the abnormal expression of LINC00319 in human cancers and related molecular mechanisms, providing clues for further diagnosis and treatment.

Identification and Characterization of a ceRNA Regulatory Network Involving LINC00482 and PRRC2B in Peripheral Blood Mononuclear Cells: Implications for COPD Pathogenesis and Diagnosis

Purpose

Chronic obstructive pulmonary disease (COPD) is the third leading cause of death worldwide, characterized by intense lung infiltrations of immune cells (macrophages and monocytes). While existing studies have highlighted the crucial role of the competitive endogenous RNA (ceRNA) regulatory network in COPD development, the complexity and characteristics of the ceRNA network in monocytes remain unexplored.

Methods

We downloaded messenger RNA (mRNA), microRNA (miRNA), and long noncoding RNA (lncRNA) microarray data from GSE146560, GSE102915, and GSE71220 in the Gene Expression Omnibus (GEO) database. This data was used to identify differentially expressed mRNAs (DEmRNAs), miRNAs (DEmiRNAs), and lncRNAs (DElncRNAs). Predicted miRNAs that bind to DElncRNAs were intersected with DEmiRNAs, forming a set of intersecting miRNAs. This set was then used to predict potential binding mRNAs, intersected with DEmRNAs, and underwent functional enrichment analysis using R software and the STRING database. The resulting triple regulatory network and hub genes were constructed using Cytoscape. Comparative Toxicomics Database (CTD) was utilized for disease correlation predictions, and ROC curve analysis assessed diagnostic accuracy.

Results

Our study identified 5 lncRNAs, 4 miRNAs, and 149 mRNAs as differentially expressed. A lncRNA-miRNA-mRNA regulatory network was constructed, and hub genes were selected through hub analysis. Enrichment analysis highlighted terms related to cell movement and gene expression regulation. We established a LINC00482-has-miR-6088-PRRC2B ceRNA network with diagnostic relevance for COPD. ROC analysis demonstrated the diagnostic value of these genes. Moreover, a positive correlation between LINC00482 and PRRC2B expression was observed in COPD PBMCs. The CTD database indicated their involvement in inflammatory responses.

Conclusion

In summary, our study not only identified pivotal hub genes in peripheral blood mononuclear cells (PBMCs) of COPD but also constructed a ceRNA regulatory network. This contributes to understanding the pathophysiological processes of COPD through bioinformatics analysis, expanding our knowledge of COPD, and providing a foundation for potential diagnostic and therapeutic targets for COPD.

CTISL: a dynamic stacking multi-class classification approach for identifying cell types from single-cell RNA-seq data

MOTIVATION

Effective identification of cell types is of critical importance in single-cell RNA-sequencing (scRNA-seq) data analysis. To date, many supervised machine learning-based predictors have been implemented to identify cell types from scRNA-seq datasets. Despite the technical advances of these state-of-the-art tools, most existing predictors were single classifiers, of which the performances can still be significantly improved. It is therefore highly desirable to employ the ensemble learning strategy to develop more accurate computational models for robust and comprehensive identification of cell types on scRNA-seq datasets.

RESULTS

We propose a two-layer stacking model, termed CTISL (Cell Type Identification by Stacking ensemble Learning), which integrates multiple classifiers to identify cell types. In the first layer, given a reference scRNA-seq dataset with known cell types, CTISL dynamically combines multiple cell-type-specific classifiers (i.e. support-vector machine and logistic regression) as the base learners to deliver the outcomes for the input of a meta-classifier in the second layer. We conducted a total of 24 benchmarking experiments on 17 human and mouse scRNA-seq datasets to evaluate and compare the prediction performance of CTISL and other state-of-the-art predictors. The experiment results demonstrate that CTISL achieves superior or competitive performance compared to these state-of-the-art approaches. We anticipate that CTISL can serve as a useful and reliable tool for cost-effective identification of cell types from scRNA-seq datasets.

AVAILABILITY AND IMPLEMENTATION

The webserver and source code are freely available at http://bigdata.biocie.cn/CTISLweb/home and https://zenodo.org/records/10568906, respectively.

DeepLocRNA: an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning

MOTIVATION

Accurate prediction of RNA subcellular localization plays an important role in understanding cellular processes and functions. Although post-transcriptional processes are governed by trans-acting RNA binding proteins (RBPs) through interaction with cis-regulatory RNA motifs, current methods do not incorporate RBP-binding information.

RESULTS

In this article, we propose DeepLocRNA, an interpretable deep-learning model that leverages a pre-trained multi-task RBP-binding prediction model to predict the subcellular localization of RNA molecules via fine-tuning. We constructed DeepLocRNA using a comprehensive dataset with variant RNA types and evaluated it on the held-out dataset. Our model achieved state-of-the-art performance in predicting RNA subcellular localization in mRNA and miRNA. It has also demonstrated great generalization capabilities, performing well on both human and mouse RNA. Additionally, a motif analysis was performed to enhance the interpretability of the model, highlighting signal factors that contributed to the predictions. The proposed model provides general and powerful prediction abilities for different RNA types and species, offering valuable insights into the localization patterns of RNA molecules and contributing to our understanding of cellular processes at the molecular level. A user-friendly web server is available at: https://biolib.com/KU/DeepLocRNA/.

Identification and clinical value of a new ceRNA axis (TIMP3/hsa-miR-181b-5p/PAX8-AS1) in thyroid cancer

Background

Thyroid cancer (TC) is a prevalent and increasingly common malignant tumor. In most cases, TC progresses slowly and runs a virtually benign course. However, challenges remain with the treatment of refractory TC, which does not respond to traditional management or is subject to relapse or metastasis. Therefore, new therapeutic regimens for TC patients with poor outcomes are urgently needed.

Methods

The differentially expressed RNAs were identified from the expression profile data of RNA from TC downloaded from The Cancer Genome Atlas database. Multiple databases were utilized to investigate the regulatory relationship among RNAs. Subsequently, a competitive endogenous RNA (ceRNA) network was established to elucidate the ceRNA axis that is responsible for the clinical prognosis of TC. To understand the potential mechanism of ceRNA axis in TC, location analysis, functional enrichment analysis, and immune-related analysis were conducted.

Results

A ceRNA network of TC was constructed, and the TIMP3/hsa-miR-181b-5p/PAX8-AS1 ceRNA axis associated with the prognosis of TC was successfully identified. Our results showed that the axis might influence the prognosis of TC through its regulation of regulating tumor immunity.

Conclusions

Our findings provide evidence that TIMP3/hsa-miR-181b-5p/PAX8-AS1 axis is significantly related to the prognosis of TC. The molecules involved in this axis may serve as novel therapeutic approaches for TC treatment.

Epigenetic variation mediated by lncRNAs accounts for adaptive genomic differentiation of the endemic blue mussel Mytiluschilensis

Epigenetic variation affects gene expression without altering the underlying DNA sequence of genes controlling ecologically relevant phenotypes through different mechanisms, one of which is long non-coding RNAs (lncRNAs). This study identified and evaluated the gene expression of lncRNAs in the gill and mantle tissues of Mytilus chilensis individuals from two ecologically different sites: Cochamó (41°S) and Yaldad (43°S), southern Chile, both impacted by climatic-related conditions and by mussel farming given their use as seedbeds. Sequences identified as lncRNAs exhibited tissue-specific differences, mapping to 3.54 % of the gill transcriptome and 1.96 % of the mantle transcriptome, representing an average of 2.76 % of the whole transcriptome. Using a high fold change value (≥|100|), we identified 43 and 47 differentially expressed lncRNAs (DE-lncRNAs) in the gill and mantle tissue of individuals sampled from Cochamó and 21 and 17 in the gill and mantle tissue of individuals sampled from Yaldad. Location-specific DE-lncRNAs were also detected in Cochamó (65) and Yaldad (94) samples. Via analysis of the differential expression of neighboring protein-coding genes, we identified enriched GO terms related to metabolic, genetic, and environmental information processing and immune system functions, reflecting how the impact of local ecological conditions may influence the M. chilensis (epi)genome expression. These DE-lncRNAs represent complementary biomarkers to DNA sequence variation for maintaining adaptive differences and phenotypic plasticity to cope with natural and human-driven perturbations.

Unveiling dysregulated lncRNAs and networks in non-syndromic cleft lip with or without cleft palate pathogenesis

Non-syndromic cleft lip with or without cleft palate (NSCL/P) is a common congenital facial malformation with a complex, incompletely understood origin. Long noncoding RNAs (lncRNAs) have emerged as pivotal regulators of gene expression, potentially shedding light on NSCL/P's etiology. This study aimed to identify critical lncRNAs and construct regulatory networks to unveil NSCL/P's underlying molecular mechanisms. Integrating gene expression profiles from the Gene Expression Omnibus (GEO) database, we pinpointed 30 dysregulated NSCL/P-associated lncRNAs. Subsequent analyses enabled the creation of competing endogenous RNA (ceRNA) networks, lncRNA-RNA binding protein (RBP) interaction networks, and lncRNA cis and trans regulation networks. RT-qPCR was used to examine the regulatory networks of lncRNA in vivo and in vitro. Furthermore, protein levels of lncRNA target genes were validated in human NSCL/P tissue samples and murine palatal shelves. Consequently, two lncRNAs and three mRNAs: FENDRR (log2FC = - 0.671, P = 0.040), TPT1-AS1 (log2FC = 0.854, P = 0.003), EIF3H (log2FC = - 1.081, P = 0.041), RBBP6 (log2FC = 0.914, P = 0.037), and SRSF1 (log2FC = 0.763, P = 0.026) emerged as potential contributors to NSCL/P pathogenesis. Functional enrichment analyses illuminated the biological functions and pathways associated with these lncRNA-related networks in NSCL/P. In summary, this study comprehensively delineates the dysregulated transcriptional landscape, identifies associated lncRNAs, and reveals pivotal sub-networks relevant to NSCL/P development, aiding our understanding of its molecular progression and setting the stage for further exploration of lncRNA and mRNA regulation in NSCL/P.

Comprehensive non-coding RNA analysis reveals specific lncRNA/circRNA-miRNA-mRNA regulatory networks in the cotton response to drought stress

Root and leaf are essential organs of plants in sensing and responding to drought stress. However, comparative knowledge of non-coding RNAs (ncRNAs) of root and leaf tissues in the regulation of drought response in cotton is limited. Here, we used deep sequencing data of leaf and root tissues of drought-resistant and drought-sensitive cotton varieties for identifying miRNAs, lncRNAs and circRNAs. A total of 1531 differentially expressed (DE) ncRNAs was identified, including 77 DE miRNAs, 1393 DE lncRNAs and 61 DE circRNAs. The tissue-specific and variety-specific competing endogenous RNA (ceRNA) networks of DE lncRNA-miRNA-mRNA response to drought were constructed. Furthermore, the novel drought-responsive lncRNA 1 (DRL1), specifically and differentially expressed in root, was verified to positively affect phenotypes of cotton seedlings under drought stress, competitively binding to miR477b with GhNAC1 and GhSCL3. In addition, we also constructed another ceRNA network consisting of 18 DE circRNAs, 26 DE miRNAs and 368 DE mRNAs. Fourteen circRNA were characterized, and a novel molecular regulatory system of circ125- miR7484b/miR7450b was proposed under drought stress. Our findings revealed the specificity of ncRNA expression in tissue- and variety-specific patterns involved in the response to drought stress, and uncovered novel regulatory pathways and potentially effective molecules in genetic improvement for crop drought resistance.