RNA modifications and their role in gene expression

Post-transcriptional RNA modifications have recently emerged as critical regulators of gene expression programs. Understanding normal tissue development and disease susceptibility requires knowledge of the various cellular mechanisms which control gene expression in multicellular organisms. Research into how different RNA modifications such as in N6-methyladenosine (m6A), inosine (I), 5-methylcytosine (m5C), pseudouridine (Ψ), 5-hydroxymethylcytosine (hm5C), N1-methyladenosine (m1A), N6,2'-O-dimethyladenosine (m6Am), 2'-O-methylation (Nm), N7-methylguanosine (m7G) etc. affect the expression of genes could be valuable. This review highlights the current understanding of RNA modification, methods used to study RNA modification, types of RNA modification, and molecular mechanisms underlying RNA modification. The role of RNA modification in modulating gene expression in both physiological and diseased states is discussed. The potential applications of RNA modification in therapeutic development are elucidated.

Using statistical analysis to explore the influencing factors of data imbalance for machine learning identification methods of human transcriptome m6A modification sites

RNA methylation, particularly through m6A modification, represents a crucial epigenetic mechanism that governs gene expression and influences a range of biological functions. Accurate identification of methylation sites is crucial for understanding their biological functions. Traditional experimental methods, however, are often costly and can be influenced by experimental conditions, making machine learning, especially deep learning techniques, a vital tool for m6A site identification. Despite their utility, current machine learning models struggle with unbalanced datasets, a common issue in bioinformatics. This study addresses the RNA methylation site data imbalance problem from three key perspectives: feature encoding representation, deep learning models, and data resampling strategies. Using the K-mer one-hot encoding strategy, we effectively extracted RNA sequence features and developed classification prediction models utilizing long short-term memory networks (LSTM) and its variant, Multiplicative LSTM (mLSTM). We further enhanced model performance by ensemble and weighted strategy models. Additionally, we utilized the sequence generative adversarial network (SeqGAN) and the synthetic minority resampling technique (SMOTE) to construct balanced datasets for RNA methylation sites. The prediction results were rigorously analyzed using the Wilcoxon test and multivariate linear regression to explore the effects of different K-mer values, model architectures, and sampling methods on classification outcomes. The analysis underscored the significant impact of feature selection, model architecture, and sampling techniques in addressing data imbalance. Notably, the optimal prediction performance was achieved with a K value of 5 using the mLSTM-ensemble model. These findings not only offer new insights and methodologies for RNA methylation site identification but also provide valuable guidance for addressing similar challenges in bioinformatics.

MST-m6A: A Novel Multi-Scale Transformer-based Framework for Accurate Prediction of m6A Modification Sites Across Diverse Cellular Contexts

N6-methyladenosine (m6A) modification, a prevalent epigenetic mark in eukaryotic cells, is crucial in regulating gene expression and RNA metabolism. Accurately identifying m6A modification sites is essential for understanding their functions within biological processes and the intricate mechanisms that regulate them. Recent advances in high-throughput sequencing technologies have enabled the generation of extensive datasets characterizing m6A modification sites at single-nucleotide resolution, leading to the development of computational methods for identifying m6A RNA modification sites. However, most current methods focus on specific cell lines, limiting their generalizability and practical application across diverse biological contexts. To address the limitation, we propose MST-m6A, a novel approach for identifying m6A modification sites with higher accuracy across various cell lines and tissues. MST-m6A utilizes a multi-scale transformer-based architecture, employing dual k-mer tokenization to capture rich feature representations and global contextual information from RNA sequences at multiple levels of granularity. These representations are then effectively combined using a channel fusion mechanism and further processed by a convolutional neural network to enhance prediction accuracy. Rigorous validation demonstrates that MST-m6A significantly outperforms conventional machine learning models, deep learning models, and state-of-the-art predictors. We anticipate that the high precision and cross-cell-type adaptability of MST-m6A will provide valuable insights into m6A biology and facilitate advancements in related fields. The proposed approach is available at https://github.com/cbbl-skku-org/MST-m6A/ for prediction and reproducibility purposes.

Capturing short-range and long-range dependencies of nucleotides for identifying RNA N6-methyladenosine modification sites

N6-methyladenosine (m6A) plays a crucial role in enriching RNA functional and genetic information, and the identification of m6A modification sites is therefore an important task to promote the understanding of RNA epigenetics. In the identification process, current studies are mainly concentrated on capturing the short-range dependencies between adjacent nucleotides in RNA sequences, while ignoring the impact of long-range dependencies between non-adjacent nucleotides for learning high-quality representation of RNA sequences. In this work, we propose an end-to-end prediction model, called m6ASLD, to improve the identification accuracy of m6A modification sites by capturing the short-range and long-range dependencies of nucleotides. Specifically, m6ASLD first encodes the type and position information of nucleotides to construct the initial embeddings of RNA sequences. A self-correlation map is then generated to characterize both short-range and long-range dependencies with a designed map generating block for each RNA sequence. After that, m6ASLD learns the global and local representations of RNA sequences by using a graph convolution process and a designed dependency searching block respectively, and finally achieves its identification task under a joint training scheme. Extensive experiments have demonstrated the promising performance of m6ASLD on 11 benchmark datasets across several evaluation metrics.

METTL3‑mediated N6‑methyladenosine modification of MMP9 mRNA promotes colorectal cancer proliferation and migration

N6‑methyladenosine (m6A) is the predominant chemical modification of eukaryotic mRNA, dynamically mediated by the RNA methyltransferase, methyltransferase-like 3 (METTL3). m6A modification plays a critical role in cancer progression through post‑transcriptional regulation in various types of cancer. However, the role of METTL3 and its associated m6A modification in colorectal tumorigenesis remains to be fully elucidated. In the present study, it was demonstrated that METTL3 expression and the m6A levels were both upregulated in colorectal cancer (CRC) and positively associated with clinical progression, based on the bioinformatics analysis of cancer databases. Furthermore, knockdown and overexpression of METTL3 notably affected CRC cell viability, apoptosis and migration in vitro. Similarly, xenograft animal models confirmed that METTL3 promoted CRC tumorigenicity in vivo. Mechanistically, it was revealed that the m6A modification of matrix metallopeptidase 9 (MMP9) mRNA mediated by METTL3 promoted its expression in CRC by decreasing its degradation. Collectively, the findings of the present study suggested that the METTL3/MMP9 axis could serve as a novel promising therapeutic candidate for CRC.

AI techniques have facilitated the understanding of epitranscriptome distribution

N6-methyladenosine (m6A), the most prevalent internal mRNA modification in higher eukaryotes, plays diverse roles in cellular regulation. By incorporating both sequence- and genome-derived features, Fan et al.1 designed a novel Transformer-BiGRU framework that achieves superior performance in computational m6A identification, thus demonstrating the potential of AI in genomic studies.

A combined deep learning framework for mammalian m6A site prediction

N6-methyladenosine (m6A) is the most prevalent chemical modification in eukaryotic mRNAs and plays key roles in diverse cellular processes. Precise localization of m6A sites is thus critical for characterizing the functional roles of m6A in various conditions and dissecting the mechanisms governing its deposition. Here, we design a combined framework of Transformer architecture and recurrent neural network, deepSRAMP, to identify m6A sites using sequence-based and genome-derived features. As a result, deepSRAMP achieves a notably enhanced performance compared to its predecessor, SRAMP, the most-used predictor in this field. Moreover, based on multiple benchmark datasets, deepSRAMP greatly outperforms other state-of-the-art m6A predictors, including WHISTLE and DeepPromise, with an average 16.1% and 18.3% increase in AUROC and a 43.9% and 46.4% increase in AUPRC. Finally, deepSRAMP can be successfully exploited on mammalian m6A epitranscriptome mapping under diverse cellular conditions and can potentially reveal differential m6A sites among transcript isoforms of individual genes.

Domain-knowledge enabled ensemble learning of 5-formylcytosine (f5C) modification sites

5-formylcytidine (f5C) is a unique post-transcriptional RNA modification found in mRNA and tRNA at the wobble site, playing a crucial role in mitochondrial protein synthesis and potentially contributing to the regulation of translation. Recent studies have unveiled that the f5C modifications may drive mitochondrial mRNA translation to power cancer metastasis. Accurate identification of f5C sites is essential for further unraveling their molecular functions and regulatory mechanisms, but there are currently no computational methods available for predicting their locations. In this study, we introduce an innovative ensemble approach, successfully enabling the computational recognition of Saccharomyces cerevisiae f5C. We conducted a comprehensive model selection process that involved multiple basic machine learning and deep learning algorithms such as recurrent neural networks, convolutional neural networks and Transformer-based models. Initially trained only on sequence information, these individual models achieved an AUROC ranging from 0.7104 to 0.7492. Through the integration of 32 novel domain-derived genomic features, the performance of individual models has significantly improved to an AUROC between 0.7309 and 0.8076. To further enhance accuracy and robustness, we then constructed the ensembles of these individual models with different combinations. The best performance attained by our ensemble models reached an AUROC of 0.8391. Shapley additive explanations were conducted to explain the significant contributions of genomic features, providing insights into the putative distribution of f5C across various topological regions and potentially paving the way for revealing their functional relevance within distinct genomic contexts. A freely accessible web server that allows real-time analysis of user-uploaded sites can be accessed at: www.rnamd.org/Resf5C-Pred.

RNA-ModX: a multilabel prediction and interpretation framework for RNA modifications

Accurate prediction of RNA modifications holds profound implications for elucidating RNA function and mechanism, with potential applications in drug development. Here, the RNA-ModX presents a highly precise predictive model designed to forecast post-transcriptional RNA modifications, complemented by a user-friendly web application tailored for seamless utilization by future researchers. To achieve exceptional accuracy, the RNA-ModX systematically explored a range of machine learning models, including Long Short-Term Memory (LSTM), Gated Recurrent Unit, and Transformer-based architectures. The model underwent rigorous testing using a dataset comprising RNA sequences containing the four fundamental nucleotides (A, C, G, U) and spanning 12 prevalent modification classes (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um), with sequences of length 1001 nucleotides. Notably, the LSTM model, augmented with 3-mer encoding, demonstrated the highest level of model accuracy. Furthermore, Local Interpretable Model-Agnostic Explanations were employed to facilitate result interpretation, enhancing the transparency and interpretability of the model's predictions. In conjunction with the model development, a user-friendly web application was meticulously crafted, featuring an intuitive interface for researchers to effortlessly upload RNA sequences. Upon submission, the model executes in the backend, generating predictions which are seamlessly presented to the user in a coherent manner. This integration of cutting-edge predictive modeling with a user-centric interface signifies a significant step forward in facilitating the exploration and utilization of RNA modification prediction technologies by the broader research community.

PSATF-6mA: an integrated learning fusion feature-encoded DNA-6 mA methylcytosine modification site recognition model based on attentional mechanisms

DNA methylation is of crucial importance for biological genetic expression, such as biological cell differentiation and cellular tumours. The identification of DNA-6mA sites using traditional biological experimental methods requires more cumbersome steps and a large amount of time. The advent of neural network technology has facilitated the identification of 6 mA sites on cross-species DNA with enhanced efficacy. Nevertheless, the majority of contemporary neural network models for identifying 6 mA sites prioritize the design of the identification model, with comparatively limited research conducted on the statistically significant DNA sequence itself. Consequently, this paper will focus on the statistical strategy of DNA double-stranded features, utilising the multi-head self-attention mechanism in neural networks applied to DNA position probabilistic relationships. Furthermore, a new recognition model, PSATF-6 mA, will be constructed by continually adjusting the attentional tendency of feature fusion through an integrated learning framework. The experimental results, obtained through cross-validation with cross-species data, demonstrate that the PSATF-6 mA model outperforms the baseline model. The in-Matthews correlation coefficient (MCC) for the cross-species dataset of rice and m. musus genomes can reach a score of 0.982. The present model is expected to assist biologists in more accurately identifying 6 mA locus and in formulating new testable biological hypotheses.

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.

BLAM6A-Merge: Leveraging Attention Mechanisms and Feature Fusion Strategies to Improve the Identification of RNA N6-Methyladenosine Sites

RNA N6-methyladenosine is a prevalent and abundant type of RNA modification that exerts significant influence on diverse biological processes. To date, numerous computational approaches have been developed for predicting methylation, with most of them ignoring the correlations of different encoding strategies and failing to explore the adaptability of various attention mechanisms for methylation identification. To solve the above issues, we proposed an innovative framework for predicting RNA m6A modification site, termed BLAM6A-Merge. Specifically, it utilized a multimodal feature fusion strategy to combine the classification results of four features and Blastn tool. Apart from this, different attention mechanisms were employed for extracting higher-level features on specific features after the screening process. Extensive experiments on 12 benchmarking datasets demonstrated that BLAM6A-Merge achieved superior performance (average AUC: 0.849 for the full transcript mode and 0.784 for the mature mRNA mode). Notably, the Blastn tool was employed for the first time in the identification of methylation sites.

A hybrid residue based sequential encoding mechanism with XGBoost improved ensemble model for identifying 5-hydroxymethylcytosine modifications

RNA modifications play an important role in actively controlling recently created formation in cellular regulation mechanisms, which link them to gene expression and protein. The RNA modifications have numerous alterations, presenting broad glimpses of RNA's operations and character. The modification process by the TET enzyme oxidation is the crucial change associated with cytosine hydroxymethylation. The effect of CR is an alteration in specific biochemical ways of the organism, such as gene expression and epigenetic alterations. Traditional laboratory systems that identify 5-hydroxymethylcytosine (5hmC) samples are expensive and time-consuming compared to other methods. To address this challenge, the paper proposed XGB5hmC, a machine learning algorithm based on a robust gradient boosting algorithm (XGBoost), with different residue based formulation methods to identify 5hmC samples. Their results were amalgamated, and six different frequency residue based encoding features were fused to form a hybrid vector in order to enhance model discrimination capabilities. In addition, the proposed model incorporates SHAP (Shapley Additive Explanations) based feature selection to demonstrate model interpretability by highlighting the high contributory features. Among the applied machine learning algorithms, the XGBoost ensemble model using the tenfold cross-validation test achieved improved results than existing state-of-the-art models. Our model reported an accuracy of 89.97%, sensitivity of 87.78%, specificity of 94.45%, F1-score of 0.8934%, and MCC of 0.8764%. This study highlights the potential to provide valuable insights for enhancing medical assessment and treatment protocols, representing a significant advancement in RNA modification analysis.

RNA modifications in physiology and pathology: Progressing towards application in clinical settings

The potential to modify individual nucleotides through chemical means in order to impact the electrostatic charge, hydrophobic properties, and base pairing of RNA molecules is harnessed in the medical application of stable synthetic RNAs like mRNA vaccines and synthetic small RNA molecules. These modifications are used to either increase or decrease the production of therapeutic proteins. Additionally, naturally occurring biochemical alterations of nucleotides play a role in regulating RNA metabolism and function, thereby modulating essential cellular processes. Research elucidating the mechanisms through which RNA modifications govern fundamental cellular functions in multicellular organisms has enhanced our comprehension of how irregular RNA modification profiles can lead to human diseases. Collectively, these fundamental scientific findings have unveiled the molecular and cellular functions of RNA modifications, offering new opportunities for therapeutic intervention and paving the way for a variety of innovative clinical strategies.

Bioinformatics for Inosine: Tools and Approaches to Trace This Elusive RNA Modification

Inosine is a nucleotide resulting from the deamination of adenosine in RNA. This chemical modification process, known as RNA editing, is typically mediated by a family of double-stranded RNA binding proteins named Adenosine Deaminase Acting on dsRNA (ADAR). While the presence of ADAR orthologs has been traced throughout the evolution of metazoans, the existence and extension of RNA editing have been characterized in a more limited number of animals so far. Undoubtedly, ADAR-mediated RNA editing plays a vital role in physiology, organismal development and disease, making the understanding of the evolutionary conservation of this phenomenon pivotal to a deep characterization of relevant biological processes. However, the lack of direct high-throughput methods to reveal RNA modifications at single nucleotide resolution limited an extended investigation of RNA editing. Nowadays, these methods have been developed, and appropriate bioinformatic pipelines are required to fully exploit this data, which can complement existing approaches to detect ADAR editing. Here, we review the current literature on the "bioinformatics for inosine" subject and we discuss future research avenues in the field.

MPEK: a multitask deep learning framework based on pretrained language models for enzymatic reaction kinetic parameters prediction

Enzymatic reaction kinetics are central in analyzing enzymatic reaction mechanisms and target-enzyme optimization, and thus in biomanufacturing and other industries. The enzyme turnover number (kcat) and Michaelis constant (Km), key kinetic parameters for measuring enzyme catalytic efficiency, are crucial for analyzing enzymatic reaction mechanisms and the directed evolution of target enzymes. Experimental determination of kcat and Km is costly in terms of time, labor, and cost. To consider the intrinsic connection between kcat and Km and further improve the prediction performance, we propose a universal pretrained multitask deep learning model, MPEK, to predict these parameters simultaneously while considering pH, temperature, and organismal information. Through testing on the same kcat and Km test datasets, MPEK demonstrated superior prediction performance over the previous models. Specifically, MPEK achieved the Pearson coefficient of 0.808 for predicting kcat, improving ca. 14.6% and 7.6% compared to the DLKcat and UniKP models, and it achieved the Pearson coefficient of 0.777 for predicting Km, improving ca. 34.9% and 53.3% compared to the Kroll_model and UniKP models. More importantly, MPEK was able to reveal enzyme promiscuity and was sensitive to slight changes in the mutant enzyme sequence. In addition, in three case studies, it was shown that MPEK has the potential for assisted enzyme mining and directed evolution. To facilitate in silico evaluation of enzyme catalytic efficiency, we have established a web server implementing this model, which can be accessed at http://mathtc.nscc-tj.cn/mpek.

Variable calling of m6A and associated features in databases: a guide for end-users

N6-methyladenosine (m$^{6}$A) is a widely-studied methylation to messenger RNAs, which has been linked to diverse cellular processes and human diseases. Numerous databases that collate m$^{6}$A profiles of distinct cell types have been created to facilitate quick and easy mining of m$^{6}$A signatures associated with cell-specific phenotypes. However, these databases contain inherent complexities that have not been explicitly reported, which may lead to inaccurate identification and interpretation of m$^{6}$A-associated biology by end-users who are unaware of them. Here, we review various m$^{6}$A-related databases, and highlight several critical matters. In particular, differences in peak-calling pipelines across databases drive substantial variability in both peak number and coordinates with only moderate reproducibility, and the inclusion of peak calls from early m$^{6}$A sequencing protocols may lead to the reporting of false positives or negatives. The awareness of these matters will help end-users avoid the inclusion of potentially unreliable data in their studies and better utilize m$^{6}$A databases to derive biologically meaningful results.

PEA-m6A: an ensemble learning framework for accurately predicting N6-methyladenosine modifications in plants

N 6-methyladenosine (m6A), which is the mostly prevalent modification in eukaryotic mRNAs, is involved in gene expression regulation and many RNA metabolism processes. Accurate prediction of m6A modification is important for understanding its molecular mechanisms in different biological contexts. However, most existing models have limited range of application and are species-centric. Here we present PEA-m6A, a unified, modularized and parameterized framework that can streamline m6A-Seq data analysis for predicting m6A-modified regions in plant genomes. The PEA-m6A framework builds ensemble learning-based m6A prediction models with statistic-based and deep learning-driven features, achieving superior performance with an improvement of 6.7% to 23.3% in the area under precision-recall curve compared with state-of-the-art regional-scale m6A predictor WeakRM in 12 plant species. Especially, PEA-m6A is capable of leveraging knowledge from pretrained models via transfer learning, representing an innovation in that it can improve prediction accuracy of m6A modifications under small-sample training tasks. PEA-m6A also has a strong capability for generalization, making it suitable for application in within- and cross-species m6A prediction. Overall, this study presents a promising m6A prediction tool, PEA-m6A, with outstanding performance in terms of its accuracy, flexibility, transferability, and generalization ability. PEA-m6A has been packaged using Galaxy and Docker technologies for ease of use and is publicly available at https://github.com/cma2015/PEA-m6A.

Dexmedetomidine suppressed the biological behavior of RAW264.7 cells treated with LPS by down-regulating HOTAIR

Background

Previous studies have revealed dexmedetomidine have potential protective effects on vital organs by inhibiting the release of inflammatory cytokines. To investigate the effects of dexmedetomidine on sepsis, especially in the initial inflammatory stage of sepsis. RAW264.7 cells were used as the cell model in this study to elucidate the underlying mechanisms.

Methods

In this study, we conducted several assays to investigate the mechanisms of dexmedetomidine and HOTAIR in sepsis. Cell viability was assessed using the CCK-8 kit, while inflammation responses were measured using ELISA for IL-1β, IL-6, and TNF-α. Additionally, we employed qPCR, MeRIP, and RIP to further explore the underlying mechanisms.

Results

Our findings indicate that dexmedetomidine treatment enhanced cell viability and reduced the production of inflammatory cytokines in LPS-treated RAW264.7 cells. Furthermore, we observed that the expression of HOTAIR was increased in LPS-treated RAW264.7 cells, which was then decreased upon dexmedetomidine pre-treatment. Further investigation demonstrated that HOTAIR could counteract the beneficial effects of dexmedetomidine on cell viability and cytokine production. Interestingly, we discovered that YTHDF1 targeted HOTAIR and was upregulated in LPS-treated RAW264.7 cells, but reduced in dexmedetomidine treatment. We also found that YTHDF1 increased HOTAIR and HOTAIR m6A levels.

Conclusions

Collectively, our results suggest that dexmedetomidine downregulates HOTAIR and YTHDF1 expression, which in turn inhibits the biological behavior of LPS-treated RAW264.7 cells. This finding has potential implications for the prevention and treatment of sepsis-induced kidney injury.

m6A-TCPred: a web server to predict tissue-conserved human m6A sites using machine learning approach

BACKGROUND

N6-methyladenosine (m6A) is the most prevalent post-transcriptional modification in eukaryotic cells that plays a crucial role in regulating various biological processes, and dysregulation of m6A status is involved in multiple human diseases including cancer contexts. A number of prediction frameworks have been proposed for high-accuracy identification of putative m6A sites, however, none have targeted for direct prediction of tissue-conserved m6A modified residues from non-conserved ones at base-resolution level.

RESULTS

We report here m6A-TCPred, a computational tool for predicting tissue-conserved m6A residues using m6A profiling data from 23 human tissues. By taking advantage of the traditional sequence-based characteristics and additional genome-derived information, m6A-TCPred successfully captured distinct patterns between potentially tissue-conserved m6A modifications and non-conserved ones, with an average AUROC of 0.871 and 0.879 tested on cross-validation and independent datasets, respectively.

CONCLUSION

Our results have been integrated into an online platform: a database holding 268,115 high confidence m6A sites with their conserved information across 23 human tissues; and a web server to predict the conserved status of user-provided m6A collections. The web interface of m6A-TCPred is freely accessible at: www.rnamd.org/m6ATCPred .

Interpretable Multi-Scale Deep Learning for RNA Methylation Analysis across Multiple Species

RNA modification plays a crucial role in cellular regulation. However, traditional high-throughput sequencing methods for elucidating their functional mechanisms are time-consuming and labor-intensive, despite extensive research. Moreover, existing methods often limit their focus to specific species, neglecting the simultaneous exploration of RNA modifications across diverse species. Therefore, a versatile computational approach is necessary for interpretable analysis of RNA modifications across species. A multi-scale biological language-based deep learning model is proposed for interpretable, sequential-level prediction of diverse RNA modifications. Benchmark comparisons across species demonstrate the model's superiority in predicting various RNA methylation types over current state-of-the-art methods. The cross-species validation and attention weight visualization also highlight the model's capability to capture sequential and functional semantics from genomic backgrounds. Our analysis of RNA modifications helps us find the potential existence of "biological grammars" in each modification type, which could be effective for mapping methylation-related sequential patterns and understanding the underlying biological mechanisms of RNA modifications.

Deficiency of Acetyltransferase nat10 in Zebrafish Causes Developmental Defects in the Visual Function

Purpose

N4-acetylcytidine (ac4C) is a post-transcriptional RNA modification catalyzed by N-acetyltransferase 10 (NAT10), a critical factor known to influence mRNA stability. However, the role of ac4C in visual development remains unexplored.

Methods

Analysis of public datasets and immunohistochemical staining were conducted to assess the expression pattern of nat10 in zebrafish. We used CRISPR/Cas9 and RNAi technologies to knockout (KO) and knockdown (KD) nat10, the zebrafish ortholog of human NAT10, and evaluated its effects on early development. To assess the impact of nat10 knockdown on visual function, we performed comprehensive histological evaluations and behavioral analyses. Transcriptome profiling and real-time (RT)-PCR were utilized to detect alterations in gene expression resulting from the nat10 knockdown. Dot-blot and RNA immunoprecipitation (RIP)-PCR analyses were conducted to verify changes in ac4C levels in both total RNA and opsin mRNA specifically. Additionally, we used the actinomycin D assay to examine the stability of opsin mRNA following the nat10 KD.

Results

Our study found that the zebrafish NAT10 protein shares similar structural properties with its human counterpart. We observed that the nat10 gene was prominently expressed in the visual system during early zebrafish development. A deficiency of nat10 in zebrafish embryos resulted in increased mortality and developmental abnormalities. Behavioral and histological assessments indicated significant vision impairment in nat10 KD zebrafish. Transcriptomic analysis and RT-PCR identified substantial downregulation of retinal transcripts related to phototransduction, light response, photoreceptors, and visual perception in the nat10 KD group. Dot-blot and RIP-PCR analyses confirmed a pronounced reduction in ac4C levels in both total RNA and specifically in opsin messenger RNA (mRNA). Additionally, by evaluating mRNA decay in zebrafish treated with actinomycin D, we observed a significant decrease in the stability of opsin mRNA in the nat10 KD group.

Conclusions

The ac4C-mediated mRNA modification plays an essential role in maintaining visual development and retinal function. The loss of NAT10-mediated ac4C modification results in significant disruptions to these processes, underlining the importance of this RNA modification in ocular development.

MSCAN: multi-scale self- and cross-attention network for RNA methylation site prediction

BACKGROUND

Epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all RNA types. Precise recognition of RNA modifications is critical for understanding their functions and regulatory mechanisms. However, wet experimental methods are often costly and time-consuming, limiting their wide range of applications. Therefore, recent research has focused on developing computational methods, particularly deep learning (DL). Bidirectional long short-term memory (BiLSTM), convolutional neural network (CNN), and the transformer have demonstrated achievements in modification site prediction. However, BiLSTM cannot achieve parallel computation, leading to a long training time, CNN cannot learn the dependencies of the long distance of the sequence, and the Transformer lacks information interaction with sequences at different scales. This insight underscores the necessity for continued research and development in natural language processing (NLP) and DL to devise an enhanced prediction framework that can effectively address the challenges presented.

RESULTS

This study presents a multi-scale self- and cross-attention network (MSCAN) to identify the RNA methylation site using an NLP and DL way. Experiment results on twelve RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) reveal that the area under the receiver operating characteristic of MSCAN obtains respectively 98.34%, 85.41%, 97.29%, 96.74%, 99.04%, 79.94%, 76.22%, 65.69%, 92.92%, 92.03%, 95.77%, 89.66%, which is better than the state-of-the-art prediction model. This indicates that the model has strong generalization capabilities. Furthermore, MSCAN reveals a strong association among different types of RNA modifications from an experimental perspective. A user-friendly web server for predicting twelve widely occurring human RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) is available at http://47.242.23.141/MSCAN/index.php .

CONCLUSIONS

A predictor framework has been developed through binary classification to predict RNA methylation sites.

m5UMCB: Prediction of RNA 5-methyluridine sites using multi-scale convolutional neural network with BiLSTM

As a prevalent RNA modification, 5-methyluridine (m5U) plays a critical role in diverse biological processes and disease pathogenesis. High-throughput identification of m5U typically relies on labor-intensive biochemical experiments using various sequencing-based techniques, which are not only time-consuming but also expensive. Consequently, there is a pressing need for more efficient and cost-effective computational methods to complement these high-throughput techniques. In this study, we present m5UMCB, a novel approach that harnesses a multi-scale convolutional neural network (CNN) in tandem with bidirectional long short-term memory (BiLSTM) to recognize m5U sites. Our method involves segmenting RNA sequences into smaller fragments based on a 3-mer length and subsequently mapping each fragment to a lower-dimensional vector representation using the global vectors for word representation (GloVe) technique. Through a series of multi-scale convolution and pooling operations, local features are extracted from RNA sequences and transformed into abstract, high-level features. The feature matrix is then inputted into a BiLSTM network, enabling the capture of contextual information and long-term dependencies within the sequence. Ultimately, a fully connected layer is employed to classify m5U sites. The validation results from 5-fold cross-validation (5-fold CV) test indicate that m5UMCB outperforms existing state-of-the-art predictive methods, demonstrating a 1.98% increase in the area under ROC curve (AUC) and significant improvements in relevant evaluation metrics. We are confident that m5UMCB will serve as a valuable tool for m5U prediction.

Nicotine destructs dental stem cell-based periodontal tissue regeneration

Background/purpose

Nicotine is a widely known addictive and toxic substance in cigarette that exacerbates periodontitis. However, its deleterious effects on dental stem cells and subsequent implications in tissue regeneration remain unclear. This study aimed to explore the effects of nicotine on the regenerative capacity of human periodontal ligament stem cells (hPDLSCs) based on transcriptomics and proteomics, and determined possible targeted genes associated with smoking-related periodontitis.

Materials and methods

hPDLSCs were treated with different concentrations of nicotine ranging from 10-3 to 10-8 M. Transcriptomics and proteomics were performed and confirmed employing Western blot, 5-ethynyl-2'-deoxyuridine (EdU), and alkaline phosphatase (ALP) staining. A ligature-induced periodontitis mouse model was established and administrated with nicotine (16.2 μg/10 μL) via gingival sulcus. The bone resorption was assessed by micro-computed tomography and histological staining. Key genes were identified using multi-omics analysis with verifications in hPDLSCs and human periodontal tissues.

Results

Based on enrichments analysis, nicotine-treated hPDLSCs exhibited decreased proliferation and differentiation abilities. Local administration of nicotine in mouse model significantly aggravated bone resorption and undermined periodontal tissue regeneration by inhibiting the endogenous dental stem cells regenerative ability. HMGCS1, GPNMB, and CHRNA7 were hub-genes according to the network analysis and corelated with proliferation and differentiation capabilities, which were also verified in both cells and tissues.

Conclusion

Our study investigated the destructive effects of nicotine on the regeneration of periodontal tissues from aspects of in vitro and in vivo with the supporting information from both transcriptome and proteome, providing novel targets into the molecular mechanisms of smoking-related periodontitis.

MTTLm6A: A multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer

N6-methyladenosine (m6A) is a crucial RNA modification involved in various biological activities. Computational methods have been developed for the detection of m6A sites in Saccharomyces cerevisiae at base-resolution due to their cost-effectiveness and efficiency. However, the generalization of these methods has been hindered by limited base-resolution datasets. Additionally, RMBase contains a vast number of low-resolution m6A sites for Saccharomyces cerevisiae, and base-resolution sites are often inferred from these low-resolution results through post-calibration. We propose MTTLm6A, a multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer. First, the RNA sequences are encoded by using one-hot encoding. Then, we construct a multi-task model that combines a convolutional neural network with a multi-head-attention deep framework. This model not only detects low-resolution m6A sites, it also assigns reasonable probabilities to the predicted sites. Finally, we employ transfer learning to predict base-resolution m6A sites based on the low-resolution m6A sites. Experimental results on Saccharomyces cerevisiae m6A and Homo sapiens m1A data demonstrate that MTTLm6A respectively achieved area under the receiver operating characteristic (AUROC) values of 77.13% and 92.9%, outperforming the state-of-the-art models. At the same time, it shows that the model has strong generalization ability. To enhance user convenience, we have made a user-friendly web server for MTTLm6A publicly available at http://47.242.23.141/MTTLm6A/index.php.

Interpretable prediction models for widespread m6A RNA modification across cell lines and tissues

MOTIVATION

RNA N6-methyladenosine (m6A) in Homo sapiens plays vital roles in a variety of biological functions. Precise identification of m6A modifications is thus essential to elucidation of their biological functions and underlying molecular-level mechanisms. Currently available high-throughput single-nucleotide-resolution m6A modification data considerably accelerated the identification of RNA modification sites through the development of data-driven computational methods. Nevertheless, existing methods have limitations in terms of the coverage of single-nucleotide-resolution cell lines and have poor capability in model interpretations, thereby having limited applicability.

RESULTS

In this study, we present CLSM6A, comprising a set of deep learning-based models designed for predicting single-nucleotide-resolution m6A RNA modification sites across eight different cell lines and three tissues. Extensive benchmarking experiments are conducted on well-curated datasets and accordingly, CLSM6A achieves superior performance than current state-of-the-art methods. Furthermore, CLSM6A is capable of interpreting the prediction decision-making process by excavating critical motifs activated by filters and pinpointing highly concerned positions in both forward and backward propagations. CLSM6A exhibits better portability on similar cross-cell line/tissue datasets, reveals a strong association between highly activated motifs and high-impact motifs, and demonstrates complementary attributes of different interpretation strategies.

AVAILABILITY AND IMPLEMENTATION

The webserver is available at http://csbio.njust.edu.cn/bioinf/clsm6a. The datasets and code are available at https://github.com/zhangying-njust/CLSM6A/.

Analysis approaches for the identification and prediction of N6-methyladenosine sites

The global dynamics in a variety of biological processes can be revealed by mapping transcriptional m⁶A sites, in particular full-transcriptome m⁶A. And individual m⁶A sites have contributed to biological function, which can be evaluated by stoichiometric information obtained from the single nucleotide resolution. Currently, the identification of m⁶A sites is mainly carried out by experiment and prediction methods, based on high-throughput sequencing and machine learning model respectively. This review summarizes the recent topics and progress made in bioinformatics methods of deciphering the m⁶A methylation, including the experimental detection of m⁶A methylation sites, techniques of data analysis, the way of predicting m⁶A methylation sites, m⁶A methylation databases, and detection of m⁶A modification in circRNA. At the end, the essay makes a brief discussion for the development perspective in this area.

ADAR1 regulates vascular remodeling in hypoxic pulmonary hypertension through N1-methyladenosine modification of circCDK17

Pulmonary hypertension (PH) is an extremely malignant pulmonary vascular disease of unknown etiology. ADAR1 is an RNA editing enzyme that converts adenosine in RNA to inosine, thereby affecting RNA expression. However, the role of ADAR1 in PH development remains unclear. In the present study, we investigated the biological role and molecular mechanism of ADAR1 in PH pulmonary vascular remodeling. Overexpression of ADAR1 aggravated PH progression and promoted the proliferation of pulmonary artery smooth muscle cells (PASMCs). Conversely, inhibition of ADAR1 produced opposite effects. High-throughput whole transcriptome sequencing showed that ADAR1 was an important regulator of circRNAs in PH. CircCDK17 level was significantly lowered in the serum of PH patients. The effects of ADAR1 on cell cycle progression and proliferation were mediated by circCDK17. ADAR1 affects the stability of circCDK17 by mediating A-to-I modification at the A5 and A293 sites of circCDK17 to prevent it from m1A modification. We demonstrate for the first time that ADAR1 contributes to the PH development, at least partially, through m1A modification of circCDK17 and the subsequent PASMCs proliferation. Our study provides a novel therapeutic strategy for treatment of PH and the evidence for circCDK17 as a potential novel marker for the diagnosis of this disease.

In-depth characterization and identification of translatable lncRNAs

Long non-coding RNAs (LncRNAs) are non-protein coding transcripts more than 200 nucleotides in length. Deep sequencing technologies have unveiled lncRNAs can harbor translatable short open reading frames (sORFs). Yet the regulatory mechanisms governing lncRNA translation events remain poorly understood. Here, we exhaustively detected the sequence, functional element, and structure features relevant to lncRNA translation in human. Extensive identification and analysis reveal that translatable lncRNAs contain richer protein-coding related sequence features, cap-dependent and cap-independent translation initiation mechanisms, and more stable secondary structures, as compared to untranslatable lncRNAs. These findings strongly support lncRNAs serve as a repository for the production of new small peptides. Based on the feature fusion affecting translation and the extreme gradient boosting (XGBoost) algorithm, we developed the first computational tool that dedicated for predicting translatable lncRNAs, named TransLncPred. Benchmark experimental results show that our method outperforms several state-of-the-art RNA coding potential prediction tools on the same training and testing datasets. The 100-time 10-fold cross-validation tests also demonstrate that regulatory element-derived features, especially N7-methylguanosine (m7G) and internal ribosome entry site (IRES), contribute to the improvement in predictive performance.

Prediction of Multiple Types of RNA Modifications via Biological Language Model

It has been demonstrated that RNA modifications play essential roles in multiple biological processes. Accurate identification of RNA modifications in the transcriptome is critical for providing insights into the biological functions and mechanisms. Many tools have been developed for predicting RNA modifications at single-base resolution, which employ conventional feature engineering methods that focus on feature design and feature selection processes that require extensive biological expertise and may introduce redundant information. With the rapid development of artificial intelligence technologies, end-to-end methods are favorably received by researchers. Nevertheless, each well-trained model is only suitable for a specific RNA methylation modification type for nearly all of these approaches. In this study, we present MRM-BERT by feeding task-specific sequences into the powerful BERT (Bidirectional Encoder Representations from Transformers) model and implementing fine-tuning, which exhibits competitive performance to the state-of-the-art methods. MRM-BERT avoids repeated de novo training of the model and can predict multiple RNA modifications such as pseudouridine, m6A, m5C, and m1A in Mus musculus, Arabidopsis thaliana, and Saccharomyces cerevisiae. In addition, we analyse the attention heads to provide high attention regions for the prediction, and conduct saturated in silico mutagenesis of the input sequences to discover potential changes of RNA modifications, which can better assist researchers in their follow-up research.

Rm-LR: A long-range-based deep learning model for predicting multiple types of RNA modifications

Recent research has highlighted the pivotal role of RNA post-transcriptional modifications in the regulation of RNA expression and function. Accurate identification of RNA modification sites is important for understanding RNA function. In this study, we propose a novel RNA modification prediction method, namely Rm-LR, which leverages a long-range-based deep learning approach to accurately predict multiple types of RNA modifications using RNA sequences only. Rm-LR incorporates two large-scale RNA language pre-trained models to capture discriminative sequential information and learn local important features, which are subsequently integrated through a bilinear attention network. Rm-LR supports a total of ten RNA modification types (m6A, m1A, m5C, m5U, m6Am, Ψ, Am, Cm, Gm, and Um) and significantly outperforms the state-of-the-art methods in terms of predictive capability on benchmark datasets. Experimental results show the effectiveness and superiority of Rm-LR in prediction of various RNA modifications, demonstrating the strong adaptability and robustness of our proposed model. We demonstrate that RNA language pretrained models enable to learn dense biological sequential representations from large-scale long-range RNA corpus, and meanwhile enhance the interpretability of the models. This work contributes to the development of accurate and reliable computational models for RNA modification prediction, providing insights into the complex landscape of RNA modifications.

m6A-TSHub: Unveiling the Context-specific m6A Methylation and m6A-affecting Mutations in 23 Human Tissues

As the most pervasive epigenetic marker present on mRNAs and long non-coding RNAs (lncRNAs), N6-methyladenosine (m6A) RNA methylation has been shown to participate in essential biological processes. Recent studies have revealed the distinct patterns of m6A methylome across human tissues, and a major challenge remains in elucidating the tissue-specific presence and circuitry of m6A methylation. We present here a comprehensive online platform, m6A-TSHub, for unveiling the context-specific m6A methylation and genetic mutations that potentially regulate m6A epigenetic mark. m6A-TSHub consists of four core components, including (1) m6A-TSDB, a comprehensive database of 184,554 functionally annotated m6A sites derived from 23 human tissues and 499,369 m6A sites from 25 tumor conditions, respectively; (2) m6A-TSFinder, a web server for high-accuracy prediction of m6A methylation sites within a specific tissue from RNA sequences, which was constructed using multi-instance deep neural networks with gated attention; (3) m6A-TSVar, a web server for assessing the impact of genetic variants on tissue-specific m6A RNA modifications; and (4) m6A-CAVar, a database of 587,983 The Cancer Genome Atlas (TCGA) cancer mutations (derived from 27 cancer types) that were predicted to affect m6A modifications in the primary tissue of cancers. The database should make a useful resource for studying the m6A methylome and the genetic factors of epitranscriptome disturbance in a specific tissue (or cancer type). m6A-TSHub is accessible at www.xjtlu.edu.cn/biologicalsciences/m6ats.

PromGER: Promoter Prediction Based on Graph Embedding and Ensemble Learning for Eukaryotic Sequence

Promoters are DNA non-coding regions around the transcription start site and are responsible for regulating the gene transcription process. Due to their key role in gene function and transcriptional activity, the prediction of promoter sequences and their core elements accurately is a crucial research area in bioinformatics. At present, models based on machine learning and deep learning have been developed for promoter prediction. However, these models cannot mine the deeper biological information of promoter sequences and consider the complex relationship among promoter sequences. In this work, we propose a novel prediction model called PromGER to predict eukaryotic promoter sequences. For a promoter sequence, firstly, PromGER utilizes four types of feature-encoding methods to extract local information within promoter sequences. Secondly, according to the potential relationships among promoter sequences, the whole promoter sequences are constructed as a graph. Furthermore, three different scales of graph-embedding methods are applied for obtaining the global feature information more comprehensively in the graph. Finally, combining local features with global features of sequences, PromGER analyzes and predicts promoter sequences through a tree-based ensemble-learning framework. Compared with seven existing methods, PromGER improved the average specificity of 13%, accuracy of 10%, Matthew's correlation coefficient of 16%, precision of 4%, F1 score of 6%, and AUC of 9%. Specifically, this study interpreted the PromGER by the t-distributed stochastic neighbor embedding (t-SNE) method and SHAPley Additive exPlanations (SHAP) value analysis, which demonstrates the interpretability of the model.

M1A and m7G modification-related genes are potential biomarkers for survival prognosis and for deciphering the tumor immune microenvironment in esophageal squamous cell carcinoma

BACKGROUND

Esophageal squamous cell carcinoma (ESCC) is the most common esophageal malignancy, and RNA methylation has been reported to be involved in the tumorigenesis of ESCC. However, no study has explored methylation modifications in m¹A and m⁷G as prognostic markers for survival prediction in ESCC.

METHODS

Public gene-expression data and clinical annotation of 254 patients obtained from The Cancer Genome Atlas and the Gene Expression Omnibus databases were analyzed to identify potential consensus clusters of m¹A and m⁷G modification-related genes. The RNA-seq of 20 patients in Sun Yat-Sen University Cancer Center was used as the validation set. Following screening for relevant differentially expressed genes (DEGs) and enrichment pathways were elucidated. DEGs were used to construct risk models using the randomForest algorithm, and the prognostic role of the models was assessed by applying Kaplan-Meier analysis. Extent of immune cell infiltration, drug resistance, and response to cancer treatment among different clusters and risk groups were also evaluated.

RESULTS

Consensus clustering analysis based on m¹A and m⁷G modification patterns revealed three potential clusters. In total, 212 RNA methylation-related DEGs were identified. The methylation-associated signature consisting of 6 genes was then constructed to calculate methylation-related score (MRScore) and patients were dived into MRScore-high and MRScore-low groups. This signature has satisfied prognostic value for survival of ESCC (AUC = 0.66, 0.67, 0.64 for 2-, 3-, 4- year OS), and has satisfied performance in the validation SYSUCC cohort (AUC = 0.66 for 2- and 3-year OS). Significant correlation between m¹A and m⁷G modification-related genes and immune cell infiltration, and drug resistance was also observed.

CONCLUSIONS

Transcriptomic prognostic signatures based on m¹A and m⁷G modification-related genes are closely associated with immune cell infiltration in ESCC patients and have important correlations with the therapeutic sensitivity of multiple chemotherapeutic agents.

Evaluation and development of deep neural networks for RNA 5-Methyluridine classifications using autoBioSeqpy

Post-transcriptionally RNA modifications, also known as the epitranscriptome, play crucial roles in the regulation of gene expression during development. Recently, deep learning (DL) has been employed for RNA modification site prediction and has shown promising results. However, due to the lack of relevant studies, it is unclear which DL architecture is best suited for some pyrimidine modifications, such as 5-methyluridine (m⁵U). To fill this knowledge gap, we first performed a comparative evaluation of various commonly used DL models for epigenetic studies with the help of autoBioSeqpy. We identified optimal architectural variations for m⁵U site classification, optimizing the layer depth and neuron width. Second, we used this knowledge to develop Deepm5U, an improved convolutional-recurrent neural network that accurately predicts m⁵U sites from RNA sequences. We successfully applied Deepm5U to transcriptomewide m⁵U profiling data across different sequencing technologies and cell types. Third, we showed that the techniques for interpreting deep neural networks, including LayerUMAP and DeepSHAP, can provide important insights into the internal operation and behavior of models. Overall, we offered practical guidance for the development, benchmark, and analysis of deep learning models when designing new algorithms for RNA modifications.

N6-methyladenosine (m6A) in cancer stem cell: From molecular mechanisms to therapeutic implications

The emergence of drug resistance and metastasis has long been a difficult problem for cancer treatment. Recent studies have shown that cancer stem cell populations are key factors in the regulation of cancer aggressiveness, relapse and drug resistance. Cancer stem cell (CSC) populations are highly plastic and self-renewing, giving them unique metabolic, metastatic, and chemotherapy resistance properties. N6-methyladenosine (m6A) is the most abundant internal modification of mRNA and is involved in a variety of cell growth and development processes, including RNA transcription, alternative splicing, degradation, and translation. It has also been linked to the development of various cancers. At present, the important role of m6A in tumour progression is gradually attracting attention, especially in the tumour stemness regulation process. Abnormal m6A modifications regulate tumour metastasis, recurrence and drug resistance. This paper aims to explore the regulatory mechanism of m6A in CSCs and clinical therapy, clarify its regulatory network, and provide theoretical guidance for the development of clinical targets and improvement of therapeutic effects.

Concepts and methods for transcriptome-wide prediction of chemical messenger RNA modifications with machine learning

The expanding field of epitranscriptomics might rival the epigenome in the diversity of biological processes impacted. In recent years, the development of new high-throughput experimental and computational techniques has been a key driving force in discovering the properties of RNA modifications. Machine learning applications, such as for classification, clustering or de novo identification, have been critical in these advances. Nonetheless, various challenges remain before the full potential of machine learning for epitranscriptomics can be leveraged. In this review, we provide a comprehensive survey of machine learning methods to detect RNA modifications using diverse input data sources. We describe strategies to train and test machine learning methods and to encode and interpret features that are relevant for epitranscriptomics. Finally, we identify some of the current challenges and open questions about RNA modification analysis, including the ambiguity in predicting RNA modifications in transcript isoforms or in single nucleotides, or the lack of complete ground truth sets to test RNA modifications. We believe this review will inspire and benefit the rapidly developing field of epitranscriptomics in addressing the current limitations through the effective use of machine learning.

Identification of species-specific RNA N6-methyladinosine modification sites from RNA sequences

N6-methyladinosine (m6A) modification is the most abundant co-transcriptional modification in eukaryotic RNA and plays important roles in cellular regulation. Traditional high-throughput sequencing experiments used to explore functional mechanisms are time-consuming and labor-intensive, and most of the proposed methods focused on limited species types. To further understand the relevant biological mechanisms among different species with the same RNA modification, it is necessary to develop a computational scheme that can be applied to different species. To achieve this, we proposed an attention-based deep learning method, adaptive-m6A, which consists of convolutional neural network, bi-directional long short-term memory and an attention mechanism, to identify m6A sites in multiple species. In addition, three conventional machine learning (ML) methods, including support vector machine, random forest and logistic regression classifiers, were considered in this work. In addition to the performance of ML methods for multi-species prediction, the optimal performance of adaptive-m6A yielded an accuracy of 0.9832 and the area under the receiver operating characteristic curve of 0.98. Moreover, the motif analysis and cross-validation among different species were conducted to test the robustness of one model towards multiple species, which helped improve our understanding about the sequence characteristics and biological functions of RNA modifications in different species.

M6A-BERT-Stacking: A Tissue-Specific Predictor for Identifying RNA N6-Methyladenosine Sites Based on BERT and Stacking Strategy

As the most abundant RNA methylation modification, N6-methyladenosine (m6A) could regulate asymmetric and symmetric division of hematopoietic stem cells and play an important role in various diseases. Therefore, the precise identification of m6A sites around the genomes of different species is a critical step to further revealing their biological functions and influence on these diseases. However, the traditional wet-lab experimental methods for identifying m6A sites are often laborious and expensive. In this study, we proposed an ensemble deep learning model called m6A-BERT-Stacking, a powerful predictor for the detection of m6A sites in various tissues of three species. First, we utilized two encoding methods, i.e., di ribonucleotide index of RNA (DiNUCindex_RNA) and k-mer word segmentation, to extract RNA sequence features. Second, two encoding matrices together with the original sequences were respectively input into three different deep learning models in parallel to train three sub-models, namely residual networks with convolutional block attention module (Resnet-CBAM), bidirectional long short-term memory with attention (BiLSTM-Attention), and pre-trained bidirectional encoder representations from transformers model for DNA-language (DNABERT). Finally, the outputs of all sub-models were ensembled based on the stacking strategy to obtain the final prediction of m6A sites through the fully connected layer. The experimental results demonstrated that m6A-BERT-Stacking outperformed most of the existing methods based on the same independent datasets.

NeuroPpred-SVM: A New Model for Predicting Neuropeptides Based on Embeddings of BERT

Neuropeptides play pivotal roles in different physiological processes and are related to different kinds of diseases. Identification of neuropeptides is of great benefit for studying the mechanism of these physiological processes and the treatment of neurological disorders. Several state-of-the-art neuropeptide predictors have been developed by using a two-layer stacking ensemble algorithm. Although the two-layer stacking ensemble algorithm can improve the feature representability, these models are complex, which are not as efficient as the models based on one classifier. In this study, we proposed a new model, NeuroPpred-SVM, to predict neuropeptides based on the embeddings of Bidirectional Encoder Representations from Transformers and other sequential features by using a support vector machine (SVM). The experimental results indicate that our model achieved a cross-validation area under the receiver operating characteristic (AUROC) curve of 0.969 on the training data set and an AUROC of 0.966 on the independent test set. By comparing our model with the other four state-of-the-art models including NeuroPIpred, PredNeuroP, NeuroPpred-Fuse, and NeuroPpred-FRL on the independent test set, our model achieved the highest AUROC, Matthews correlation coefficient, accuracy, and specificity, which indicate that our model outperforms the existing models. We believed that NeuroPpred-SVM could be a useful tool for identifying neuropeptides with high accuracy and low cost. The data sets and Python code are available at https://github.com/liuyf-a/NeuroPpred-SVM.

ELMo4m6A: A Contextual Language Embedding-Based Predictor for Detecting RNA N6-Methyladenosine Sites

N6-methyladenosine (m6A) is a universal post-transcriptional modification of RNAs, and it is widely involved in various biological processes. Identifying m6A modification sites accurately is indispensable to further investigate m6A-mediated biological functions. How to better represent RNA sequences is crucial for building effective computational methods for detecting m6A modification sites. However, traditional encoding methods require complex biological prior knowledge and are time-consuming. Furthermore, most of the existing m6A sites prediction methods are limited to single species, and few methods are able to predict m6A sites across different species and tissues. Thus, it is necessary to design a more efficient computational method to predict m6A sites across multiple species and tissues. In this paper, we proposed ELMo4m6A, a contextual language embedding-based method for predicting m6A sites from RNA sequences without any prior knowledge. ELMo4m6A first learns embeddings of RNA sequences using a language model ELMo, then uses a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) to identify m6A sites. The results of 5-fold cross-validation and independent testing demonstrate that ELMo4m6A is superior to state-of-the-art methods. Moreover, we applied integrated gradients to find potential sequence patterns contributing to m6A sites.

Bioinformatic tools for epitranscriptomics

The epitranscriptome, defined as RNA modifications that do not involve alterations in the nucleotide sequence, is a popular topic in the genomic sciences. Because we need massive computational techniques to identify epitranscriptomes within individual transcripts, many tools have been developed to infer epitranscriptomic sites as well as to process datasets using high-throughput sequencing. In this review, we summarize recent developments in epitranscriptome spatial detection and data analysis and discuss their progression.

Dynamic m6A-ncRNAs association and their impact on cancer pathogenesis, immune regulation and therapeutic response

Several types of modifications have been proven to participate in the metabolism and processing of different RNA types, including non-coding RNAs (ncRNAs). N-6-methyladenosine (m6A) is a dynamic and reversible RNA modification that is closely involved in the ncRNA homeostasis, and serves as a crucial regulator for multiple cancer-associated signaling pathways. The ncRNAs usually regulate the epigenetic modification, mRNA transcription and other biological processes, displaying enormous roles in human cancers. In this review, we summarized the significant implications of m6A-ncRNA interaction in various types of cancers. In particular, the interplay between m6A and ncRNAs in cancer pathogenesis and therapeutic resistance are being widely recognized. We also discussed the relevance of m6A-ncRNA interaction in immune regulation, followed by the interference on cancer immunotherapeutic procedures. In addition, we briefly highlighted the computation tools that could identify the accurate features of m6A methylome among ncRNAs. In summary, this review would pave the way for a better understanding of the biological functions of m6A-ncRNA crosstalk in cancer research and treatment.

Dynamic regulation and key roles of ribonucleic acid methylation

Ribonucleic acid (RNA) methylation is the most abundant modification in biological systems, accounting for 60% of all RNA modifications, and affects multiple aspects of RNA (including mRNAs, tRNAs, rRNAs, microRNAs, and long non-coding RNAs). Dysregulation of RNA methylation causes many developmental diseases through various mechanisms mediated by N ⁶-methyladenosine (m⁶A), 5-methylcytosine (m⁵C), N ¹-methyladenosine (m¹A), 5-hydroxymethylcytosine (hm⁵C), and pseudouridine (Ψ). The emerging tools of RNA methylation can be used as diagnostic, preventive, and therapeutic markers. Here, we review the accumulated discoveries to date regarding the biological function and dynamic regulation of RNA methylation/modification, as well as the most popularly used techniques applied for profiling RNA epitranscriptome, to provide new ideas for growth and development.

RNADSN: Transfer-Learning 5-Methyluridine (m5U) Modification on mRNAs from Common Features of tRNA

One of the most abundant non-canonical bases widely occurring on various RNA molecules is 5-methyluridine (m5U). Recent studies have revealed its influences on the development of breast cancer, systemic lupus erythematosus, and the regulation of stress responses. The accurate identification of m⁵U sites is crucial for understanding their biological functions. We propose RNADSN, the first transfer learning deep neural network that learns common features between tRNA m⁵U and mRNA m⁵U to enhance the prediction of mRNA m⁵U. Without seeing the experimentally detected mRNA m⁵U sites, RNADSN has already outperformed the state-of-the-art method, m5UPred. Using mRNA m⁵U classification as an additional layer of supervision, our model achieved another distinct improvement and presented an average area under the receiver operating characteristic curve (AUC) of 0.9422 and an average precision (AP) of 0.7855. The robust performance of RNADSN was also verified by cross-technical and cross-cellular validation. The interpretation of RNADSN also revealed the sequence motif of common features. Therefore, RNADSN should be a useful tool for studying m⁵U modification.

Geographic encoding of transcripts enabled high-accuracy and isoform-aware deep learning of RNA methylation

As the most pervasive epigenetic mark present on mRNA and lncRNA, N6-methyladenosine (m6A) RNA methylation regulates all stages of RNA life in various biological processes and disease mechanisms. Computational methods for deciphering RNA modification have achieved great success in recent years; nevertheless, their potential remains underexploited. One reason for this is that existing models usually consider only the sequence of transcripts, ignoring the various regions (or geography) of transcripts such as 3'UTR and intron, where the epigenetic mark forms and functions. Here, we developed three simple yet powerful encoding schemes for transcripts to capture the submolecular geographic information of RNA, which is largely independent from sequences. We show that m6A prediction models based on geographic information alone can achieve comparable performances to classic sequence-based methods. Importantly, geographic information substantially enhances the accuracy of sequence-based models, enables isoform- and tissue-specific prediction of m6A sites, and improves m6A signal detection from direct RNA sequencing data. The geographic encoding schemes we developed have exhibited strong interpretability, and are applicable to not only m6A but also N1-methyladenosine (m1A), and can serve as a general and effective complement to the widely used sequence encoding schemes in deep learning applications concerning RNA transcripts.

MTDeepM6A-2S: A two-stage multi-task deep learning method for predicting RNA N6-methyladenosine sites of Saccharomyces cerevisiae

N6-methyladenosine (m6A) is one of the most important RNA modifications, which is involved in many biological activities. Computational methods have been developed to detect m6A sites due to their high efficiency and low costs. As one of the most widely utilized model organisms, many methods have been developed for predicting m6A sites of Saccharomyces cerevisiae. However, the generalization of these methods was hampered by the limited size of the benchmark datasets. On the other hand, over 60,000 low resolution m6A sites and more than 10,000 base resolution m6A sites of Saccharomyces cerevisiae are recorded in RMBase and m6A-Atlas, respectively. The base resolution m6A sites are often obtained from low resolution results by post calibration. In view of these, we proposed a two-stage deep learning method, named MTDeepM6A-2S, to predict RNA m6A sites of Saccharomyces cerevisiae based on RNA sequence information. In the first stage, a multi-task model with convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) deep framework was built to not only detect the low resolution m6A sites but also assign a reasonable probability for the predicted site. In the second stage, a transfer-learning strategy was used to build the model to predict the base resolution m6A sites from those low resolution m6A sites. The effectiveness of our model was validated on both training and independent test sets. The results show that our model outperforms other state-of-the-art models on the independent test set, which indicates that our model holds high potential to become a useful tool for epitranscriptomics analysis.

PredPromoter-MF(2L): A Novel Approach of Promoter Prediction Based on Multi-source Feature Fusion and Deep Forest

Promoters short DNA sequences play vital roles in initiating gene transcription. However, it remains a challenge to identify promoters using conventional experiment techniques in a high-throughput manner. To this end, several computational predictors based on machine learning models have been developed, while their performance is unsatisfactory. In this study, we proposed a novel two-layer predictor, called PredPromoter-MF(2L), based on multi-source feature fusion and ensemble learning. PredPromoter-MF(2L) was developed based on various deep features learned by a pre-trained deep learning network model and sequence-derived features. Feature selection based on XGBoost was applied to reduce fused features dimensions, and a cascade deep forest model was trained on the selected feature subset for promoter prediction. The results both fivefold cross-validation and independent test demonstrated that PredPromoter-MF(2L) outperformed state-of-the-art methods.