m7GHub: deciphering the location, regulation and pathogenesis of internal mRNA N7-methylguanosine (m7G) sites in human

N7-methylguanosine-related lncRNAs: Predicting the prognosis and diagnosis of colorectal cancer in the cold and hot tumors

Background: 7-Methylguanosine(m7G) contributes greatly to its pathogenesis and progression in colorectal cancer. We proposed building a prognostic model of m7G-related LncRNAs. Our prognostic model was used to identify differences between hot and cold tumors.

Methods: The study included 647 colorectal cancer patients (51 cancer-free patients and 647 cancer patients) from The Cancer Genome Atlas (TCGA). We identified m7G-related prognostic lncRNAs by employing the univariate Cox regression method. Assessments were conducted using univariate Cox regression, multivariate Cox regression, receiver operating characteristics (ROC), nomogram, calibration curves, and Kaplan-Meier analysis. All of these procedures were used with the aim of confirming the validity and stability of the model. Besides these two analyses, we also conducted half-maximal inhibitory concentration (IC50), immune analysis, principal component analysis (PCA), and gene set enrichment analysis (GSEA). The entire set of m7G-related (lncRNAs) with respect to cold and hot tumors has been divided into two clusters for further discussion of immunotherapy.

Results: The risk model was constructed with 17 m7G-related lncRNAs. A good correlation was found between the calibration plots and the prognosis prediction in the model. By assessing IC50 in a significant way across risk groups, systemic treatment can be guided. By using clusters, it may be possible to distinguish hot and cold tumors effectively and to aid in specific therapeutic interventions. Cluster 1 was identified as having the highest response to immunotherapy drugs and thus was identified as the hot tumor.

Conclusion: This study shows that 17 m7G-related lncRNA can be used in clinical settings to predict prognosis and use them to determine whether a tumor is cold or hot in colorectal cancer and improve the individualization of treatment.

Transcriptome Profiling of N7-Methylguanosine Modification of Messenger RNA in Drug-Resistant Acute Myeloid Leukemia

Acute myeloid leukemia (AML) is an aggressive hematological tumor caused by the malignant transformation of myeloid progenitor cells. Although intensive chemotherapy leads to an initial therapeutic response, relapse due to drug resistance remains a significant challenge. In recent years, accumulating evidence has suggested that post-transcriptional methylation modifications are strongly associated with tumorigenesis. However, the mRNA profile of m7G modification in AML and its role in drug-resistant AML are unknown. In this study, we used MeRIP-seq technology to establish the first transcriptome-wide m7G methylome profile for AML and drug-resistant AML cells, and differences in m7G between the two groups were analyzed. In addition, bioinformatics analysis was conducted to explore the function of m7G-specific methylated transcripts. We found significant differences in m7G mRNA modification between AML and drug-resistant AML cells. Furthermore, bioinformatics analysis revealed that differential m7G-modified mRNAs were associated with a wide range of cellular functions. Importantly, down-methylated m7G modification was significantly enriched in ABC transporter-related mRNAs, which are widely recognized to play a key role in multidrug resistance. Our results provide new insights into a novel function of m7G methylation in drug resistance progression of AML.

Primary sequence-assisted prediction of m6A RNA methylation sites from Oxford nanopore direct RNA sequencing data

Traditional epitranscriptome profiling approach relies on specific antibodies or chemical treatments to capture modified RNA molecules and then applies high throughput sequencing to identify their transcriptomic locations. However, due to the lack of suitable or high-quality antibodies, only a small proportion of the 170 documented RNA modifications were profiled with those approaches. Direct sequencing of native RNA molecules using Oxford Nanopore Technologies (ONT) enabled straight inspection of RNA modifications and offered a promising alternative solution. N6-methyladenosine (m6A) is known to cause characteristic changes and increased base call errors of ONT signals compared with non-modified adenosines, based on which, the m6A sites can be identified directly from ONT signals. Meanwhile, a number of studies have shown that it is possible to predict m6A sites from RNA primary sequences. Using the m6A sites revealed by Illumina technology as benchmark, we showed that, the accuracy of ONT-based m6A site prediction can be further increased by integrating additional information from the primary sequences of RNA (AUROC of 0.918), compared with using ONT signals only (AUROC 0.878 using Base call error features, and 0.804 using Tombo features), providing a new perspective for more reliable mining of the relatively noisy ONT signals.

WHISTLE server: A high-accuracy genomic coordinate-based machine learning platform for RNA modification prediction

The primary sequences of DNA, RNA and protein have been used as the dominant information source of existing machine learning tools, especially for contexts not fully explored by wet-experimental approaches. Since molecular markers are profoundly orchestrated in the living organisms, those markers that cannot be unambiguously recovered from the primary sequence often help to predict other biological events. To the best of our knowledge, there is no current tool to build and deploy machine learning models that consider genomic evidence. We therefore developed the WHISTLE server, the first machine learning platform based on genomic coordinates. It features convenient covariate extraction and model web deployment with 46 distinct genomic features integrated along with the conventional sequence features. We showed that, when predicting m6A sites from SRAMP project, the model integrating genomic features substantially outperformed those based on only sequence features. The WHISTLE server should be a useful tool for studying biological attributes specifically associated with genomic coordinates, and is freely accessible at: www.xjtlu.edu.cn/biologicalsciences/whi2.

m6AmPred: Identifying RNA N6, 2'-O-dimethyladenosine (m6Am) sites based on sequence-derived information

N6,2'-O-dimethyladenosine (m6Am) is a reversible modification widely occurred on varied RNA molecules. The biological function of m6Am is yet to be known though recent studies have revealed its influences in cellular mRNA fate. Precise identification of m6Am sites on RNA is vital for the understanding of its biological functions. We present here m6AmPred, the first web server for in silico identification of m6Am sites from the primary sequences of RNA. Built upon the eXtreme Gradient Boosting with Dart algorithm (XgbDart) and EIIP-PseEIIP encoding scheme, m6AmPred achieved promising prediction performance with the AUCs greater than 0.954 when tested by 10-fold cross-validation and independent testing datasets. To critically test and validate the performance of m6AmPred, the experimentally verified m6Am sites from two data sources were cross-validated. The m6AmPred web server is freely accessible at: https://www.xjtlu.edu.cn/biologicalsciences/m6am, and it should make a useful tool for the researchers who are interested in N6,2'-O-dimethyladenosine RNA modification.

Identification of m7G-associated lncRNA prognostic signature for predicting the immune status in cutaneous melanoma

RNA modifications, including RNA methylation, are widely existed in cutaneous melanoma (CM). Among epigenetic modifications, N7-methylguanosine (m7G) is a kind of modification at 5' cap of RNA which participate in maintaining the stability of mRNA and various cell biological processes. However, there is still no study concerning the relationship between CM and m7G methylation complexes, METTL1 and WDR4. Here, long non-coding RNA (lncRNAs) and gene expression data of CM from the Cancer Genome Atlas (TCGA) database were retrieved to identify differentially expressed m7G-related lncRNAs connected with overall survival of CM. Then, Cox regression analyses was applied to construct a lncRNA risk signature, the prognostic value of identified signature was further evaluated. As a result, 6 m7G-associated lncRNAs that were significantly related to CM prognosis were incorporated into our prognostic signature. The functional analyses indicated that the prognostic model was correlated with patient survival, cancer metastasis, and growth. Meanwhile, its diagnostic accuracy was better than conventional clinicopathological characteristics. The pathway enrichment analysis showed that the risk model was enriched in several immunity-associated pathways. Moreover, the signature model was significantly connected with the immune subtypes, infiltration of immune cells, immune microenvironment, as well as several m6A-related genes and tumor stem cells. Finally, a nomogram based on the calculated risk score was established. Overall, a risk signature based on 6 m7G-associated lncRNAs was generated which presented predictive value for the prognosis of CM patients and can be further used in the development of novel therapeutic strategies for CM.

Pharmacoepitranscriptomic landscape revealing m6A modification could be a drug-effect biomarker for cancer treatment

RNA chemical modifications are a new but rapidly developing field. They can directly affect RNA splicing, transport, stability, and translation. Consequently, they are involved in the occurrence and development of diseases that have been studied extensively in recent years. However, few studies have focused on the correlation between chemical modifications and drug effects. Here, we provide a landscape of six RNA modifications in pharmacogene RNA (pharmacoepitranscriptomics) to fully clarify the correlation between chemical modifications and drugs. We performed systematic and comprehensive analyses on pharmacoepitranscriptomics, including basic characteristics of RNA modification and modification-associated mutations and drugs affected by them. Our results show that chemical modifications are common in pharmacogenes, especially N6-methyladenosine (m6A) modification. In addition, we found a very close relationship between chemical modifications and anti-tumor drugs. More interestingly, the results demonstrate the importance of m6A modification for anti-tumor drugs, especially for drugs in triple-negative breast cancer (TNBC), ovarian cancer, and acute myelocytic leukemia (AML). These results indicate that pharmacoepitranscriptomics could be a new source of drug-effect biomarkers, especially for m6A and anti-tumor drugs.

N7-Methylguanosine Genes Related Prognostic Biomarker in Hepatocellular Carcinoma

Background: About 90% of liver cancer-related deaths are caused by hepatocellular carcinoma (HCC). N7-methylguanosine (m7G) modification is associated with the biological process and regulation of various diseases. To the best of our knowledge, its role in the pathogenesis and prognosis of HCC has not been thoroughly investigated. Aim: To identify N7-methylguanosine (m7G) related prognostic biomarkers in HCC. Furthermore, we also studied the association of m7G-related prognostic gene signature with immune infiltration in HCC. Methods: The TCGA datasets were used as a training and GEO dataset "GSE76427" for validation of the results. Statistical analyses were performed using the R statistical software version 4.1.2. Results: Functional enrichment analysis identified some pathogenesis related to HCC. We identified 3 m7G-related genes (CDK1, ANO1, and PDGFRA) as prognostic biomarkers for HCC. A risk score was calculated from these 3 prognostic m7G-related genes which showed the high-risk group had a significantly poorer prognosis than the low-risk group in both training and validation datasets. The 3- and 5-years overall survival was predicted better with the risk score than the ideal model in the entire cohort in the predictive nomogram. Furthermore, immune checkpoint genes like CTLA4, HAVCR2, LAG3, and TIGT were expressed significantly higher in the high-risk group and the chemotherapy sensitivity analysis showed that the high-risk groups were responsive to sorafenib treatment. Conclusion: These 3 m7G genes related signature model can be used as prognostic biomarkers in HCC and a guide for immunotherapy and chemotherapy response. Future clinical study on this biomarker model is required to verify its clinical implications.

Expression and Potential Biomarkers of Regulators for M7G RNA Modification in Gliomas

Gliomas are the most frequent primary malignant brain tumors of the central nervous system, causing significant impairment and death. There is mounting evidence that N7 methylguanosine (m7G) RNA dysmethylation plays a significant role in the development and progression of cancer. However, the expression patterns and function of the m7G RNA methylation regulator in gliomas are yet unknown. The goal of this study was to examine the expression patterns of 31 critical regulators linked with m7G RNA methylation and their prognostic significance in gliomas. To begin, we systematically analyzed patient clinical and prognostic data and mRNA gene expression data from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) databases. We found that 17 key regulators of m7G RNA methylation showed significantly higher expression levels in gliomas. We then divided the sample into two subgroups by consensus clustering. Cluster 2 had a poorer prognosis than cluster 1 and was associated with a higher histological grade. In addition, cluster 2 was significantly enriched for cancer-related pathways. Based on this discovery, we developed a risk model involving three m7G methylation regulators. Patients were divided into high-risk and low-risk groups based on risk scores. Overall survival (OS) was significantly lower in the high-risk group than in the low-risk group. Further analysis showed that the risk score was an independent prognostic factor for gliomas.

Effect of Humantenine on mRNA m6A Modification and Expression in Human Colon Cancer Cell Line HCT116

Humantenine, an alkaloid isolated from the medicinal herb Gelsemium elegans (Gardner & Chapm.) Benth., has been reported to induce intestinal irritation, but the underlying toxicological mechanisms remain unclear. The object of the present study was to investigate the RNA N6-methyladenosine (m6A) modification and distinct mRNA transcriptome profiles in humantenine-treated HCT116 human colon cancer cells. High-throughput MeRIP-seq and mRNA-seq were performed, and bioinformatic analysis was performed to reveal the role of abnormal RNA m6A modification and mRNA expression in humantenine-induced intestinal cell toxicity. After humantenine treatment of HCT116 cells, 1401 genes were in the overlap of differentially m6A-modified mRNA and differentially expressed mRNA. The Kyoto Encyclopedia of Genes and Genomes and Gene Ontology annotation terms for actin cytoskeleton, tight junctions, and adherens junctions were enriched. A total of 11 kinds of RNA m6A methylation regulators were differentially expressed. The m6A methylation levels of target genes were disordered in the humantenine group. In conclusion, this study suggested that the HCT116 cell injury induced by humantenine was associated with the abnormal mRNA expression of m6A regulators, as well as disordered m6A methylation levels of target genes.

Identification of RNA Methylation-Related lncRNAs Signature for Predicting Hot and Cold Tumors and Prognosis in Colon Cancer

N6-methyladenosine (m6A), N1-methyladenosine (m1A), 5-methylcytosine (m5C), and 7-methylguanosine (m7G) are the major forms of RNA methylation modifications, which are closely associated with the development of many tumors. However, the prognostic value of RNA methylation-related long non-coding RNAs (lncRNAs) in colon cancer (CC) has not been defined. This study summarised 50 m6A/m1A/m5C/m7G-related genes and downloaded 41 normal and 471 CC tumor samples with RNA-seq data and clinicopathological information from The Cancer Genome Atlas (TCGA) database. A total of 1057 RNA methylation-related lncRNAs (RMlncRNAs) were identified with Pearson correlation analysis. Twenty-three RMlncRNAs with prognostic values were screened using univariate Cox regression analysis. By consensus clustering analysis, CC patients were classified into two molecular subtypes (Cluster 1 and Cluster 2) with different clinical outcomes and immune microenvironmental infiltration characteristics. Cluster 2 was considered to be the “hot tumor” with a better prognosis, while cluster 1 was regarded as the “cold tumor” with a poorer prognosis. Subsequently, we constructed a seven-lncRNA prognostic signature using the least absolute shrinkage and selection operator (LASSO) Cox regression. In combination with other clinical traits, we found that the RNA methylation-related lncRNA prognostic signature (called the “RMlnc-score”) was an independent prognostic factor for patients with colon cancer. In addition, immune infiltration, immunotherapy response analysis, and half-maximum inhibitory concentration (IC50) showed that the low RMlnc-score group was more sensitive to immunotherapy, while the high RMlnc-score group was sensitive to more chemotherapeutic agents. In summary, the RMlnc-score we developed could be used to predict the prognosis, immunotherapy response, and drug sensitivity of CC patients, guiding more accurate, and personalized treatment regimens.

m5CRegpred: Epitranscriptome Target Prediction of 5-Methylcytosine (m5C) Regulators Based on Sequencing Features

5-methylcytosine (m5C) is a common post-transcriptional modification observed in a variety of RNAs. m5C has been demonstrated to be important in a variety of biological processes, including RNA structural stability and metabolism. Driven by the importance of m5C modification, many projects focused on the m5C sites prediction were reported before. To better understand the upstream and downstream regulation of m5C, we present a bioinformatics framework, m5CRegpred, to predict the substrate of m5C writer NSUN2 and m5C readers YBX1 and ALYREF for the first time. After features comparison, window lengths selection and algorism comparison on the mature mRNA model, our model achieved AUROC scores 0.869, 0.724 and 0.889 for NSUN2, YBX1 and ALYREF, respectively in an independent test. Our work suggests the substrate of m5C regulators can be distinguished and may help the research of m5C regulators in a special condition, such as substrates prediction of hyper- or hypo-expressed m5C regulators in human disease.

A bibliometric analysis of RNA methylation in diabetes mellitus and its complications from 2002 to 2022

BACKGROUND

RNA methylation has emerged as an active research field in diabetes mellitus (DM) and its complications, while few bibliometric analyses have been performed. We aimed to visualize the hotspots and trends using bibliometric analysis to provide a comprehensive and objective overview of the current search state in this field.

METHODS

The articles and reviews regarding RNA methylation in DM and its complications were from the Web of Science Core Collection. A retrospective bibliometric analysis and science mapping was performed using the CiteSpace software to plot the knowledge maps and predict the hotspots and trends.

RESULTS

Three hundred seventy-five qualified records were retrieved. The annual publications gradually increased over the past 20 years. These publications mainly came from 66 countries led by Canada and 423 institutions. Leiter and Sievenpiper were the most productive authors, and Jenkins ranked first in the cited authors. Diabetes Care was the most co-cited journal. The most common keywords were "Type 2 diabetes", "cardiovascular disease", "diabetes mellitus", and "n 6 methyladenosine". The extracted keywords mainly clustered in "beta-cell function", "type 2 diabetes", "diabetic nephropathy", "aging", and "n6-methyladenosine". N6-methyladenosine (m⁶A) in DM and its complications were the developing areas of study.

CONCLUSION

Studies on RNA methylation, especially m⁶A modification, are the current hotspots and the future trends in type 2 diabetes (T2D) and diabetic nephropathy (DN), as well as a frontier field for other complications of DM. Strengthening future cooperation and exchange between countries and institutions is strongly advisable to promote research developments in this field.

Epitranscriptomics of cardiovascular diseases (Review)

RNA modifications have recently become the focus of attention due to their extensive regulatory effects in a vast array of cellular networks and signaling pathways. Just as epigenetics is responsible for the imprinting of environmental conditions on a genetic level, epitranscriptomics follows the same principle at the RNA level, but in a more dynamic and sensitive manner. Nevertheless, its impact in the field of cardiovascular disease (CVD) remains largely unexplored. CVD and its associated pathologies remain the leading cause of death in Western populations due to the limited regenerative capacity of the heart. As such, maintenance of cardiac homeostasis is paramount for its physiological function and its capacity to respond to environmental stimuli. In this context, epitranscriptomic modifications offer a novel and promising therapeutic avenue, based on the fine‑tuning of regulatory cascades, necessary for cardiac function. This review aimed to provide an overview of the most recent findings of key epitranscriptomic modifications in both coding and non‑coding RNAs. Additionally, the methods used for their detection and important associations with genetic variations in the context of CVD were summarized. Current knowledge on cardiac epitranscriptomics, albeit limited still, indicates that the impact of epitranscriptomic editing in the heart, in both physiological and pathological conditions, holds untapped potential for the development of novel targeted therapeutic approaches in a dynamic manner.

m6A-Maize: Weakly supervised prediction of m6A-carrying transcripts and m6A-affecting mutations in maize (Zea mays)

With the rapid development of high-throughput sequencing techniques nowadays, extensive attention has been paid to epitranscriptomics, which covers more than 150 distinct chemical modifications to date. Among that, N6-methyladenosine (m⁶A) modification has the most abundant existence, and it is also significantly related to varieties of biological processes. Meanwhile, maize is the most important food crop and cultivated throughout the world. Therefore, the study of m⁶A modification in maize has both economic and academic value. In this research, we proposed a weakly supervised learning model to predict the situation of m⁶A modification in maize. The proposed model learns from low-resolution epitranscriptome datasets (e.g., MeRIP-seq), which predicts the m⁶A methylation status of given fragments or regions. By taking advantage of our prediction model, we further identified traits-associated SNPs that may affect (add or remove) m⁶A modifications in maize, which may provide potential regulatory mechanisms at epitranscriptome layer. Additionally, a centralized online-platform was developed for m⁶A study in maize, which contains 58,838 experimentally validated maize m⁶A-containing regions including training and testing datasets, and a database for 2,578 predicted traits-associated m⁶A-affecting maize mutations. Furthermore, the online web server based on proposed weakly supervised model is available for predicting putative m⁶A sites from user-uploaded maize sequences, as well as accessing the epitranscriptome impact of user-interested maize SNPs on m⁶A modification. In all, our work provided a useful resource for the study of m⁶A RNA methylation in maize species. It is freely accessible at www.xjtlu.edu.cn/biologicalsciences/maize.

ConsRM: collection and large-scale prediction of the evolutionarily conserved RNA methylation sites, with implications for the functional epitranscriptome

Motivation N6-methyladenosine (m6A) is the most prevalent RNA modification on mRNAs and lncRNAs. Evidence increasingly demonstrates its crucial importance in essential molecular mechanisms and various diseases. With recent advances in sequencing techniques, tens of thousands of m6A sites are identified in a typical high-throughput experiment, posing a key challenge to distinguish the functional m6A sites from the remaining 'passenger' (or 'silent') sites. Results: We performed a comparative conservation analysis of the human and mouse m6A epitranscriptomes at single site resolution. A novel scoring framework, ConsRM, was devised to quantitatively measure the degree of conservation of individual m6A sites. ConsRM integrates multiple information sources and a positive-unlabeled learning framework, which integrated genomic and sequence features to trace subtle hints of epitranscriptome layer conservation. With a series validation experiments in mouse, fly and zebrafish, we showed that ConsRM outperformed well-adopted conservation scores (phastCons and phyloP) in distinguishing the conserved and unconserved m6A sites. Additionally, the m6A sites with a higher ConsRM score are more likely to be functionally important. An online database was developed containing the conservation metrics of 177 998 distinct human m6A sites to support conservation analysis and functional prioritization of individual m6A sites. And it is freely accessible at: https://www.xjtlu.edu.cn/biologicalsciences/con.

Identifying N7-methylguanosine sites by integrating multiple features

Recent studies reported that N7-methylguanosine (m7G) plays a vital role in gene expression regulation. As a consequence, determining the distribution of m7G is a crucial step towards further understanding its biological functions. Although biological experimental approaches are capable of accurately locating m7G sites, they are labor-intensive, costly, and time-consuming. Therefore, it is necessary to develop more effective and robust computational methods to replace, or at least complement current experimental methods. In this study, we developed a novel sequence-based computational tool to identify RNA m7G sites. In this model, 22 kinds of dinucleotide physicochemical (PC) properties were employed to encode the RNA sequence. Three types of descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were adopted to extract effective features from the PC matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was utilized to reduce the influence of irrelevant or redundant features. Finally, these selected features were fed into a support vector machine (SVM) for distinguishing m7G from non-m7G sites. The proposed method significantly outperforms existing predictors across all evaluation metrics. It indicates that the approach is effective in identifying RNA m7G sites.

m7G-DPP: Identifying N7-methylguanosine sites based on dinucleotide physicochemical properties of RNA

N7-methylguanosine (m7G) modification is one of the most common post-transcriptional RNA modifications, which play vital role in the regulation of gene expression. Dysfunction of m7G may result to developmental defects and the appearance of some serious diseases. Thus, it is an urgent task to fast and accurate identifying m7G sites. In view of experimental approaches are costly and time-consuming, researchers focused their attention on computational models. Hence, in current study, we proposed a novel predictor called m7G-DPP to identify m7G sites. In the predictor, the RNA sequences were firstly encoded by physicochemical (PC) properties of dinucleotide. Then, sliding window approach was adopted to divide PC matrix into multiple matrixes, and Pearson's correlation coefficient (PCC), dynamic time warping (DTW), and distance correlation (DC) were employed to extract classification features at each window. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was applied to select discriminative features. Finally, these selected features were fed into support vector machine to identify m7G sites. Experimental results showed that the proposed method is effective, which may play a complementary role in current m7G sites prediction studies. The MATLAB codes and dataset can be obtained from website at https://figshare.com/articles/online_resource/m7G-DPP/15000348.

Machine learning applications in RNA modification sites prediction

Ribonucleic acid (RNA) modifications are post-transcriptional chemical composition changes that have a fundamental role in regulating the main aspect of RNA function. Recently, large datasets have become available thanks to the recent development in deep sequencing and large-scale profiling. This availability of transcriptomic datasets has led to increased use of machine learning based approaches in epitranscriptomics, particularly in identifying RNA modifications. In this review, we comprehensively explore machine learning based approaches used for the prediction of 11 RNA modification types, namely,m 1 A ,m 6 A ,m 5 C , 5 hmC , ψ , 2 ' - O - Me , ac 4 C ,m 7 G , A - to - I ,m 2 G , and D . This review covers the life cycle of machine learning methods to predict RNA modification sites including available benchmark datasets, feature extraction, and classification algorithms. We compare available methods in terms of datasets, target species, approach, and accuracy for each RNA modification type. Finally, we discuss the advantages and limitations of the reviewed approaches and suggest future perspectives.

Development and Validation of a Novel Gene Signature for Predicting the Prognosis by Identifying m5C Modification Subtypes of Cervical Cancer

Background: 5-Methylcytidine (m5C) is the most common RNA modification and plays an important role in multiple tumors including cervical cancer (CC). We aimed to develop a novel gene signature by identifying m5C modification subtypes of CC to better predict the prognosis of patients. Methods: We obtained the expression of 13 m5C regulatory factors from The Cancer Genome Atlas (TCGA all set, 257 patients) to determine m5C modification subtypes by the "nonnegative matrix factorization" (NMF). Then the "limma" package was used to identify differentially expressed genes (DEGs) between different subtypes. According to these DEGs, we performed Cox regression and Kaplan-Meier (KM) survival analysis to establish a novel gene signature in TCGA training set (128 patients). We also verified the risk prediction effect of gene signature in TCGA test set (129 patients), TCGA all set (257 patients) and GSE44001 (300 patients). Furthermore, a nomogram including this gene signature and clinicopathological parameters was established to predict the individual survival rate. Finally, the expression and function of these signature genes were explored by qRT-PCR, immunohistochemistry (IHC) and proliferation, colony formation, migration and invasion assays. Results: Based on consistent clustering of 13 m5C-modified genes, CC was divided into two subtypes (C1 and C2) and the C1 subtype had a worse prognosis. The 4-gene signature comprising FNDC3A, VEGFA, OPN3 and CPE was constructed. In TCGA training set and three validation sets, we found the prognosis of patients in the low-risk group was much better than that in the high-risk group. A nomogram incorporating the gene signature and T stage was constructed, and the calibration plot suggested that it could accurately predict the survival rate. The expression levels of FNDC3A, VEGFA, OPN3 and CPE were all high in cervical cancer tissues. Downregulation of FNDC3A, VEGFA or CPE expression suppressed the proliferation, migration and invasion of SiHa cells. Conclusions: Two m5C modification subtypes of CC were identified and then a 4-gene signature was established, which provide new feasible methods for clinical risk assessment and targeted therapies for CC.

BERT-m7G: A Transformer Architecture Based on BERT and Stacking Ensemble to Identify RNA N7-Methylguanosine Sites from Sequence Information

As one of the most prevalent posttranscriptional modifications of RNA, N7-methylguanosine (m7G) plays an essential role in the regulation of gene expression. Accurate identification of m7G sites in the transcriptome is invaluable for better revealing their potential functional mechanisms. Although high-throughput experimental methods can locate m7G sites precisely, they are overpriced and time-consuming. Hence, it is imperative to design an efficient computational method that can accurately identify the m7G sites. In this study, we propose a novel method via incorporating BERT-based multilingual model in bioinformatics to represent the information of RNA sequences. Firstly, we treat RNA sequences as natural sentences and then employ bidirectional encoder representations from transformers (BERT) model to transform them into fixed-length numerical matrices. Secondly, a feature selection scheme based on the elastic net method is constructed to eliminate redundant features and retain important features. Finally, the selected feature subset is input into a stacking ensemble classifier to predict m7G sites, and the hyperparameters of the classifier are tuned with tree-structured Parzen estimator (TPE) approach. By 10-fold cross-validation, the performance of BERT-m7G is measured with an ACC of 95.48% and an MCC of 0.9100. The experimental results indicate that the proposed method significantly outperforms state-of-the-art prediction methods in the identification of m7G modifications.

Weakly supervised learning of RNA modifications from low-resolution epitranscriptome data

Motivation

Increasing evidence suggests that post-transcriptional ribonucleic acid (RNA) modifications regulate essential biomolecular functions and are related to the pathogenesis of various diseases. Precise identification of RNA modification sites is essential for understanding the regulatory mechanisms of RNAs. To date, many computational approaches for predicting RNA modifications have been developed, most of which were based on strong supervision enabled by base-resolution epitranscriptome data. However, high-resolution data may not be available.

Results

We propose WeakRM, the first weakly supervised learning framework for predicting RNA modifications from low-resolution epitranscriptome datasets, such as those generated from acRIP-seq and hMeRIP-seq. Evaluations on three independent datasets (corresponding to three different RNA modification types and their respective sequencing technologies) demonstrated the effectiveness of our approach in predicting RNA modifications from low-resolution data. WeakRM outperformed state-of-the-art multi-instance learning methods for genomic sequences, such as WSCNN, which was originally designed for transcription factor binding site prediction. Additionally, our approach captured motifs that are consistent with existing knowledge, and visualization of the predicted modification-containing regions unveiled the potentials of detecting RNA modifications with improved resolution.

Availability implementation

The source code for the WeakRM algorithm, along with the datasets used, are freely accessible at: https://github.com/daiyun02211/WeakRM

Supplementary information

Supplementary data are available at Bioinformatics online.

MYC-targeted WDR4 promotes proliferation, metastasis, and sorafenib resistance by inducing CCNB1 translation in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common malignancies worldwide. However, there still remains a lack of effective diagnostic and therapeutic targets for this disease. Increasing evidence demonstrates that RNA modifications play an important role in the progression of HCC, but the role of the N7-methylguanosine (m7G) methylation modification in HCC has not been properly evaluated. Thus, the goal of the present study was to investigate the function and mechanism of the m7G methyltransferase WD repeat domain 4 (WDR4) in HCC as well as its clinical relevance and potential value. We first verified the high expression of WDR4 in HCC and observed that upregulated WDR4 expression increased the m7G methylation level in HCC. WDR4 promoted HCC cell proliferation by inducing the G2/M cell cycle transition and inhibiting apoptosis in addition to enhancing metastasis and sorafenib resistance through epithelial-mesenchymal transition (EMT). Furthermore, we observed that c-MYC (MYC) can activate WDR4 transcription and that WDR4 promotes CCNB1 mRNA stability and translation to enhance HCC progression. Mechanistically, we determined that WDR4 enhances CCNB1 translation by promoting the binding of EIF2A to CCNB1 mRNA. Furthermore, CCNB1 was observed to promote PI3K and AKT phosphorylation in HCC and reduce P53 protein expression by promoting P53 ubiquitination. In summary, we elucidated the MYC/WDR4/CCNB1 signalling pathway and its impact on PI3K/AKT and P53. Furthermore, the result showed that the m7G methyltransferase WDR4 is a tumour promoter in the development and progression of HCC and may act as a candidate therapeutic target in HCC treatment.

m5C-Related lncRNAs Predict Overall Survival of Patients and Regulate the Tumor Immune Microenvironment in Lung Adenocarcinoma

Long non-coding RNAs (lncRNAs), which are involved in the regulation of RNA methylation, can be used to evaluate tumor prognosis. lncRNAs are closely related to the prognosis of patients with lung adenocarcinoma (LUAD); thus, it is crucial to identify RNA methylation-associated lncRNAs with definitive prognostic value. We used Pearson correlation analysis to construct a 5-Methylcytosine (m5C)-related lncRNAs–mRNAs coexpression network. Univariate and multivariate Cox proportional risk analyses were then used to determine a risk model for m5C-associated lncRNAs with prognostic value. The risk model was verified using Kaplan–Meier analysis, univariate and multivariate Cox regression analysis, and receiver operating characteristic curve analysis. We used principal component analysis and gene set enrichment analysis functional annotation to analyze the risk model. We also verified the expression level of m5C-related lncRNAs in vitro. The association between the risk model and tumor-infiltrating immune cells was assessed using the CIBERSORT tool and the TIMER database. Based on these analyses, a total of 14 m5C-related lncRNAs with prognostic value were selected to build the risk model. Patients were divided into high- and low-risk groups according to the median risk score. The prognosis of the high-risk group was worse than that of the low-risk group, suggesting the good sensitivity and specificity of the constructed risk model. In addition, 5 types of immune cells were significantly different in the high-and low-risk groups, and 6 types of immune cells were negatively correlated with the risk score. These results suggested that the risk model based on 14 m5C-related lncRNAs with prognostic value might be a promising prognostic tool for LUAD and might facilitate the management of patients with LUAD.

Recent advances in functional annotation and prediction of the epitranscriptome

RNA modifications, in particular N⁶-methyladenosine (m⁶A), participate in every stages of RNA metabolism and play diverse roles in essential biological processes and disease pathogenesis. Thanks to the advances in sequencing technology, tens of thousands of RNA modification sites can be identified in a typical high-throughput experiment; however, it remains a major challenge to decipher the functional relevance of these sites, such as, affecting alternative splicing, regulation circuit in essential biological processes or association to diseases. As the focus of RNA epigenetics gradually shifts from site discovery to functional studies, we review here recent progress in functional annotation and prediction of RNA modification sites from a bioinformatics perspective. The review covers naïve annotation with associated biological events, e.g., single nucleotide polymorphism (SNP), RNA binding protein (RBP) and alternative splicing, prediction of key sites and their regulatory functions, inference of disease association, and mining the diagnosis and prognosis value of RNA modification regulators. We further discussed the limitations of existing approaches and some future perspectives.

RNA modifications in cardiovascular diseases, the potential therapeutic targets

More than one hundred RNA modifications decorate the chemical and topological properties of these ribose nucleotides, thereby executing their biological functions through post-transcriptional regulation. In cardiovascular diseases, a wide range of RNA modifications including m⁶A (N6-adenosine methylation), m⁵C (5-methylcytidin), Nm (2'-O-ribose-methylation), Ψ (pseudouridine), m⁷G (N7-methylguanosine), and m¹A (N1-adenosine methylation) have been found in tRNA, rRNA, mRNA and other noncoding RNA, which can function as a novel mechanism in metabolic syndrome, heart failure, coronary heart disease, and hypertension. In this review, we will summarize the current understanding of the regulatory roles and significance of several types of RNA modifications in CVDs (cardiovascular diseases) and the interplay between RNA modifications and noncoding RNA, epigenetics. Finally, we will focus on the potential therapeutic strategies by using RNA modifications.

Prognostic Significance and Tumor Immune Microenvironment Heterogenicity of m5C RNA Methylation Regulators in Triple-Negative Breast Cancer

Purpose

The m5C RNA methylation regulators are closely related to tumor proliferation, occurrence, and metastasis. This study aimed to investigate the gene expression, clinicopathological characteristics, and prognostic value of m5C regulators in triple-negative breast cancer (TNBC) and their correlation with the tumor immune microenvironment (TIM).

Methods

The TNBC data, Luminal BC data and HER2 positive BC data set were obtained from The Cancer Genome Atlas and Gene Expression Omnibus, and 11 m5C RNA methylation regulators were analyzed. Univariate Cox regression and the least absolute shrinkage and selection operator regression models were used to develop a prognostic risk signature. The UALCAN and cBioportal databases were used to analyze the gene characteristics and gene alteration frequency of prognosis-related m5C RNA methylation regulators. Gene set enrichment analysis was used to analyze cellular pathways enriched by prognostic factors. The Tumor Immune Single Cell Hub (TISCH) and Timer online databases were used to explore the relationship between prognosis-related genes and the TIM.

Results

Most of the 11 m5C RNA methylation regulators were differentially expressed in TNBC and normal samples. The prognostic risk signature showed good reliability and an independent prognostic value. Prognosis-related gene mutations were mainly amplified. Concurrently, the NOP2/Sun domain family member 2 (NSUN2) upregulation was closely related to spliceosome, RNA degradation, cell cycle signaling pathways, and RNA polymerase. Meanwhile, NSUN6 downregulation was related to extracellular matrix receptor interaction, metabolism, and cell adhesion. Analysis of the TISCH and Timer databases showed that prognosis-related genes affected the TIM, and the subtypes of immune-infiltrating cells differed between NSUN2 and NSUN6.

Conclusion

Regulatory factors of m5C RNA methylation can predict the clinical prognostic risk of TNBC patients and affect tumor development and the TIM. Thus, they have the potential to be a novel prognostic marker of TNBC, providing clues for understanding the RNA epigenetic modification of TNBC.

m7GDisAI: N7-methylguanosine (m7G) sites and diseases associations inference based on heterogeneous network

Background

Recent studies have confirmed that N7-methylguanosine (m⁷G) modification plays an important role in regulating various biological processes and has associations with multiple diseases. Wet-lab experiments are cost and time ineffective for the identification of disease-associated m⁷G sites. To date, tens of thousands of m⁷G sites have been identified by high-throughput sequencing approaches and the information is publicly available in bioinformatics databases, which can be leveraged to predict potential disease-associated m⁷G sites using a computational perspective. Thus, computational methods for m⁷G-disease association prediction are urgently needed, but none are currently available at present.

Results

To fill this gap, we collected association information between m⁷G sites and diseases, genomic information of m⁷G sites, and phenotypic information of diseases from different databases to build an m⁷G-disease association dataset. To infer potential disease-associated m⁷G sites, we then proposed a heterogeneous network-based model, m⁷G Sites and Diseases Associations Inference (m⁷GDisAI) model. m⁷GDisAI predicts the potential disease-associated m⁷G sites by applying a matrix decomposition method on heterogeneous networks which integrate comprehensive similarity information of m⁷G sites and diseases. To evaluate the prediction performance, 10 runs of tenfold cross validation were first conducted, and m⁷GDisAI got the highest AUC of 0.740(± 0.0024). Then global and local leave-one-out cross validation (LOOCV) experiments were implemented to evaluate the model’s accuracy in global and local situations respectively. AUC of 0.769 was achieved in global LOOCV, while 0.635 in local LOOCV. A case study was finally conducted to identify the most promising ovarian cancer-related m⁷G sites for further functional analysis. Gene Ontology (GO) enrichment analysis was performed to explore the complex associations between host gene of m⁷G sites and GO terms. The results showed that m⁷GDisAI identified disease-associated m⁷G sites and their host genes are consistently related to the pathogenesis of ovarian cancer, which may provide some clues for pathogenesis of diseases.

Conclusion

The m⁷GDisAI web server can be accessed at http://180.208.58.66/m7GDisAI/, which provides a user-friendly interface to query disease associated m⁷G. The list of top 20 m⁷G sites predicted to be associted with 177 diseases can be achieved. Furthermore, detailed information about specific m⁷G sites and diseases are also shown.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04007-9.

A brief review of RNA modification related database resources

To date, over 150 different RNA modifications have been identified, playing crucial roles in biological processes and disease pathogenesis. Thanks to the advancement of high-throughput sequencing technologies employed for transcriptome-wide mapping, a bunch of RNA modification databases have emerged as an exciting area, which promotes further investigation of the mechanisms and functions of these modified ribonucleotides. This article introduces the high-throughput sequencing technique developed for transcriptome-wide mapping of RNA modifications, as well as the procedures and main techniques of building these databases from the developers' perspective. It also reviews existing RNA modification databases in terms of their main functions, species, the number of sites they collected, the annotations, and the tools they provided. From the view of users, we further analyze and compare these databases in terms of their functions. For instance, these databases can be applied to record chemical structures and biosynthetic pathways, or unravel the epi-transcriptome comprehensively, or only investigate specific features of RNA modifications. Additionally, the limitations of the existing approaches are discussed, and some future suggestions are offered.

HN-CNN: A Heterogeneous Network Based on Convolutional Neural Network for m7 G Site Disease Association Prediction

N⁷-methylguanosine (m⁷G) is a typical positively charged RNA modification, playing a vital role in transcriptional regulation. m⁷G can affect the biological processes of mRNA and tRNA and has associations with multiple diseases including cancers. Wet-lab experiments are cost and time ineffective for the identification of disease-related m⁷G sites. Thus, a heterogeneous network method based on Convolutional Neural Networks (HN-CNN) has been proposed to predict unknown associations between m⁷G sites and diseases. HN-CNN constructs a heterogeneous network with m⁷G site similarity, disease similarity, and disease-associated m⁷G sites to formulate features for m⁷G site-disease pairs. Next, a convolutional neural network (CNN) obtains multidimensional and irrelevant features prominently. Finally, XGBoost is adopted to predict the association between m⁷G sites and diseases. The performance of HN-CNN is compared with Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), as well as Gradient Boosting Decision Tree (GBDT) through 10-fold cross-validation. The average AUC of HN-CNN is 0.827, which is superior to others.

Potential regulatory role of epigenetic RNA methylation in cardiovascular diseases

Cardiovascular diseases (CVDs) are the leading cause of morbidity and mortality worldwide, especially in developing countries. To date, several approaches have been proposed for the prevention and treatment of CVDs. However, the increased risk of developing cardiovascular events that result in hospitalization has become a growing public health concern. The pathogenesis of CVDs has been analyzed from various perspectives. Recent data suggest that regulatory RNAs play a multidimensional role in the development of CVDs. Studies have identified several mRNA modifications that have contributed to the functional characterization of various cardiac diseases. RNA methylation, such as N6-methyladenosine, N1-methyladenosine, 5-methylcytosine, N7-methylguanosine, N4-acetylcytidine, and 2'-O-methylation are novel epigenetic modifications that affect the regulation of cell growth, immunity, DNA damage, calcium signaling, apoptosis, and aging in cardiomyocytes. In this review, we summarize the role of RNA methylation in the pathophysiology of CVDs and the potential of using epigenetics to treat such disorders.

RMDisease: a database of genetic variants that affect RNA modifications, with implications for epitranscriptome pathogenesis

Deciphering the biological impacts of millions of single nucleotide variants remains a major challenge. Recent studies suggest that RNA modifications play versatile roles in essential biological mechanisms, and are closely related to the progression of various diseases including multiple cancers. To comprehensively unveil the association between disease-associated variants and their epitranscriptome disturbance, we built RMDisease, a database of genetic variants that can affect RNA modifications. By integrating the prediction results of 18 different RNA modification prediction tools and also 303,426 experimentally-validated RNA modification sites, RMDisease identified a total of 202,307 human SNPs that may affect (add or remove) sites of eight types of RNA modifications (m6A, m5C, m1A, m5U, Ψ, m6Am, m7G and Nm). These include 4,289 disease-associated variants that may imply disease pathogenesis functioning at the epitranscriptome layer. These SNPs were further annotated with essential information such as post-transcriptional regulations (sites for miRNA binding, interaction with RNA-binding proteins and alternative splicing) revealing putative regulatory circuits. A convenient graphical user interface was constructed to support the query, exploration and download of the relevant information. RMDisease should make a useful resource for studying the epitranscriptome impact of genetic variants via multiple RNA modifications with emphasis on their potential disease relevance. RMDisease is freely accessible at: www.xjtlu.edu.cn/biologicalsciences/rmd.

m5UPred: A Web Server for the Prediction of RNA 5-Methyluridine Sites from Sequences

As one of the widely occurring RNA modifications, 5-methyluridine (m5U) has recently been shown to play critical roles in various biological functions and disease pathogenesis, such as under stress response and during breast cancer development. Precise identification of m5U sites on RNA is vital for the understanding of the regulatory mechanisms of RNA life. We present here m5UPred, the first web server for in silico identification of m5U sites from the primary sequences of RNA. Built upon the support vector machine (SVM) algorithm and the biochemical encoding scheme, m5UPred achieved reasonable prediction performance with the area under the receiver operating characteristic curve (AUC) greater than 0.954 by 5-fold cross-validation and independent testing datasets. To critically test and validate the performance of our newly proposed predictor, the experimentally validated m5U sites were further separated by high-throughput sequencing techniques (miCLIP-Seq and FICC-Seq) and cell types (HEK293 and HAP1). When tested on cross-technique and cross-cell-type validation using independent datasets, m5UPred achieved an average AUC of 0.922 and 0.926 under mature mRNA mode, respectively, showing reasonable accuracy and reliability. The m5UPred web server is freely accessible now and it should make a useful tool for the researchers who are interested in m5U RNA modification.

Iterative feature representation algorithm to improve the predictive performance of N7-methylguanosine sites

MOTIVATION

N7-methylguanosine (m7G) is an important epigenetic modification, playing an essential role in gene expression regulation. Therefore, accurate identification of m7G modifications will facilitate revealing and in-depth understanding their potential functional mechanisms. Although high-throughput experimental methods are capable of precisely locating m7G sites, they are still cost ineffective. Therefore, it's necessary to develop new methods to identify m7G sites.

RESULTS

In this work, by using the iterative feature representation algorithm, we developed a machine learning based method, namely m7G-IFL, to identify m7G sites. To demonstrate its superiority, m7G-IFL was evaluated and compared with existing predictors. The results demonstrate that our predictor outperforms existing predictors in terms of accuracy for identifying m7G sites. By analyzing and comparing the features used in the predictors, we found that the positive and negative samples in our feature space were more separated than in existing feature space. This result demonstrates that our features extracted more discriminative information via the iterative feature learning process, and thus contributed to the predictive performance improvement.

Prediction of N7-methylguanosine sites in human RNA based on optimal sequence features

N-7 methylguanosine (m7G) modification is a ubiquitous post-transcriptional RNA modification which is vital for maintaining RNA function and protein translation. Developing computational tools will help us to easily predict the m7G sites in RNA sequence. In this work, we designed a sequence-based method to identify the modification site in human RNA sequences. At first, several kinds of sequence features were extracted to code m7G and non-m7G samples. Subsequently, we used mRMR, F-score, and Relief to obtain the optimal subset of features which could produce the maximum prediction accuracy. In 10-fold cross-validation, results showed that the highest accuracy is 94.67% achieved by support vector machine (SVM) for identifying m7G sites in human genome. In addition, we examined the performances of other algorithms and found that the SVM-based model outperformed others. The results indicated that the predictor could be a useful tool for studying m7G. A prediction model is available at https://github.com/MapFM/m7g_model.git.

Prediction of RNA Methylation Status From Gene Expression Data Using Classification and Regression Methods

RNA N 6-methyladenosine (m6A) has emerged as an important epigenetic modification for its role in regulating the stability, structure, processing, and translation of RNA. Instability of m6A homeostasis may result in flaws in stem cell regulation, decrease in fertility, and risk of cancer. To this day, experimental detection and quantification of RNA m6A modification are still time-consuming and labor-intensive. There is only a limited number of epitranscriptome samples in existing databases, and a matched RNA methylation profile is not often available for a biological problem of interests. As gene expression data are usually readily available for most biological problems, it could be appealing if we can estimate the RNA methylation status from gene expression data using in silico methods. In this study, we explored the possibility of computational prediction of RNA methylation status from gene expression data using classification and regression methods based on mouse RNA methylation data collected from 73 experimental conditions. Elastic Net-regularized Logistic Regression (ENLR), Support Vector Machine (SVM), and Random Forests (RF) were constructed for classification. Both SVM and RF achieved the best performance with the mean area under the curve (AUC) = 0.84 across samples; SVM had a narrower AUC spread. Gene Site Enrichment Analysis was conducted on those sites selected by ENLR as predictors to access the biological significance of the model. Three functional annotation terms were found statistically significant: phosphoprotein, SRC Homology 3 (SH3) domain, and endoplasmic reticulum. All 3 terms were found to be closely related to m6A pathway. For regression analysis, Elastic Net was implemented, which yielded a mean Pearson correlation coefficient = 0.68 and a mean Spearman correlation coefficient = 0.64. Our exploratory study suggested that gene expression data could be used to construct predictors for m6A methylation status with adequate accuracy. Our work showed for the first time that RNA methylation status may be predicted from the matched gene expression data. This finding may facilitate RNA modification research in various biological contexts when a matched RNA methylation profile is not available, especially in the very early stage of the study.

Bioinformatics approaches for deciphering the epitranscriptome: Recent progress and emerging topics

Post-transcriptional RNA modification occurs on all types of RNA and plays a vital role in regulating every aspect of RNA function. Thanks to the development of high-throughput sequencing technologies, transcriptome-wide profiling of RNA modifications has been made possible. With the accumulation of a large number of high-throughput datasets, bioinformatics approaches have become increasing critical for unraveling the epitranscriptome. We review here the recent progress in bioinformatics approaches for deciphering the epitranscriptomes, including epitranscriptome data analysis techniques, RNA modification databases, disease-association inference, general functional annotation, and studies on RNA modification site prediction. We also discuss the limitations of existing approaches and offer some future perspectives.

PSI-MOUSE: Predicting Mouse Pseudouridine Sites From Sequence and Genome-Derived Features

Pseudouridine (Ψ) is the first discovered and the most prevalent posttranscriptional modification, which has been widely studied during the past decades. Pseudouridine was observed in almost all kinds of RNAs and shown to have important biological functions. Currently, the time-consuming and high-cost procedures of experimental approaches limit its uses in real-life Ψ site detection. Alternatively, by taking advantage of the explosive growth of Ψ sequencing data, the computational methods may provide a more cost-effective avenue. To date, the existing mouse Ψ site predictors were all developed based on sequence-derived features, and their performance can be further improved by adding the domain knowledge derived feature. Therefore, it is highly desirable to propose a genomic feature-based computational method to increase the accuracy and efficiency of the identification of Ψ RNA modification in the mouse transcriptome. In our study, a predictive framework PSI-MOUSE was built. Besides the conventional sequence-based features, PSI-MOUSE first introduced 38 additional genomic features derived from the mouse genome, which achieved a satisfactory improvement in the prediction performance, compared with other existing models. Moreover, PSI-MOUSE also features in automatically annotating the putative Ψ sites with diverse types of posttranscriptional regulations (RNA-binding protein [RBP]-binding regions, miRNA-RNA interactions, and splicing sites), which can serve as a useful research tool for the study of Ψ RNA modification in the mouse genome. Finally, 3282 experimentally validated mouse Ψ sites were also collected in a database with customized query functions. For the convenience of academic users, a website was built to provide a user-friendly interface for the query and analysis on the database. The website is freely accessible at www.xjtlu.edu.cn/biologicalsciences/psimouse and http://psimouse.rnamd.com. We introduced the genome-derived features to mouse for the first time, and we achieved a good performance in mouse Ψ site prediction. Compared with the existing state-of-art methods, our newly developed approach PSI-MOUSE obtained a substantial improvement in prediction accuracy, marking the reliable contributions of genomic features for the prediction of RNA modifications in a species other than human.