As the most pervasive epigenetic marker present on mRNA and lncRNA, N6-methyladenosine (m6A) RNA methylation has been shown to participate in essential biological processes. Recent studies 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 modification; and (4) m6A-CAVar: a database of 587,983 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 genetic factor of epitranscriptome disturbance in a specific tissue (or cancer type). m6A-TSHub is accessible at: www.xjtlu.edu.cn/biologicalsciences/m6ats.

Background Chemically modified therapeutic mRNAs have gained its momentum recently. In addition to commonly used modifications (e.g., pseudouridine), 5moU is considered a promising substitution of uridine in therapeutic mRNAs. Accurate identification of 5-Methoxyuridine (5moU) would be crucial for the study and quality control of relevant IVT mRNAs. However, current methods exhibit deficiencies in providing comprehensive methodologies for detecting such modification. By taking advantage of Oxford nanopore direct RNA sequencing, we present here NanoML-5moU, a machine-learning framework designed specifically for the read-level detection and quantification of 5moU modification. Results Nanopore direct RNA sequencing data of 5moU-modified and unmodified control samples were collected. We then examined signal event features (i.e., current intensity means, medians, standard deviations, and dwell time) and classical machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), and XGBoost, for 5moU detection within NNUNN (N = A, C, T or G) 5-mers. The signal event features for each base of NNUNN 5-mers, plus the XGBoost algorithm achieved exceptional performance (maximum AUROC = 0.9567 in “AGTTC”, minimum AUROC = 0.8113 in “TGTGC”), substantially surpassing the existing background error comparison model (ELIGOs AUC 0.751 for site-level prediction). Availability: The NanoML-5moU framework is publicly available on GitHub (https://github.com/JiayiLi21/NanoML-5moU). Conclusions NanoML-5moU enables accurate read-level profiling of 5moU modification with nanopore direct RNA-sequencing, which is also transferable to the detection of other kinds of modifications and biological samples.