Recent studies suggest that epi-transcriptome regulation via post-transcriptional RNA modifications is vital for all RNA types. Precise identification of RNA modification sites is essential for understanding the functions and regulatory mechanisms of RNAs. Here, we present MultiRM, a method for the integrated prediction and interpretation of post-transcriptional RNA modifications from RNA sequences. Built upon an attention-based multi-label deep learning framework, MultiRM not only simultaneously predicts the putative sites of twelve widely occurring transcriptome modifications (m⁶A, m¹A, m⁵C, m⁵U, m⁶Am, m⁷G, Ψ, I, Am, Cm, Gm, and Um), but also returns the key sequence contents that contribute most to the positive predictions. Importantly, our model revealed a strong association among different types of RNA modifications from the perspective of their associated sequence contexts. Our work provides a solution for detecting multiple RNA modifications, enabling an integrated analysis of these RNA modifications, and gaining a better understanding of sequence-based RNA modification mechanisms.

With advanced technologies to map RNA modifications, our understanding of them has been revolutionized, and they are seen to be far more widespread and important than previously thought. Current next-generation sequencing (NGS)-based modification profiling methods are blind to RNA modifications and thus require selective chemical treatment or antibody immunoprecipitation methods for particular modification types. They also face the problem of short read length, isoform ambiguities, biases and artifacts. Direct RNA sequencing (DRS) technologies, commercialized by Oxford Nanopore Technologies (ONT), enable the direct interrogation of any given modification present in individual transcripts and promise to address the limitations of previous NGS-based methods. Here, we present the first ONT-based database of quantitative RNA modification profiles, DirectRMDB, which includes 16 types of modification and a total of 904,712 modification sites in 25 species identified from 39 independent studies. In addition to standard functions adopted by existing databases, such as gene annotations and post-transcriptional association analysis, we provide a fresh view of RNA modifications, which enables exploration of the epitranscriptome in an isoform-specific manner. The DirectRMDB database is freely available at: http://www.rnamd.org/directRMDB/.

As the most pervasive epigenetic marker present on mRNAs and long non-coding RNAs (lncRNAs), N 6-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.

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.

Profiling RNA modifications is essential to understand their functions and interactions. By taking the advantages of nanopore direct RNA sequencing, we present DirectRM, enabling simultaneous detection of six abundant modifications (N4-acetylcytidine, 1-methyladenosine, 5-methylcytidine, N7-methlguanosine, N6-methyladenosine, and pseudouridine) in native RNAs. Its two-stage pipeline identifies candidate modified kmers using binary classifier, then determines specific modifications and positions using an attention-based neural network. Trained with molecule-level features extracted from native RNA samples and validated on human cell lines and viral RNAs, DirectRM demonstrates high sensitivity, precision and robustness, outperforming existing tools. Crucially, we reveal the associations between modifications at both transcript and molecule-level. Modifications tend to proximate to each other on the transcript level, while at the molecule level, the presence of one modification is likely to reduce the occurrence of modifications at adjacent positions. DirectRM offers a powerful approach for studying epitranscriptome complexity and is expandable for future research.

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.