nanoDoc: RNA modification detection using Nanopore raw reads with Deep One-Class Classification

Ueda, Hiroki

doi:10.1101/2020.09.13.295089

Cited by 23 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparative approaches do not require training data for known RNA modifications but instead use control or reference samples to detect meaningful shifts in signal-based features that correlate to the presence of modifications. Comparative methods such as Tombo 37 , DRUMMER 38 , nanoDOC 39 , Nanocompore 40 , ELIGOS 41 , xPore 42 , and Yanocomp 43 detect m6A sites by comparing with a sample with few or no m6A modifications. While these methods are accurate, their success relies on the availability of m6A-free control samples which typically involves silencing of specific writer genes which can be a limiting factor.…”

Section: Introductionmentioning

confidence: 99%

Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework

Hendra

Pratanwanich

Wan

et al. 2021

Preprint

View full text Add to dashboard Cite

RNA modifications such as m6A methylation form an additional layer of complexity in the transcriptome. Nanopore direct RNA sequencing captures this information in the raw current signal for each RNA molecule, enabling the detection of RNA modifications using supervised machine learning. However, experimental approaches provide only site-level training data, whereas the modification status for each single RNA molecule is missing. Here we present m6Anet, a neural network-based method that leverages the Multiple Instance Learning framework to specifically handle missing read-level modification labels in site-level training data. m6Anet outperforms existing computational methods, shows similar accuracy as experimental approaches, and generalises to different cell lines with almost identical accuracy. We demonstrate that m6Anet captures the underlying read-level stoichiometry that can be used to approximate differences in modification rates. m6Anet achieves this without retraining model parameters, enabling the transcriptome-wide identification and quantification of m6A from a single run of direct RNA sequencing.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework

Hendra

Pratanwanich

Wan

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The first strategy, which is implemented in tools such as Epinano 14 , DiffErr 15 , Eligos 16 , and Drummer 17 , has shown interesting results despite not considering the effects of RNA modification on the raw electrical signal; however, modern basecalling models tend to become more insensitive to common PTM, with the risk that methods of this group could quickly become ineffective at detecting modifications. On the other hand, methods based on raw signal space analyses (such as Tombo 18 , Mines 19 , xPore 20 , nanom6A 21 , nanoRMS 22 , nanoDoc 23 , Yanocomp 24 , and Penguin 25 ) can lead to richer comparative analyses, but are more complicated and come with steeper computational costs. The methods described above can be further classified into two groups: de novo detection methods, that use a trained model to identify modifications, and comparative methods, where differences between two samples are evaluated to infer the presence of a modification.…”

mentioning

confidence: 99%

RNA modifications detection by comparative Nanopore direct RNA sequencing

et al. 2021

View full text Add to dashboard Cite

RNA molecules undergo a vast array of chemical post-transcriptional modifications (PTMs) that can affect their structure and interaction properties. In recent years, a growing number of PTMs have been successfully mapped to the transcriptome using experimental approaches relying on high-throughput sequencing. Oxford Nanopore direct-RNA sequencing has been shown to be sensitive to RNA modifications. We developed and validated Nanocompore, a robust analytical framework that identifies modifications from these data. Our strategy compares an RNA sample of interest against a non-modified control sample, not requiring a training set and allowing the use of replicates. We show that Nanocompore can detect different RNA modifications with position accuracy in vitro, and we apply it to profile m6A in vivo in yeast and human RNAs, as well as in targeted non-coding RNAs. We confirm our results with orthogonal methods and provide novel insights on the co-occurrence of multiple modified residues on individual RNA molecules.

show abstract

“…Thus, even regarding the strong effort realised by several teams the last 5 years to identify precisely Nm modification on mammalian tRNA, we do not exclude the possibility that there may still be other tRNA targets of FTSJ1 that were not uncovered yet neither by MS nor by RiboMethSeq approaches. This is why we believe that a combinatorial approach is of great interest in the future for the community as well as ongoing approaches to detect Nm modification using direct RNA sequencing nanopore approach (Ueda 2020). Importantly, our RiboMethSeq results performed on NSXLID patients’ blood-derived LCLs have with confidence extended the panel of FTSJ1’s tRNA targets, thus providing new potential biomarker sources for diagnosis of FTSJ1-related intellectual disability in the future.…”

Section: Discussionmentioning

confidence: 99%

The ribose methylation enzyme FTSJ1 has a conserved role in neuron morphology and learning performance

Dimitrova

Brazane

Pigeon

et al. 2021

Preprint

View full text Add to dashboard Cite

FTSJ1 is a phyllogenetically conserved human 2-O-methyltransferase (Nm-MTase) which modifies position 32 as well as the wobble position 34 in the AntiCodon Loop (ACL) of specific tRNAs: tRNAPhe(GAA), tRNATrp(CCA) and tRNALeu(UAA). FTSJ1 loss of function has been linked to Non-Syndromic X-Linked Intellectual Disability (NSXLID), and more recently in cancers. However, the exact molecular mechanisms underlying FTSJ1-related pathogenesis are unknown and a potential extended variety of FTSJ1 tRNA targets has not been fully addressed yet. We performed unbiased and comprehensive RiboMethSeq analysis of the Nm profiles for human tRNA population extracted from cells derived from NSXLID patients blood bearing various characterized loss of function mutations in FTSJ1. In addition, we reported a novel FTSJ1 pathogenic variant from a NSXLID patient bearing a de novo mutation in the FTSJ1 gene. Some of the newly identified FTSJ1 tRNA targets are also conserved in Drosophila as shown by our previous study on the fly homologues Trm7_32 and Trm7_34, whose loss affects small RNA silencing pathways. In the current study, we reveal a conserved deregulation in both the miRNA and mRNA populations when FTSJ1 function is compromised. In addition, a cross-analysing between deregulated miRNA and mRNA obtained in FTSJ1 mutants highlighted upregulation of miR10a-5p which has the capacity to silence the SPARC gene mRNA, downregulated in FTSJ1 mutant cells. This suggests that FTSJ1 loss may influence gene expression deregulation by modulation of miRNA silencing. A gene-ontology (GO) enrichment analysis of the deregulated mRNAs primarily matched to brain morphogenesis terms, followed by metabolism and translation related genes. In parallel, the deregulated miRNAs are mostly known for their implication in brain functions and cancers. Based on these results, we suggest that miRNA silencing variations may play a role in the pathological mechanisms of FTSJ1-dependent NSXLID. Finally, our results highlight miR-181a-5p as a potential companion diagnostic test in clinical settings for FTSJ1-related intellectual disability.

show abstract

nanoDoc: RNA modification detection using Nanopore raw reads with Deep One-Class Classification

Cited by 23 publications

References 43 publications

Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework

Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework

RNA modifications detection by comparative Nanopore direct RNA sequencing

The ribose methylation enzyme FTSJ1 has a conserved role in neuron morphology and learning performance

Contact Info

Product

Resources

About