Skip to content
2000
Volume 26, Issue 11
  • ISSN: 1389-4501
  • E-ISSN: 1873-5592

Abstract

Introduction

N6-methyladenosine (m6A) is the most prevalent RNA modification in eukaryotic cells, influencing RNA lifecycle processes. Existing m6A detection methods, such as wet-lab techniques and statistical approaches, are time-consuming, labor-intensive, or require control samples, while machine learning models often lack cross-species applicability. This study aims to develop RMNet, a robust cross-species m6A detection method using nanopore sequencing.

Methods

RMNet employs Conformer and RNN architectures, integrating signal and alignment features from nanopore sequencing data. Contrastive learning enhances differentiation between m6A and non-m6A sites. The model was trained and tested on datasets from synthesized RNA, Arabidopsis, and human samples, using a single set of model weights.

Results

RMNet achieved state-of-the-art performance with accuracies of 99.7% for synthesized RNA, 78.8% for , and 88.9% for human datasets. It outperformed existing methods (m6Anet, DENA, and RedNano) across six metrics, including AUC and AUPR, demonstrating robust cross-species generalization.

Discussion

RMNet’s ability to detect m6A sites across diverse species with a single model addresses limitations of species-specific models. Its high sensitivity and feature representation enable applications in cancer research, neurodevelopmental studies, and plant biology. Limitations include higher error rates in human datasets for thymine-rich k-mers, likely due to complex secondary structures.

Conclusion

RMNet provides an efficient, powerful tool for cross-species m6A detection, advancing epitranscriptomics research with potential applications in precision medicine and agricultural science.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cdt/10.2174/0113894501405283250627072052
2025-07-04
2026-01-26

  • From This Site

    /content/journals/cdt/10.2174/0113894501405283250627072052
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. LiW. LiX. MaX. XiaoW. ZhangJ. Mapping the m1A, m5C, m6A and m7G methylation atlas in zebrafish brain under hypoxic conditions by MeRIP-seq.BMC Genomics202223110510.1186/s12864‑022‑08350‑w 35135476
     [Google Scholar]
  2. XiaW. LiuY. LuJ. CheungH.H. MengQ. HuangB. RNA methylation in neurodevelopment and related diseases.Acta Biochim. Biophys. Sin. (Shanghai)202456121723173210.3724/abbs.2024159 39344412
     [Google Scholar]
  3. HuJ. ManduzioS. KangH. Epitranscriptomic RNA methylation in plant development and abiotic stress responses.Front Plant Sci20191050010.3389/fpls.2019.00500 31110512
     [Google Scholar]
  4. WangR. JiangY. JinJ. DeepBIO: An automated and interpretable deep-learning platform for high-throughput biological sequence prediction, functional annotation and visualization analysis.Nucleic Acids Res.20235173017302910.1093/nar/gkad055 36796796
     [Google Scholar]
  5. BoccalettoP. StefaniakF. RayA. MODOMICS: A database of RNA modification pathways. 2021 update.Nucleic Acids Res.202250D1D231D23510.1093/nar/gkab1083 34893873
     [Google Scholar]
  6. ShindeH. DudhateA. KadamU.S. HongJ.C. RNA methylation in plants: An overview.Front Plant Sci202314113295910.3389/fpls.2023.1132959 36938064
     [Google Scholar]
  7. ShenL. LiangZ. WongC.E. YuH. Messenger RNA modifications in plants.Trends Plant Sci.201924432834110.1016/j.tplants.2019.01.005 30745055
     [Google Scholar]
  8. LiL. XiaX. YangT. RNA methylation: A potential therapeutic target in autoimmune disease.Int. Rev. Immunol.202443316017710.1080/08830185.2023.2280544 37975549
     [Google Scholar]
  9. LiJ. YangX. QiZ. The role of mRNA m6A methylation in the nervous system.Cell Biosci.2019916610.1186/s13578‑019‑0330‑y 31452869
     [Google Scholar]
  10. YangB. WangJ.Q. TanY. YuanR. ChenZ.S. ZouC. RNA methylation and cancer treatment.Pharmacol. Res.202117410593710.1016/j.phrs.2021.105937 34648969
     [Google Scholar]
  11. KrugR.M. MorganM.A. ShatkinA.J. Influenza viral mRNA contains internal N6-methyladenosine and 5′-terminal 7-methylguanosine in cap structures.J. Virol.1976201455310.1128/jvi.20.1.45‑53.1976 1086370
     [Google Scholar]
  12. ParkerM.T. KnopK. SherwoodA.V. Nanopore direct RNA sequencing maps the complexity of Arabidopsis mRNA processing and m6A modification.eLife20209e4965810.7554/eLife.49658 31931956
     [Google Scholar]
  13. ZhaoB.S. RoundtreeI.A. HeC. Post-transcriptional gene regulation by mRNA modifications.Nat. Rev. Mol. Cell Biol.2017181314210.1038/nrm.2016.132 27808276
     [Google Scholar]
  14. QiaoJ. JinJ. YuH. WeiL. Towards retraining-free RNA modification prediction with incremental learning.Inf. Sci.202466012010510.1016/j.ins.2024.120105
     [Google Scholar]
  15. ShenL. LiangZ. GuX. N6-Methyladenosine RNA modification regulates shoot stem cell fate in arabidopsis.Dev. Cell201638218620010.1016/j.devcel.2016.06.008 27396363
     [Google Scholar]
  16. LiuQ. GregoryR.I. RNAmod: an integrated system for the annotation of mRNA modifications.Nucleic Acids Res.201947W1W548-5510.1093/nar/gkz479 31147718
     [Google Scholar]
  17. AlarcónC.R. LeeH. GoodarziH. HalbergN. TavazoieS.F. N6-methyladenosine marks primary microRNAs for processing.Nature2015519754448248510.1038/nature14281 25799998
     [Google Scholar]
  18. NarayanP. RottmanF.M. An in vitro system for accurate methylation of internal adenosine residues in messenger RNA.Science198824248821159116210.1126/science.3187541 3187541
     [Google Scholar]
  19. SunT. WuR. MingL. The role of m6A RNA methylation in cancer.Biomed. Pharmacother.201911210861310.1016/j.biopha.2019.108613 30784918
     [Google Scholar]
  20. MeyerK.D. SaletoreY. ZumboP. nlmo O, Mason CE, Jaffrey SR. Comprehensive analysis of mRNA methylation reveals enrichment in 3′ UTRs and near stop codons.Cell201214971635164610.1016/j.cell.2012.05.003 22608085
     [Google Scholar]
  21. WeiL. ChenH. SuR. M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning.Mol. Ther. Nucleic Acids20181263564410.1016/j.omtn.2018.07.004 30081234
     [Google Scholar]
  22. LinderB. GrozhikA.V. Olarerin-GeorgeA.O. MeydanC. MasonC.E. JaffreyS.R. Single-nucleotide-resolution mapping of m6A and m6Am throughout the transcriptome.Nat. Methods201512876777210.1038/nmeth.3453 26121403
     [Google Scholar]
  23. KohC.W.Q. GohY.T. GohW.S.S. Atlas of quantitative single-base-resolution N6-methyl-adenine methylomes.Nat. Commun.2019101563610.1038/s41467‑019‑13561‑z 31822664
     [Google Scholar]
  24. CarlileT.M. Rojas-DuranM.F. ZinshteynB. ShinH. BartoliK.M. GilbertW.V. Pseudouridine profiling reveals regulated mRNA pseudouridylation in yeast and human cells.Nature2014515752514314610.1038/nature13802 25192136
     [Google Scholar]
  25. MarchandV. AyadiL. ErnstF.G.M. AlkAniline‐Seq: Profiling of m7 G and m3 C RNA modifications at single nucleotide resolution.Angew. Chem. Int. Ed.20185751167851679010.1002/anie.201810946 30370969
     [Google Scholar]
  26. Garcia-CamposM.A. EdelheitS. TothU. Deciphering the “m6A Code” via antibody-independent quantitative profiling.Cell20191783731747.e1610.1016/j.cell.2019.06.013 31257032
     [Google Scholar]
  27. ZhangZ. ChenL.Q. ZhaoY.L. Single-base mapping of m6 A by an antibody-independent method.Sci. Adv.201957eaax025010.1126/sciadv.aax0250 31281898
     [Google Scholar]
  28. WangY. ZhaoY. BollasA. WangY. AuK.F. Nanopore sequencing technology, bioinformatics and applications.Nat. Biotechnol.202139111348136510.1038/s41587‑021‑01108‑x 34750572
     [Google Scholar]
  29. DeamerD. AkesonM. BrantonD. Three decades of nanopore sequencing.Nat. Biotechnol.201634551852410.1038/nbt.3423 27153285
     [Google Scholar]
  30. LiQ. SunC. WangD. LouJ. GCRTcall: A transformer based basecaller for nanopore RNA sequencing enhanced by gated convolution and relative position embedding via joint loss training.Front. Genet.202415144353210.3389/fgene.2024.1443532 39649096
     [Google Scholar]
  31. LiQ. SunC. WangD. LouJ. BaseNet: A transformer-based toolkit for nanopore sequencing signal decoding.Comput. Struct. Biotechnol. J.2024233430344410.1016/j.csbj.2024.09.016 39391372
     [Google Scholar]
  32. YinC. WangR. QiaoJ. NanoCon: contrastive learning-based deep hybrid network for nanopore methylation detection.Bioinformatics2024402btae04610.1093/bioinformatics/btae046 38305428
     [Google Scholar]
  33. JenjaroenpunP. WongsurawatT. WadleyT.D. Decoding the epitranscriptional landscape from native RNA sequences.Nucleic Acids Res.2021492e710.1093/nar/gkaa620 32710622
     [Google Scholar]
  34. PratanwanichP.N. YaoF. ChenY. Identification of differential RNA modifications from nanopore direct RNA sequencing with xPore.Nat. Biotechnol.202139111394140210.1038/s41587‑021‑00949‑w 34282325
     [Google Scholar]
  35. LegerA. AmaralP.P. PandolfiniL. RNA modifications detection by comparative Nanopore direct RNA sequencing.Nat. Commun.2021121719810.1038/s41467‑021‑27393‑3 34893601
     [Google Scholar]
  36. VaswaniA ShazeerN ParmarN UszoreitJ JonesL Attention is all you need.arXiv201710.48550/arXiv.1706.03762
     [Google Scholar]
  37. RadfordA WuJ ChildR LuanD AmodeiD SutskeverI Language models are unsupervised multitask learners.arXiv201910.48550/arXiv.1902.00751
     [Google Scholar]
  38. DuZ QianY LiuX DingM QiuJ YangZ. GLM: General language model pretraining with autoregressive blank infilling.arXiv202110.48550/arXiv.2103.10360
     [Google Scholar]
  39. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Las Vegas, NV, USA, 27-30 June201677077810.1109/CVPR.2016.90
     [Google Scholar]
  40. DosovitskiyA. An image is worth 16x16 words: Transformers for image recognition at scale.arXiv202010.48550/arXiv.2010.11929
     [Google Scholar]
  41. RedmonJ. DivvalaS. GirshickR. You only look once: Unified, real-time object detection.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Las Vegas, NV, USA27-30 June 201677978810.1109/CVPR.2016.91
     [Google Scholar]
  42. RadfordA. RadfordA. KimJ.W. Robust speech recognition via large-scale weak supervision.International Conference on Machine Learning (ICML)Baltimore, MD, USA, 17-23 July2022284922851810.48550/arXiv.2212.04356
     [Google Scholar]
  43. BaevskiA. wav2vec 2.0: A framework for self-supervised learning of speech representations.arXiv202010.48550/arXiv.2006.11477
     [Google Scholar]
  44. GaoZ ZhangP YanC. Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition.Interspeech. Incheon, Korea, 18-22 September20221866187010.21437/Interspeech.2022‑10146
     [Google Scholar]
  45. LiQ. XuL. LiQ. ZhangL. Identification and classification of enhancers using dimension reduction technique and recurrent neural network.Comput. Math. Methods Med.202020201910.1155/2020/8852258 33133227
     [Google Scholar]
  46. LiQ. ZhouW. WangD. WangS. LiQ. Prediction of anticancer peptides using a low-dimensional feature model.Front. Bioeng. Biotechnol.2020889210.3389/fbioe.2020.00892 32903381
     [Google Scholar]
  47. LiQ. ZhangL. XuL. ZouQ. WuJ. LiQ. Identification and classification of promoters using the attention mechanism based on long short-term memory.Front. Comput. Sci.202216416434810.1007/s11704‑021‑0548‑9
     [Google Scholar]
  48. LiQ DongB WangD WangS Identification of secreted proteins from malaria protozoa with few features.IEEE Access202088979380110.1109/ACCESS.2020.2994206
     [Google Scholar]
  49. WeiL. Computational prediction and interpretation of cell-specific replication origin sites from multiple eukaryotes by exploiting stacking framework.Brief. Bioinform.2020 33152766
     [Google Scholar]
  50. LiuH. BegikO. NovoaE.M. EpiNano: Detection of m6A RNA modifications using oxford nanopore direct RNA sequencing.Methods Mol. Biol.20212298315210.1007/978‑1‑0716‑1374‑0_3 34085237
     [Google Scholar]
  51. GaoY. LiuX. WuB. Quantitative profiling of N6-methyladenosine at single-base resolution in stem-differentiating xylem of Populus trichocarpa using Nanopore direct RNA sequencing.Genome Biol.20212212210.1186/s13059‑020‑02241‑7 33413586
     [Google Scholar]
  52. HendraC. PratanwanichP.N. WanY.K. GohW.S.S. ThieryA. GökeJ. Detection of m6A from direct RNA sequencing using a multiple instance learning framework.Nat. Methods202219121590159810.1038/s41592‑022‑01666‑1 36357692
     [Google Scholar]
  53. QinH. OuL. GaoJ. DENA: training an authentic neural network model using Nanopore sequencing data of Arabidopsis transcripts for detection and quantification of N6-methyladenosine on RNA.Genome Biol.20222312510.1186/s13059‑021‑02598‑3 35039061
     [Google Scholar]
  54. NiP. XuJ. ZhongZ. LuoF. WangJ. RNA m6A detection using raw current signals and basecalling errors from Nanopore direct RNA sequencing reads.Bioinformatics2024406btae37510.1093/bioinformatics/btae375 38889266
     [Google Scholar]
  55. LiuH. BegikO. LucasM.C. Accurate detection of m6A RNA modifications in native RNA sequences.Nat. Commun.2019101407910.1038/s41467‑019‑11713‑9 31501426
     [Google Scholar]
  56. ChenT. A simple framework for contrastive learning of visual representations.arXiv202010.48550/arXiv.2002.05709
     [Google Scholar]
  57. BeltagyI. Cohan Longformer: The long-document transformers.arXiv202010.48550/arXiv.2004.05150
     [Google Scholar]
  58. WuC YinS QiW QiX LuoJ. Fastformer: Additive attention can be all you need.arXiv202110.48550/arXiv.2108.09084
     [Google Scholar]
  59. WangS. Linformer: Self-attention with linear complexity.arXiv200610.48550/arXiv.2002.05709
     [Google Scholar]
  60. DaoT. FlashAttention: Fast and memory-efficient exact attention with io-awareness.arXiv200610.48550/arXiv.2205.141359
     [Google Scholar]
  61. DaoT. FlashAttention-2: Faster attention with better parallelism and work partitioning.arXiv202310.48550/arXiv.2307.08691
     [Google Scholar]
/content/journals/cdt/10.2174/0113894501405283250627072052
Loading
RMNet: An RNA m6A Cross-species Methylation Detection Method for Nanopore Sequencing
Curr Drug Targets 26, 799 (2025); https://doi.org/10.2174/0113894501405283250627072052
/content/journals/cdt/10.2174/0113894501405283250627072052
/content/journals/cdt/10.2174/0113894501405283250627072052
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): conformer; contrastive learning; N6-methyladenosine; nanopore sequencing; plant biology; RNA

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test