EUVIMEDEUVIMED entdecken
Open Access

Detecting m6A RNA modification from nanopore sequencing using a semisupervised learning framework

Haotian Teng iD, Marcus Stoiber, Ziv Bar-Joseph iD, Carl Kingsford iD

Genome Research · 2024-11 · 34 (11) · 1987-1999

DOI: 10.1101/gr.278960.124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genome Research, online erschienen am 15.10.2024. Verfasst von Haotian Teng und 3 weiteren Autor:innen. Beteiligte Einrichtung: Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA. Hauptthemen laut MEDLINE: Nanopore Sequencing, Adenosine. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHGRI NIH HHS, US National Science Foundation, US National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Direct nanopore-based RNA sequencing can be used to detect posttranscriptional base modifications, such as N6-methyladenosine (m6A) methylation, based on the electric current signals produced by the distinct chemical structures of modified bases. A key challenge is the scarcity of adequate training data with known methylation modifications. We present Xron, a hybrid encoder–decoder framework that delivers a direct methylation-distinguishing basecaller by training on synthetic RNA data and immunoprecipitation (IP)-based experimental data in two steps. First, we generate data with more diverse modification combinations through in silico cross-linking. Second, we use this data set to train an end-to-end neural network basecaller followed by fine-tuning on IP-based experimental data with label smoothing. The trained neural network basecaller outperforms existing methylation detection methods on both read-level and site-level prediction scores. Xron is a standalone, end-to-end m6A-distinguishing basecaller capable of detecting methylated bases directly from raw sequencing signals, enabling de novo methylome assembly.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Nanopore SequencingAdenosineMethylationHumansNeural Networks, ComputerRNARNA Processing, Post-TranscriptionalSequence Analysis, RNAMachine LearningRNA Methylation

Substanzen

AdenosineN-methyladenosineRNA

Autor:innen und Institutionen

  • Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA.
  • Oxford Nanopore Technologies, Alameda, California 94501-1170, USA.
  • Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA; carlk@cs.cmu.edu.

ORCID-Profile: Haotian Teng, Ziv Bar-Joseph, Carl Kingsford

Förderung

  • NHGRI NIH HHS
  • US National Science Foundation
  • US National Institutes of Health
  • Oxford Nanopore Technologies plc
  • School of Computer Science
  • Carnegie Mellon University

Zitieren

APA

Teng, H., Stoiber, M., Bar-Joseph, Z., & Kingsford, C. (2024). Detecting m6A RNA modification from nanopore sequencing using a semisupervised learning framework. Genome Research, 34(11), 1987-1999. https://doi.org/10.1101/gr.278960.124

Vancouver

Teng H, Stoiber M, Bar-Joseph Z, Kingsford C. Detecting m6A RNA modification from nanopore sequencing using a semisupervised learning framework. Genome Research. 2024;34(11):1987-1999. doi:10.1101/gr.278960.124

BibTeX
@article{Teng2024,
  author = {Teng, Haotian and Stoiber, Marcus and Bar-Joseph, Ziv and Kingsford, Carl},
  title = {Detecting m6A RNA modification from nanopore sequencing using a semisupervised learning framework},
  journal = {Genome Research},
  year = {2024},
  volume = {34},
  number = {11},
  pages = {1987--1999},
  doi = {10.1101/gr.278960.124}
}
Kostenlos starten →