Deep learning and direct sequencing of labeled RNA captures
transcriptome dynamics

J 2024

Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics

MARTINEK, Vlastimil; Jessica MARTIN; Cedric BELAIR; Matthew J PAYEA; Sulochan MALLA et al.

Základní údaje

Originální název

Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics

Autoři

MARTINEK, Vlastimil; Jessica MARTIN; Cedric BELAIR; Matthew J PAYEA; Sulochan MALLA; Panagiotis ALEXIOU a Manolis MARAGKAKIS

Vydání

NAR Genomics and Bioinformatics, Oxford University Press, 2024, 2631-9268

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10608 Biochemistry and molecular biology

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.800

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14740/24:00137071

Organizační jednotka

Středoevropský technologický institut

Klíčová slova anglicky

deep learning; sequencing methods

Štítky

143160, CF BIOIT, rivok

Příznaky

Recenzováno

Změněno: 25. 3. 2025 12:42, Mgr. Eva Dubská

Anotace

V originále

In eukaryotes, genes produce a variety of distinct RNA isoforms, each with potentially unique protein products, coding potential or regulatory signals such as poly(A) tail and nucleotide modifications. Assessing the kinetics of RNA isoform metabolism, such as transcription and decay rates, is essential for unraveling gene regulation. However, it is currently impeded by lack of methods that can differentiate between individual isoforms. Here, we introduce RNAkinet, a deep convolutional and recurrent neural network, to detect nascent RNA molecules following metabolic labeling with the nucleoside analog 5-ethynyl uridine and long-read, direct RNA sequencing with nanopores. RNAkinet processes electrical signals from nanopore sequencing directly and distinguishes nascent from pre-existing RNA molecules. Our results show that RNAkinet prediction performance generalizes in various cell types and organisms and can be used to quantify RNA isoform half-lives. RNAkinet is expected to enable the identification of the kinetic parameters of RNA isoforms and to facilitate studies of RNA metabolism and the regulatory elements that influence it.

Návaznosti

90254, velká výzkumná infrastruktura

Název: e-INFRA CZ II

90267, velká výzkumná infrastruktura

Název: NCMG III

Citovat

MARTINEK, Vlastimil; Jessica MARTIN; Cedric BELAIR; Matthew J PAYEA; Sulochan MALLA; Panagiotis ALEXIOU a Manolis MARAGKAKIS. Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics. NAR Genomics and Bioinformatics. Oxford University Press, 2024, roč. 6, č. 3, s. 1-9. ISSN 2631-9268. Dostupné z: https://doi.org/10.1093/nargab/lqae116.

@article{2431257,
   author = {Martinek, Vlastimil and Martin, Jessica and Belair, Cedric and Payea, Matthew J and Malla, Sulochan and Alexiou, Panagiotis and Maragkakis, Manolis},
   article_number = {3},
   doi = {https://doi.org/10.1093/nargab/lqae116},
   keywords = {deep learning; sequencing methods},
   language = {eng},
   issn = {2631-9268},
   journal = {NAR Genomics and Bioinformatics},
   title = {Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics},
   url = {https://academic.oup.com/nargab/article/6/3/lqae116/7744945},
   volume = {6},
   year = {2024}
}

TY  - JOUR
ID  - 2431257
AU  - Martinek, Vlastimil - Martin, Jessica - Belair, Cedric - Payea, Matthew J - Malla, Sulochan - Alexiou, Panagiotis - Maragkakis, Manolis
PY  - 2024
TI  - Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics
JF  - NAR Genomics and Bioinformatics
VL  - 6
IS  - 3
SP  - 1-9
EP  - 1-9
PB  - Oxford University Press
SN  - 26319268
KW  - deep learning
KW  - sequencing methods
UR  - https://academic.oup.com/nargab/article/6/3/lqae116/7744945
N2  - In eukaryotes, genes produce a variety of distinct RNA isoforms, each with potentially unique protein products, coding potential or regulatory signals such as poly(A) tail and nucleotide modifications. Assessing the kinetics of RNA isoform metabolism, such as transcription and decay rates, is essential for unraveling gene regulation. However, it is currently impeded by lack of methods that can differentiate between individual isoforms. Here, we introduce RNAkinet, a deep convolutional and recurrent neural network, to detect nascent RNA molecules following metabolic labeling with the nucleoside analog 5-ethynyl uridine and long-read, direct RNA sequencing with nanopores. RNAkinet processes electrical signals from nanopore sequencing directly and distinguishes nascent from pre-existing RNA molecules. Our results show that RNAkinet prediction performance generalizes in various cell types and organisms and can be used to quantify RNA isoform half-lives. RNAkinet is expected to enable the identification of the kinetic parameters of RNA isoforms and to facilitate studies of RNA metabolism and the regulatory elements that influence it.
ER  -

MARTINEK, Vlastimil; Jessica MARTIN; Cedric BELAIR; Matthew J PAYEA; Sulochan MALLA; Panagiotis ALEXIOU a Manolis MARAGKAKIS. Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics. \textit{NAR Genomics and Bioinformatics}. Oxford University Press, 2024, roč.~6, č.~3, s.~1-9. ISSN~2631-9268. Dostupné z: https://doi.org/10.1093/nargab/lqae116.

Přehled o publikaci