DENA: training an authentic neural network model using Nanopore sequencing data of Arabidopsis transcripts for detection and quantification of N6-methyladenosine on RNA

Hang Qin; Liang Ou; Jian Gao; Longxian Chen; Jia-Wei Wang; Pei Hao; Xuan Li

doi:10.1186/s13059-021-02598-3

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. 2022 Jan 17;23(1):25. doi: 10.1186/s13059-021-02598-3.

Authors

Hang Qin^#^{1

2}, Liang Ou^#^{2

3}, Jian Gao^{2

4}, Longxian Chen^{1

2}, Jia-Wei Wang^{5

6}, Pei Hao^{7

8}, Xuan Li^{9

10}

Affiliations

¹ Key Laboratory of Synthetic Biology, CAS Center for Excellence in Molecular Plant Sciences, Institute of Plant Physiology and Ecology, Chinese Academy of Sciences, Shanghai, China.
² University of Chinese Academy of Sciences, Beijing, China.
³ Key Laboratory of Molecular Virology and Immunology, Institut Pasteur of Shanghai, Chinese Academy of Sciences, Shanghai, China.
⁴ National Key Laboratory of Plant Molecular Genetics, CAS Center for Excellence in Molecular Plant Sciences, Institute of Plant Physiology and Ecology, Chinese Academic of Sciences, Shanghai, China.
⁵ University of Chinese Academy of Sciences, Beijing, China. jwwang@cemps.ac.cn.
⁶ National Key Laboratory of Plant Molecular Genetics, CAS Center for Excellence in Molecular Plant Sciences, Institute of Plant Physiology and Ecology, Chinese Academic of Sciences, Shanghai, China. jwwang@cemps.ac.cn.
⁷ University of Chinese Academy of Sciences, Beijing, China. phao@ips.ac.cn.
⁸ Key Laboratory of Molecular Virology and Immunology, Institut Pasteur of Shanghai, Chinese Academy of Sciences, Shanghai, China. phao@ips.ac.cn.
⁹ Key Laboratory of Synthetic Biology, CAS Center for Excellence in Molecular Plant Sciences, Institute of Plant Physiology and Ecology, Chinese Academy of Sciences, Shanghai, China. lixuan@cemps.ac.cn.
¹⁰ University of Chinese Academy of Sciences, Beijing, China. lixuan@cemps.ac.cn.

^# Contributed equally.

Abstract

Models developed using Nanopore direct RNA sequencing data from in vitro synthetic RNA with all adenosine replaced by N⁶-methyladenosine (m⁶A) are likely distorted due to superimposed signals from saturated m⁶A residues. Here, we develop a neural network, DENA, for m⁶A quantification using the sequencing data of in vivo transcripts from Arabidopsis. DENA identifies 90% of miCLIP-detected m⁶A sites in Arabidopsis and obtains modification rates in human consistent to those found by SCARLET, demonstrating its robustness across species. We sequence the transcriptome of two additional m⁶A-deficient Arabidopsis, mtb and fip37-4, using Nanopore and evaluate their single-nucleotide m⁶A profiles using DENA.

Keywords: Arabidopsis thaliana; AtFIP37; AtMTB; DENA; N 6-Methyladenosine; Nanopore direct RNA sequencing.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adenosine / analogs & derivatives
Arabidopsis* / genetics
Humans
Nanopore Sequencing*
Nanopores*
Neural Networks, Computer
RNA
RNA, Messenger / genetics
Transcriptome

Substances

RNA, Messenger
RNA
N-methyladenosine
Adenosine