DENA: training an authentic neural network model using Nanopore sequencing data of Arabidopsis transcripts for detection and quantification of N(6)-methyladenosine on RNA

Models developed using Nanopore direct RNA sequencing data from in vitro synthetic RNA with all adenosine replaced by N(6)-methyladenosine (m(6)A) are likely distorted due to superimposed signals from saturated m(6)A residues. Here, we develop a neural network, DENA, for m(6)A quantification using the sequencing data of in vivo transcripts from Arabidopsis. DENA identifies 90% of miCLIP-detected m(6)A 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 m(6)A-deficient Arabidopsis, mtb and fip37-4, using Nanopore and evaluate their single-nucleotide m(6)A profiles using DENA. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s13059-021-02598-3.