DEMINING: A deep learning model embedded framework to distinguish RNA editing from DNA mutations in RNA sequencing data

Precise calling of promiscuous adenosine-to-inosine RNA editing sites from transcriptomic datasets is hindered by DNA mutations and sequencing/mapping errors. Here, we present a stepwise computational framework, called DEMINING, to distinguish RNA editing and DNA mutations directly from RNA sequenci...

Full description

Saved in:
Bibliographic Details
Published in:Genome Biology 2024-10, Vol.25 (1), p.258-25, Article 258
Main Authors: Fu, Zhi-Can, Gao, Bao-Qing, Nan, Fang, Ma, Xu-Kai, Yang, Li
Format: Article
Language:English
Subjects:
Deep Learning
DNA mutation
Humans
Leukemia, Myeloid, Acute - genetics
Method
Mutation
Neoantigens
RNA Editing
RNA-seq
Sequence Analysis, RNA - methods
Transfer learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Precise calling of promiscuous adenosine-to-inosine RNA editing sites from transcriptomic datasets is hindered by DNA mutations and sequencing/mapping errors. Here, we present a stepwise computational framework, called DEMINING, to distinguish RNA editing and DNA mutations directly from RNA sequencing datasets, with an embedded deep learning model named DeepDDR. After transfer learning, DEMINING can also classify RNA editing sites and DNA mutations from non-primate sequencing samples. When applied in samples from acute myeloid leukemia patients, DEMINING uncovers previously underappreciated DNA mutation and RNA editing sites; some associated with the upregulated expression of host genes or the production of neoantigens.
ISSN:1474-760X
1474-7596
1474-760X
DOI:10.1186/s13059-024-03397-2