Abstract
RNA editing is a post-transcriptional RNA sequence alteration. Current methods have identified editing sites and facilitated research but require sufficient genomic annotations and prior-knowledge-based filtering steps, resulting in a cumbersome, time-consuming identification process. Moreover, these methods have limited generalizability and applicability in species with insufficient genomic annotations or in conditions of limited prior knowledge. We developed DeepRed, a deep learning-based method that identifies RNA editing from primitive RNA sequences without prior-knowledge-based filtering steps or genomic annotations. DeepRed achieved 98.1% and 97.9% area under the curve (AUC) in training and test sets, respectively. We further validated DeepRed using experimentally verified U87 cell RNA-seq data, achieving 97.9% positive predictive value (PPV). We demonstrated that DeepRed offers better prediction accuracy and computational efficiency than current methods with large-scale, mass RNA-seq data. We used DeepRed to assess the impact of multiple factors on editing identification with RNA-seq data from the Association of Biomolecular Resource Facilities and Sequencing Quality Control projects. We explored developmental RNA editing pattern changes during human early embryogenesis and evolutionary patterns in Drosophila species and the primate lineage using DeepRed. Our work illustrates DeepRed’s state-of-the-art performance; it may decipher the hidden principles behind RNA editing, making editing detection convenient and effective.
Highlights
RNA editing is a post-transcriptional modification[1] that makes a mature RNA sequence different from its template DNA sequence by inserting, deleting, or substituting bases
We developed DeepRed, a deep learning-based hybrid framework integrated with ensemble learning, to precisely and conveniently predict RNA editing sites using RNA-seq data alone
We developed a hybrid framework, named DeepRed, which integrates deep learning with ensemble learning to accurately identify RNA editing from RNA sequences without prior-knowledge-based filtering steps
Summary
RNA editing is a post-transcriptional modification[1] that makes a mature RNA sequence different from its template DNA sequence by inserting, deleting, or substituting bases. RNAEditor provides an easy-to-use tool to identify RNA editing events and developed a clustering algorithm to find editing islands[30] These methods, which use RNA-seq data alone with prior-knowledge-based filtering, have greatly facilitated RNA editing detection and effectively use public transcriptomic sequencing datasets without available DNA sequencing data. Arbitrary and artificial combinations of filtering steps may result in different candidate RNA editing sites These methods suffer from limited generalization and applicability to other species due to insufficient genomic annotations and prior knowledge. We found that the identified number of RNA editing sites between intact and degraded RNA and different library methods, laboratories, sequence depths, or combinations of read mapping and variant calling methods varied largely. The reproducibility of RNA editing sites in these experimental conditions are relatively low, whereas the reproducibility of RNA editing sites identified between different read mapping and variant calling methods is much higher
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have