ReDD: RNA editing detection by direct RNA sequencing and deep learning

Many previous studies, including the Next Generation Sequencing (NGS)-based ones, have shown the critical roles of RNA editing in biomedicine. Direct RNA sequencing emerges as another powerful technique to advance the understanding of RNA editing by new paradigms, especially in single-molecule and long-range characterization. The urgent gap is the accurate and robust identification of RNA editing at the single-molecule and single-nucleotide resolution from direct RNA sequencing. This is challenging due to the inherent nature of the context-dependence on the raw signals, which requires enormous training data with considerable diversity. Here we propose two coupled measures to address them: 1) an abductive deep learning strategy implemented as the software ReDD fully utilizes the widely accessible NGS-based RNA editing data as indirect labels of direct RNA sequencing to achieve the detection at the single-molecule level; 2) a cloud-based platform Argo-ReDD serves as a central database for assembling large and diverse data from the community to continuously train the abductive deep learning model, which also meets the community demand of a user-friendly way to perform RNA editing analyses, such as co-occurrence analysis, quantitative analysis and gene isoform-resolved analysis, based on the specific information from direct RNA sequencing. We generated definitive endoderm and pharyngeal endoderm, and primordial germ cell-like cells from human ESC, using the in vitro differentiation systems we have recently developed. We also generated HEK293T ADAR1(E912A/E912A) cells using the E912A mutation method we have previously developed.We further transfected the E912A cells with the ADAR2 gRNAs of "TGTAGAAACACTTATCACCT" and "ACCATCTTTACCTGGCAGTT", and selected single clone cells to create the HEK293T double mutant cells with ADAR1(E912A/E912A) and ADAR2(-/-). We generate long-read RNA-seq data using Oxford Nanopore Technologies (ONT) direct RNA sequencing (dRNA-ONT) protocols with one replicate and short-read RNA-seq data using Illumina with three replicates. We detects the A-to-I RNA editing sites in HEK293T, H1 and H9 cells by ReDD, our in-house software on the direct RNA sequencing data.