Massive A-to-I RNA editing is common across the Metazoa and correlates with dsRNA abundance

Abstract

Background: Adenosine to inosine (A-to-I) RNA editing is a post-transcriptional modification catalyzed by the ADAR (adenosine deaminase that acts on RNA) enzymes, which are ubiquitously expressed among metazoans. Technical requirements have limited systematic mapping of editing sites to a small number of organisms. Thus, the extent of editing across the metazoan lineage is largely unknown.

Results: Here, we apply a computational procedure to search for RNA-sequencing reads containing clusters of editing sites in 21 diverse organisms. Clusters of editing sites are abundant in repetitive genomic regions that putatively form double-stranded RNA (dsRNA) structures and are rarely seen in coding regions. The method reveals a considerable variation in hyper-editing levels across species, which is partly explained by differences in the potential of sequences to form dsRNA structures and the variability of ADAR proteins. Several commonly used model animals exhibit low editing levels and editing levels in primates is not exceptionally high, as previously suggested.

Conclusions: Editing by ADARs is highly prevalent across the Metazoa, mostly targeting dsRNA structures formed by genomic repeats. The degree to which the transcriptome of a given species undergoes hyper-editing is governed by the repertoire of repeats in the underlying genome. The strong association of RNA editing with the long dsRNA regions originating from non-coding repetitive elements is contrasted by the almost non-existing signal seen in coding regions. Hyper-edited regions are rarely expressed in a non-edited form. These results support the notion that the main role of ADAR is to suppress the cellular response to endogenous dsRNA structures.

Fig. 1

Overview: analyzing hyper-editing across species. RNA-seq datasets of 21 species were screened for clusters of RNA A-to-I editing, using the hyper-editing pipeline [39]. The identified hyper-editing sites were then characterized, revealing an enrichment in putative dsRNA structures and evolution of the ADAR sequence preference

Fig. 2

Phylogenetic tree of the studied organisms (based on the UCSC Genome Browser [59]). The lengths of branches in the phylogenetic tree are not drawn to scale

Fig. 3

Comparing the normalized hyper-editing signal for 19 different species. The level of hyper-editing is measured by the number of A-to-G mismatches in the identified clusters per million mapped bases (standard errors bars are presented for nine species for which we had biological replicates, Additional file 1: Figure S8). For comparison, the numbers of G-to-A clusters (found using the same parameters) are presented, representing the expected false-positive rate

Fig. 4

Evolution of the ADAR sequence preference, based on the sequence context (upstream and downstream adjacent locations) of the hyper-editing sites. The motifs cluster into two groups, largely consistent with their phylogeny: most vertebrates cluster together whereas amphibian and invertebrates cluster to a different group (with one exception, opossum, which has a small number of sites and possibly a noisy motif). In both clusters, G is depleted in the upstream nucleotide, whereas the downstream nucleotide preference is different for the two clusters. The first cluster exhibits a preference for G downstream, whereas in the other one A is preferred. (Red: over-representation; blue: under-representation). The downstream nucleotide preference is determined by the residue S486 (PDB structure 5HP2), as described by Matthews et al. [45]. Presented here for each organism are the amino acids observed at this position (see also Additional file 1: Figure S3). The five species exhibiting the most different 3' preference encode ADARs with a different amino acid in this position

Fig. 5

Harbinger is the most edited repeat family in Xenopus tropicalis, belonging to the DNA repeat class. The Harbinger repeats are palindromic, likely forming tight dsRNA structures. Here we show the predicted secondary structure (using MFOLD [60]) for a single representative Harbinger repeat (221-bp in length; located at GL172703: 562862-563082) which was found to be highly hyper-edited (65/77 adenosines were found hyper-edited; marked with arrows). Clearly, tight dsRNA is formed without the requirement of nearby reverse-oriented similar repeat, explaining the high level of hyper-editing in Xenopus tropicalis. We measured the editing level for each site (using all reads, including ones that were normally aligned to the region). Strongly edited sites (>30%) are marked with red arrows, moderately edited sites (1–30%) with orange arrows, and black arrows point to sites that were not found edited by the non-hyper-edited reads (or were not covered by those reads), see also Additional file 1: Figure S7