Identifying RNA editing sites using RNA sequencing data alone

Abstract

We show that RNA editing sites can be called with high confidence using RNA sequencing data from multiple samples across either individuals or species, without the need for matched genomic DNA sequence. We identified many previously unidentified editing sites in both humans and Drosophila; our results nearly double the known number of human protein recoding events. We also found that human genes harboring conserved editing sites within Alu repeats are enriched for neuronal functions.

Figure 1

Identification and validation of A-to-I RNA editing sites using RNA-seq data from human brain tissues. (a,b) Overview of the separate samples method (a) and the pooled samples method (b). (c,d) Identification of editing sites using the separate samples method. Minimum number of samples containing each variant relative to the proportion of variants that are either A-to-G or T-to-C mismatches (c). Variants were required to be supported by at least one read in each sample in c. Percentage of all 12 mismatch types (d); variants in Alu and non-Alu regions were required to be present in least one or two samples, respectively. (e,f) Identification of editing sites using the pooled samples method. Minimum number of reads supporting each variant relative to the proportion of variants that are either A-to-G or T-to-C mismatches (e). Percentage of all 12 mismatch types (f); variants in Alu and non-Alu regions were required to be supported by at least one or two reads, respectively. (g) RNA editing levels of 115 nonsynonymous nonrepetitive editing sites measured using the pooled alignments for all 50 brain data samples. Editing sites covered by less than 20 reads are identified as open diamonds. Measurements of RNA editing levels for each site in each sample (where ≥ 10 reads were available) are shown by error bars, with highest and lowest editing levels observed. Previously unidentified sites that were validated are marked with an ‘×’ on the x axis; previously unidentified sites that were not validated by PCR are marked with open circles on the x axis.

Figure 2

Accurate identification of RNA editing sites in the primate lineage. (a–c) Relationship between the A-to-G proportion of detected mismatches and the minimum editing level in Alu (a), repetitive non-Alu (b) and nonrepetitive regions (c). (d) Phylogenetic relationships among the four analyzed mammalian species (left); Myr: million years ago. Number of conserved A-to-G variants that were identified in human and each of the other three selected species (right), with a magnification for variants in non-Alu regions (bottom). (e) Functional enrichment in transcripts with edited Alu repeats. The conserved editing sites in Alu repeats, sites edited in human and chimpanzee and/or rhesus macaque brains, occur in 1,400 genes. As controls, we collected two groups of genes (1,065 and 831, respectively) with editing sites in Alu repeats that were edited in human only (Online Methods). The P values (Expression Analysis Systematic Explorer (EASE) scores) shown on the x axis were corrected for multiple hypotheses testing using the Benjamini-Hochberg method.

Figure 3

RNA editing site identification in Drosophila. (a) A-to-G proportion of detected mismatches relative to the minimum editing level for the species labeled in b. (b) Number of A-to-G variants relative to the minimum editing level. (c) RNA editing levels of 863 editing sites measured from the heads of male wild-type and Adar^5G1 mutant flies. (d) Phylogenetic relationships among the four analyzed Drosophila species (left). Myr: Million years ago. Numbers of A-to-G variants identified in D. melanogaster and each of the other three selected Drosophila species analyzed (right).