A distant cis acting intronic element induces site-selective RNA editing

Abstract

Transcripts have been found to be site selectively edited from adenosine-to-inosine (A-to-I) in the mammalian brain, mostly in genes involved in neurotransmission. While A-to-I editing occurs at double-stranded structures, other structural requirements are largely unknown. We have investigated the requirements for editing at the I/M site in the Gabra-3 transcript of the GABA(A) receptor. We identify an evolutionarily conserved intronic duplex, 150 nt downstream of the exonic hairpin where the I/M site resides, which is required for its editing. This is the first time a distant RNA structure has been shown to be important for A-to-I editing. We demonstrate that the element also can induce editing in related but normally not edited RNA sequences. In human, thousands of genes are edited in duplexes formed by inverted repeats in non-coding regions. It is likely that numerous such duplexes can induce editing of coding regions throughout the transcriptome.

Figure 1.

Efficiency of editing at the I/M site using different Gabra-3 constructs. (A) Sanger sequencing results after RT-PCR from co-transfections of ADAR1 or ADAR2 with Gabra-3 editing reporter constructs with or without intronic sequence. Editing is detected as a dual A and G peak at the I/M site and the amount of edited transcripts is determined by measuring the ratio between the A and G peak heights. Reproducible triplicates of these measurements were compared with known levels of editing at the I/M site using 454 HTP sequencing (see ‘Materials and Methods’ section; Supplementary Figure S1). For endogenous editing the reporters were transfected into HeLa cells. (B) Putative RNA secondary structure of the Gabra-3 transcript at exon 9 and part of the intron 9. The edited I/M site as well as the exon/intron junction are indicated. The conserved intronic duplex structure is located 150 nt downstream of the I/M site.

Figure 2.

Editing efficiency at the I/M site is lower in Gabra-3 transcripts in the absence of the intronic hairpin. (A) The editing levels in transcripts derived from transfected Gabra-3 constructs and edited by co-expressed ADAR1 or ADAR2 in HEK293 as well as endogenous editing in HeLa cells. Editing was determined by Sanger sequencing measuring the ratio of the A and G peak after RT-PCR and compared with known levels of editing using 454 high throughtput (HTP) sequencing (see ‘Materials and Methods’ section; Supplementary Figure S1). Reproducible triplicates were made for each sample shown in the figure. The Δ149 lane indicates a reporter construct where 149 nt and thereby the entire intronic stem loop was deleted. As a control 149 nt downstream of the intronic stem was deleted (Δ149 d.s. int). (B) The intronic duplex influences editing of an in vitro transcribed Gabra-3 RNA. A 532 nt long transcript including Gabra-3 exon 9 and part of intron 9 (WT) was used in an ADAR2 modification assay in vitro. This was compared with in vitro editing of a reporter lacking the intronic hairpin of 149 nt (Δ149). Editing was detected by Sanger sequencing after RT-PCR.

Figure 3.

Editing at several sites in the putative intronic stem loop. (A) Chromatogram showing A-to-I editing in the intronic stem of the Gabra-3 transcripts derived from mouse brain. US indicates the upper strand, while LS equals the lower strand according to the cartoon in B. Arrows indicate the edited adenosines. (B) Cartoon showing the sequence of the edited part in the intronic hairpin. Arrows indicate the edited adenosines. (C) Sanger sequencing chromatograms showing I/M editing of the wild-type Gabra-3 editing reporter in HeLa cells compared with a reporter where 9 edited adenosines were mutated to guanosines (9A->G) and a reporter with compensatory mutations, restoring the base pairs in the intronic stem (9A->G+9U->C).

Figure 4.

The intronic hairpin can induce editing at the I/M site prior to splicing. (A) Co-expression of the Gabra-3 exon–intron–exon constructs with the ADAR2 expression vector in HEK 293 cells. The chromatograms after sequencing show that the editing efficiency at the I/M site decrease from high to medium in the absence of the intronic editing inducer when spliced. (B) Detection of spliced and non-spliced Gabra-3 exon–intron–exon products after RT-PCR from the same samples as in (A). Deletion of the editing inducer (Δ149 exon–intron–exon) reduces the splicing efficiency compared to the WT exon–intron–exon reporter.

Figure 5.

Induced editing of a non-ADAR substrate in presence of the conserved Gabra-3 intronic duplex. (A) Alignment of sequences from different species of gabra-3 intron 9 at the location of the intronic duplex. Letters in bold indicate conserved nucleotides. The structure as well as the nucleotide sequence is conserved between species that are edited at the I/M site whereas little conservation can be found in non-edited species like frog and pig. Arrows indicates the location of edited adenosines. (B) Comparing the putative RNA secondary structure of Gabra-3 from pig (pGabra-3) and mouse (mGabra-3) at the I/M site. The I/M site is indicated with a circle in blue. Divergent nucleotides are in pink. (C) Sanger sequencing showing the I/M site after transfection of a pGabra-3 reporter and a construct where the mouse Gabra-3 I/M stem loop was exchanged for the pGabra-3 sequence (pGabra-3/mGabra-3 intron 9). Editing after transfection into HeLa cells and co-transfection with an ADAR2 expression vector into HEK293 cells are shown.

Figure 6.

Deletion analyses to determine the shortest sequence for efficient I/M editing of Gabra-3. Editing reporter constructs (A–E) expressing exon 9 and part of intron 9 were co-transfected into HEK 293 cells together with an ADAR1 or ADAR2 expression vector. The chromatograms after sequencing of the RT-PCR products at the I/M site are shown on top. Below are the putative secondary structures that can be formed at the I/M site. The I/M site is indicated in grey. (C′) indicates the same construct as in (C) but where 149 nt of the intronic hairpin is deleted. The number of deleted nucleotides within each reporter construct is shown below the putative structures.

Figure 7.

Model for induced editing at the I/M site of Gabra-3 by the downstream intronic editing inducer element. ADAR enzymes (black bow) are recruited to the transcript by the long intronic hairpin. Increased local concentration of ADAR leads to more efficient editing at the I/M site.