Intronic Alus influence alternative splicing

Abstract

Examination of the human transcriptome reveals higher levels of RNA editing than in any other organism tested to date. This is indicative of extensive double-stranded RNA (dsRNA) formation within the human transcriptome. Most of the editing sites are located in the primate-specific retrotransposed element called Alu. A large fraction of Alus are found in intronic sequences, implying extensive Alu-Alu dsRNA formation in mRNA precursors. Yet, the effect of these intronic Alus on splicing of the flanking exons is largely unknown. Here, we show that more Alus flank alternatively spliced exons than constitutively spliced ones; this is especially notable for those exons that have changed their mode of splicing from constitutive to alternative during human evolution. This implies that Alu insertions may change the mode of splicing of the flanking exons. Indeed, we demonstrate experimentally that two Alu elements that were inserted into an intron in opposite orientation undergo base-pairing, as evident by RNA editing, and affect the splicing patterns of a downstream exon, shifting it from constitutive to alternative. Our results indicate the importance of intronic Alus in influencing the splicing of flanking exons, further emphasizing the role of Alus in shaping of the human transcriptome.

Figure 1. Bioinformatic analysis of Alu insertion within the flanking introns.

Conserved constitutively spliced exons were analyzed for the differences in the location of antisense and sense Alus within the upstream and downstream introns (left and right panels, respectively). The x-axis is the distance in base pairs from the exon; the y-axis is the number of Alus found within this distance. Antisense Alus are marked in blue and sense Alus are marked in red.

Figure 2. The effect of intronic Alus on the splicing of a flanking exon.

(A) Schematic illustration of the RABL5 minigene containing three exons and two introns. The intronic Alus (1 through 5) are marked by boxes with a point indicating the orientation of the Alu relative to the pre-mRNA. Alu4 is an AluSx inserted between the two arms of AluJo. (B) The indicated wild-type (wt) and mutant plasmids were transfected into 293T cells, total RNA was extracted, and splicing products were separated on a 2% agarose gel after RT-PCR analysis. Lane 1, splicing products of wt RABL5 minigene. Lanes 2–26, splicing products of the indicated mutants. The following abbreviations were used: Δ indicates deletion of the specified Alu element, X 1w3 indicates replacement of Alu1 with Alu3 (i.e., the sequence of Alu3 was inserted instead of that of Alu1 and in the same orientation as Alu3), and 1int specifies replacement of the Alu1 sequence with a non-Alu intronic fragment. The two mRNA isoforms are shown on the right. Numbers on top of the gel indicate percentage of exon inclusion as determined using ImageJ software. PCR products were sequenced.

Figure 3. Editing sites within the intronic Alus.

(A) Schematic illustration of exons 2 to 3 of the RABL5 gene. Exons are depicted as black boxes; the intronic Alus, derived from AluJo and AluSx, in sense and antisense orientations, respectively, are shown in the middle gray-shaped boxes. The intronic, antisense Alu sequence (AluSx) is 102 nucleotides downstream of the sense AluJo and AluSx is 24 nucleotides upstream of the junction of exon 3. Sense and antisense Alus are expected to form a double-stranded secondary structure, thus allowing RNA editing. (B) Editing sites were inferred from alignment of five cDNAs (accession numbers BC050531, BC038668, BI547904, BI548328, and DB495755) to the human genomic DNA. RNA editing occurs at eight positions within the antisense AluSx and at eleven positions within the sense AluJo. Based on these editing sites, the pairing between the sense and antisense Alu sequences was inferred (upper and lower lines, respectively). The region in which editing occurs starts at the middle of the right arm (position 232 in the AluSx consensus) and ends at the beginning of the left arm of Alu2 (position 101 in the AluSx consensus). Panel B shows only this corresponding region, while the entire Alu-Alu potential dsRNA is shown in Figure S3. (C) To further confirm the editing activity, total RNA was extracted from a neuroblastoma (SH-SY5Y) cell-line and treated with DNaseI, followed by RT-PCR analysis using primers to exon 2 and exon 3, and to intron 2 and exon 3 (lanes 1 and 2, respectively; see also Materials and Methods). The PCR products were sequenced. (D) The upper PCR product shown in panel C lane 2 was cloned and sequenced. The Chromas sequence is shown with the editing sites, found in AluSx, marked by boxes. (E) Editing in Alu2 requires the presence of Alu1. Wild type RABL5 minigene (WT) and a mutant in which Alu1 was deleted (ΔAluJo) were transfected into 293T cells. RNA was extracted, treated with DNase I, and amplified using set of primers flanking Alu2 and designed to amplify only exogenic transcripts. Sequencing chromatograms of four nucleotides in AluSx are shown (this editing site is also marked in green in panel B).

Figure 4. Distance effect of Alu elements on the alternative splicing pattern.

(A) A schematic illustration of the genomic region between exons 2 and 3 of RABL5 gene. Arrows marked A and B indicate two positions where an intronic sequence was inserted. (B) An 800-nucleotide intronic sequence was inserted in site B. The 800-nucleotide sequence was gradually shortened to the size shown above each lane. The indicated wt and chimeric plasmids were transfected into human 293T cells, total RNA was collected and examined by RT-PCR analysis (lanes 1–9). Lanes 10–12 show insertions of a different sequence, containing 25 nucleotides without any known splicing regulatory sequences, into the same site. This sequence was duplicated and triplicated to generate 50- and 75-nucleotide inserts. These mutant RABL5 minigenes were examined as above. (C) Similar analysis as in panel B, except that the 800-nucleotide sequence and the shorter sequences were inserted into site A. Spliced products are shown on the right and each PCR product was confirmed by sequencing. Splicing products were separated on a 2% agarose gel. Numbers on top of the gel indicate percentage of exon inclusion as determined using ImageJ software.

Figure 5. The effect of Alu2 on the alternative exon.

(A) The sequence of the antisense Alu2. Mutated putative 5′ss is shown in red. A sequence of 24 nucleotides that was deleted is underlined. Three putative 3′ss that were mutated are in bold and underlined. In yellow are the right and left PPT regions with the downstream AG that were deleted. The green sequence is a stem and loop region of 18 nucleotides that was examined as shown in panel C (referred as ‘A’ region). Underlined in that region are two overlapping SC35 potential binding sites (the gray in the middle indicates the overlap region). (B) The indicated wt and mutant plasmids were transfected into 293T cells, total RNA was extracted, and splicing products were separated on a 2% agarose gel after RT-PCR analysis. Lane 1, splicing products of wt RABL5 minigene. Lanes 2–13, splicing products of the indicated mutants. The two mRNA isoforms are shown on the right. Numbers on top of the gel indicate percentage of exon inclusion, as determined using ImageJ software. (C) The upper part illustrates the putative secondary structure formed by AluJo and AluSx, as predicted using the Vienna secondary structure web site (http://www.tbi.univie.ac.at/RNA). The green arrows in the right panel indicate the start and end positions of the stem and loop structure, marked as ‘A’. The lower part shows the effect of the wt and mutant plasmids that were analyzed, as in panel B. Lane 1, wilt type. Lane 2, elimination of the two SC35 putative binding sites by mutating their overlapping sequence (AA were mutated to CC). Lane 3, deletion of the entire stem-loop ‘A’ sequence. Lane 4, replacement of the ‘A’ sequence by a random sequence lacking putative splicing binding sites. Lane 5, replacement of the loop sequence by a perfect complementary sequence, so that the ‘A’ element is entirely in a stem structure. Lane 6, disruption of the stem part of ‘A’, so that ‘A’ is entirely in a loop structure.