Detection of slipped-DNAs at the trinucleotide repeats of the myotonic dystrophy type I disease locus in patient tissues

Abstract

Slipped-strand DNAs, formed by out-of-register mispairing of repeat units on complementary strands, were proposed over 55 years ago as transient intermediates in repeat length mutations, hypothesized to cause at least 40 neurodegenerative diseases. While slipped-DNAs have been characterized in vitro, evidence of slipped-DNAs at an endogenous locus in biologically relevant tissues, where instability varies widely, is lacking. Here, using an anti-DNA junction antibody and immunoprecipitation, we identify slipped-DNAs at the unstable trinucleotide repeats (CTG)n•(CAG)n of the myotonic dystrophy disease locus in patient brain, heart, muscle and other tissues, where the largest expansions arise in non-mitotic tissues such as cortex and heart, and are smallest in the cerebellum. Slipped-DNAs are shown to be present on the expanded allele and in chromatinized DNA. Slipped-DNAs are present as clusters of slip-outs along a DNA, with each slip-out having 1-100 extrahelical repeats. The allelic levels of slipped-DNA containing molecules were significantly greater in the heart over the cerebellum (relative to genomic equivalents of pre-IP input DNA) of a DM1 individual; an enrichment consistent with increased allelic levels of slipped-DNA structures in tissues having greater levels of CTG instability. Surprisingly, this supports the formation of slipped-DNAs as persistent mutation products of repeat instability, and not merely as transient mutagenic intermediates. These findings further our understanding of the processes of mutation and genetic variation.

Figure 1. Models of expansion of trinucleotide repeats.

(A) Slipped-strand DNAs can form during various metabolic processes such as replication, repair, recombination, transcription, and at unwound DNA. Slipped-out- DNAs may form on either the CTG or CAG strand, forming SI-DNA heteroduplexes or S-DNA homoduplexes. S-DNA contains the same number of repeats in both DNA strands, with multiple clustered slip-outs per molecule. SI-DNA contains differing numbers of repeats in each strand. Mispairing of the repeats are shown at right. (B) Model of out-of-register DNA slippage in trinucleotide repeats. Slippage and mis-pairing of triplet repeats by the complementary repeat units shifting out-of register, leading to slipped-out repeats.

Figure 2. Slipped-DNAs are bound by anti-DNA junction antibody.

(A) The anti-DNA junction antibody 2D3 bound slip-outs of 1-, 3- and 20-excess repeats as well as homoduplex slipped-DNAs with multiple clustered slip-outs/molecule by electrophoretic mobility shift assay. DNA substrates were 59 bp+(CT/AG)n+54 bp radiolabeled, gel-purified and used in binding experiments. Arrowheads indicate non-specific, specific and competition-resistant specific complexes. Line for lanes of S-DNA indicates a non-specific DNA. Triangles indicate increased antibody; + indicates addition of non-specific (plasmid) competitor DNA. All samples of the band-shift experiment were resolved on a single gel with panels separated for clarity. See Fig. S2 for control IgG₁ Ab binding. (B) DM1 post-mortem patient and control, tissue, and DM1 CTG tract sizes (for the non-expanded and expanded allele for the patients, and both non-expanded alleles for the control). See Text S1 for post-mortem details. (C) Protocol to isolate slipped-DNAs from genomic DNA. Tissue DNA is isolated using a non-denaturing protocol (see Text S1). DNA is then digested to release the repeat-containing fragment at the DM1 locus from the rest of the genome (slipped-DNAs are not super-coil dependent), incubated with the anti-DNA junction antibody 2D3, pulled down using protein G beads, released from the beads, and then characterized. The BbsI-(CTG)n-BamHI restriction fragment size will vary depending upon the repeat size. NB, this image is best viewed directly on the original electronic image.

Figure 3. Immunoprecipitated DNA is enriched for the expanded DM1 allele.

(A) Multiplex PCR protocol to determine the DM1 allele specificity of IP'd DNA, where “n” and “N” are the non-expanded and expanded alleles. Two primer pairs, indicated by arrow-heads are used in the same PCR reaction in order to differentiate between the expanded and non-expanded allele in genomic and IP'd DNA. Expected products are shown in the schematic gels for each case, sizes are based upon a non-expanded allele of (CTG)₄. (B) Multiplex PCR analysis of ADM5 patient tissue DNAs shows only the lower two products in IP'd DNAs, indicating a strong enrichment of the expanded but not the non-expanded allele. DM1 individual, ADM5, has varying expanded repeat sizes between tissues – too large to be amplified across (Fig. 2B) and (CTG)₄ in the non-expanded allele. Sizes of PCR products are indicated. The products in the IP lanes appear brighter because more DNA was loaded in these lanes in order to show that apparent loss of the larger PCR products that are unique to the non-expanded allele was not due to decreased sample loading. (C) Triplet-primed PCR protocol for IP'd DNAs (see text and Methods for full explanation of protocol). Briefly, an enrichment of the smeared PCR product (expanded allele) is expected over the smaller discrete product (non-expanded allele) after IP. (D) TP-PCR reveals predominantly the expanded allele in IP'd DNA (black arrowhead), and an absence of the non-expanded allele (blue arrowhead), confirming the specific immunoprecipitation of the expanded allele. The supernatant (SN) is depleted of the expanded but not the non-expanded allele. NB, this image is best viewed directly on the original electronic image. Neither Figure 3B nor Figure 3D are quantitative in nature; they are loaded in such a way that the differences between genomic and IP'd DNA are visually apparent.

Figure 4. Quantitative and enzymatic analysis of patient DNA.

(A) Quantitative competitive PCR revealed a significant increase in the amount IP'd/input from heart compared to cerebellum DNA of the same DM1 patient (unpaired two-tailed t-test, p = 0.03, n = at least 5 experimental replicates per treatment per tissue, on at least two genomic isolations). No significant difference was found between matched tissues of a non-DM1 individual. Details of quantitative competitive PCR and examples of the raw data are presented in Fig. S4. (B) Sensitivity of DM1 patient DNAs to structure-specific enzymes. For enzyme location specificity, see Fig. S4D TP-PCR analysis of samples +/−digestions assessed by GeneScan or (C) agarose electrophoresis, show decreased signal of the expanded allele after T7endoI or MBN digestion, with control DNA showing no difference. (D) Quantification of MBN and T7endoI digestion. Untreated heart DNA compared to MBN-treated, paired t-test, p = 0.0015, and compared to T7endoI-treated, paired t-test, p = 0.0015, n = at least 5 experimental replicates per treatment, on at least two genomic isolations. For analysis of additional tissues see Fig. S4. All errors bars indicate SEM, n = at least 5 experimental replicates per treatment per tissue, on at least two genomic isolations.

Figure 5. Analysis of slipped-DNA in native chromatin, and EM of IP'd DNA.

(A) Tissues were treated in their native chromatin state with MBN and T7EndoI or AluI enzymes, DNAs extracted and analyzed by TP-PCR. Agarose electrophoretic analysis of native-chromatin context digested DNA, run out after TP-PCR, showing a decrease in the expanded allele signal from patient muscle, but not cerebellum. See Figure S5A for representative GeneScan analyses of patient DNA treated in its native chromatin context with MBN and T7EndoI or AluI enzyme (see Text S1 for Nuclease accessibility protocol). Also, see Figure S5C for a comparison of areas under each peak of the GeneScans before and after treatment. (B) The graph shows the significant difference in the reduction of the expanded allele after MBN and T7 treatment, compared to both untreated and AluI treatment (p = 0.0038), n = 3 experiments. There is no significant difference between untreated and MBN+T7 treated ADM9 cerebellum digested in the native chromatin context. All error bars indicate SEM. (C) Electron microscopic imaging shows structured DNA. Electron microscopic (EM) images of immunoprecipitated DM1 DNAs and a control fully-duplexed DNA. IP'd DM1 tissue DNA shows multiple sized and clustered structures by EM. For EM analysis of additional tissue DNA as well as wider field views, see Supplementary Fig. S7. (D) Analysis of slip-out sizes and the distance between slip-outs on immunoprecipitated slipped DNAs. The size of the slip-outs presented a bimodal distribution ranging from 1–100 repeats with peaks at ∼30 and <10 repeats. Multiple slip-outs were clustered along a given DNA, with distances of <100 bp between slip-outs. NB, this image is best viewed directly on the original electronic image.

Figure 6. Proposed model for role of slipped-DNAs in repeat instability.

Slipped homoduplex DNA that forms at a trinucleotide repeat may be a target of attempted repair. Interference by adjacent slip-outs may arrest repair, allowing for intrastrand slippage and the formation of a gap. When filled, this would result in an expansion in one of the strands, producing a heteroduplex as well as more slipped-DNA.