Engineered transfer RNAs for suppression of premature termination codons

Abstract

Premature termination codons (PTCs) are responsible for 10-15% of all inherited disease. PTC suppression during translation offers a promising approach to treat a variety of genetic disorders, yet small molecules that promote PTC read-through have yielded mixed performance in clinical trials. Here we present a high-throughput, cell-based assay to identify anticodon engineered transfer RNAs (ACE-tRNA) which can effectively suppress in-frame PTCs and faithfully encode their cognate amino acid. In total, we identify ACE-tRNA with a high degree of suppression activity targeting the most common human disease-causing nonsense codons. Genome-wide transcriptome ribosome profiling of cells expressing ACE-tRNA at levels which repair PTC indicate that there are limited interactions with translation termination codons. These ACE-tRNAs display high suppression potency in mammalian cells, Xenopus oocytes and mice in vivo, producing PTC repair in multiple genes, including disease causing mutations within cystic fibrosis transmembrane conductance regulator (CFTR).

Fig. 1

A nonsense mutation suppression screen to identify candidate anticodon edited tRNAs (ACE-tRNAs). a Schematic illustrates requisite interactions of ACE-tRNAs with translational machinery. Following delivery, ACE-tRNAs are recognized by an endogenous aminoacyl-tRNA synthetase (blue shape) and charged (aminoacylated) with their cognate amino acid (blue circle). The aminoacylated ACE-tRNA is recognized by the endogenous elongation factor 1-alpha (red shape), which protects the ACE-tRNA from being de-acylated and delivers the aminoacyl ACE-tRNA to the ribosome (light gray shape) for suppression of a premature termination codon, in this instance UGA. b Individual ACE-tRNAs were cloned into the high throughput cloning nonsense Reporter plasmid using Golden Gate paired with CcdB negative selection. The all-in-one plasmid contains the NLuc luciferase reporter with either a UGA, UAG, or UAA PTC at p.162 between the enzymatic large bit and requisite C-terminal small bit

Fig. 2

Screens of ACE-tRNA gene families with the high throughput cloning nonsense mutation reporter platform. The indicated anticodon edited PTC sequences were tested for each ACE-tRNA family that is one nucleotide away from the endogenous anticodon sequence, Supplementary Figure 1. Multiple high performing suppressor tRNA were identified for each class. Data are shown in Log10 scale in terms of normalized NLuc luminescence. Each tRNA dataset were obtained in triplicates and are displayed at average ± SEM. Coded identities and corresponding tRNA sequences are shown in Supplementary Figure 2a and Supplementary Data 1, respectively. Predicted cloverleaf structures for ACE-tRNAs for each family are included in Supplementary Figure 2b. The numerical values and ANOVA statistical analysis are located in Supplementary Data 2, where the order of tRNAs are maintained in top to bottom list form

Fig. 3

Cognate encoding and high-fidelity suppression by engineered tRNA. a Tryptic fragment of histidinol dehydrogenase (HDH), where X indicates suppressed PTC codon. MS/MS spectra of the tryptic fragment with masses of indicated y and b ions for WT (top), N94G (middle), and N94W (bottom) HDH. b9 ion mass is shifted by the predicted mass of −57 Da and +72 Da from the WT asparagine, indicating the encoding of cognate amino acids glycine and tryptophan by ACE-tRNA^Gly and ACE-tRNA^Trp (Trp-chr17.trna39), respectively. b ACE-TGA - tRNA^Gly (Glychr19.trna2) selectively suppresses the UGA stop codon in transiently transfected HEK293 cells. c ACE-tRNA^Gly transfection outperforms both gentamicin (40 µM; n = 3) and G418 (140 µM; n = 3) following a 48 h incubation in Hek293 cells stably expressing NLuc-UGA. Data is presented as standard error of mean in b and c

Fig. 4

Ribosome profiling of ACE-tRNA on transcriptome-wide 3′UTRs. a Ribosome footprint densities on 3′UTRs are plotted as log2-fold change for reads of treated cells vs. control (puc57GG empty vector) as described in the materials and methods. Transcripts were grouped by their endogenous UAA, UAG, and UGA stop codons. Each point represents the mean of two replicates for a transcript. Error bars show Mean ± SD of the log2-fold changes. b The average log2-fold change of normalized ribosome footprint occupancy was plotted for each nucleotide from −9 to +50 nt surrounding stop codons of transcriptome (18,101 sequences). The cartoon illustrates the ~9 nt offset from the 5′ end of ribosome footprint to the first base position of stop codon in the ribosome E-site. ACE-tRNA genes used for 4× constructs are Trp-chr17.trna39 (UGA), Gly-chr19.trna2 (UGA), Arg-chr9.trna6 (UGA), Gln-chr17.tRNA14 (UAA), and Glu-chr13.trna2 (UAG). Sequences are located in Supplementary Data 1

Fig. 5

In vivo delivery and suppression with ACE-tRNA as cDNA and RNA. a Representative images of mice injected with NLuc-UGA with ACE-tRNA^Arg (Arg-chr9.trna6 UGA) or pUC57 empty vector, NLuc-WT or water in the tibialis anterior muscle followed by electroporation at days 1, 2, and 7 after DNA administration. b Quantification of luminescence emission by the tibialis anterior muscles of the abovementioned mouse groups at different timepoints after DNA injection and electroporation (n = 3 mice per group, data are shown as SEM). c Rescued luminesce of stably expressed NLuc–UGA following transfection of Trpchr17.trna39cRNA and Glychr19.trna2 RNA transcripts (n = 3 for each ACE-tRNA). d Representative western blot analysis of CFTR protein expressed in HEK293 cells 36 h following transfection of WT, G542X, G542X + Glychr19.trna2, W1282X and W1282X + Trpchr17.trna39 CFTR cDNA. e Exemplar families of CFTR Cl^- current traces recorded using two-electrode voltage-clamp, 36 h following injection with WT, G542X, G542X + ACE-tRNA-Glychr19.trna2, W1282X and W1282X + ACE-tRNA-Trpchr17.trna39 CFTR cRNA. Currents were elicited using 5 mV voltage steps from −60 to +35 mV. The vertical and horizontal scale bars indicate 10 µA and 50 ms, respectively. f Dose response of G542X ACE-tRNA^Gly (filled circles; n = 11–19) and W1282X ACE-tRNA^Trp (open squares; n = 17–22) rescue (CFTR Cl^- currents elicited at +35 mV were normalized to WT CFTR Cl^- currents at +35 mV). ACE-tRNA^Gly rescue achieves WT-level of expressed CFTR current. Data is presented as standard error of mean for panels c and f