sgRNA Sequence Motifs Blocking Efficient CRISPR/Cas9-Mediated Gene Editing

Abstract

Cas9 nucleases can be programmed with single guide RNAs (sgRNAs) to mediate gene editing. High CRISPR/Cas9-mediated gene knockout efficiencies are essential for genetic screens and critically depend on the properties of the sgRNAs used. The specificity of an sgRNA is defined by its targeting sequence. Here, we discovered that two short sequence motifs at the 3' end of the targeting sequence are almost exclusively present in inefficient sgRNAs of published sgRNA-activity datasets. By specific knock-in of sgRNA target sequences with or without these motifs and quantitative measurement of knockout efficiency, we show that the presence of these motifs in sgRNAs per se results in a 10-fold reduction of gene knockout frequencies. Mechanistically, the cause of the low efficiency differs between the two motifs. These sequence motifs are relevant for future sgRNA design approaches and studies of Cas9-DNA interactions.

Keywords: CRISPR screening; CRISPR/Cas9; CrispRGold; gene targeting; knockout efficiency; scaffold RNA; sgRNA design; sgRNA efficiency; sgRNA motif.

Graphical abstract

Figure 1

sgRNA Sequence Motifs Blocking Efficient CRISPR/Cas9-Mediated Gene Editing (A) Flow cytometry plots showing the knockout frequencies (lower right gate) of CD22 (top) and B220 (bottom) in primary B cells isolated from Cas9-transgenic (GFP⁺) animals 4 days post-transduction with retroviruses encoding the indicated sgRNAs. The sequences in the four PAM-proximal bases of the targeting sequence (hereafter called efficiency-modulating sequence [EMS]) are shown in orange (T-rich) or blue (control); the PAM is shown in gray. Data are representative for two independent experiments. (B) Number of sgRNAs with the indicated sequences in the EMS in the inefficient (last 25%) or efficient (top 25%) sgRNAs reported by Doench et al. (2014). (C) Boxplots of the sgRNA activities reported by Doench et al. (2014), considering all of the sgRNAs (black) or the sgRNAs with the indicated motifs in the EMS (orange). The top, middle, and bottom lines of the boxplot represent the 25^th, 50^th, and 75^th percentiles, respectively; the whiskers represent the max and min values. Subgroups were compared to the control set using ordinary one-way ANOVA (^∗∗∗∗p < 0.0001). (D) Scheme of validation experiment. sgRNA target sequences followed by T2A and GFP were targeted in-frame into the Lamin B1 locus of a mouse B cell tumor cell line using CRISPR/Cas9. GFP⁺ cells were subcloned, transduced using retroviruses encoding the respective sgRNAs, and cultured for 8 days before analysis. (E) Example of GFP knockout measurement (GFP KO gate) by flow cytometry 8 days post-transduction with the indicated sgRNA, as in the experimental system shown in (D). (F) Heatmap of the GFP knockout frequencies in the cell lines with the indicated sequences in the EMS 8 days post-transduction with the respective sgRNAs. Sequences matching the TT- and GCC-motifs are shown in orange. (G) Knockout frequencies in Cas9-transgenic primary B cells 4 days post-transduction with sgRNAs, normalized to the higher knockout frequency of the two sgRNAs used. The sgRNAs matching the TT- or GCC-motifs are encircled, and the respective sequences indicated. Data are based on two independent experiments and adapted from Chu et al. (2016). (H) Schematic diagram of the targeting sequence of the sgRNA (blue and orange) bound to the DNA (black). The four PAM-proximal nucleotides of the targeting sequence (orange) were called EMS due to their potential for modulating knockout frequencies. The predicted CRISPR/Cas9-mediated DNA cut is indicated.

Figure 2

Mechanism of Motifs Blocking Efficient CRISPR/Cas9-Mediated Gene Editing (A) Targeting sequences of the sgRNAs used to study mechanism of motifs. The four PAM-proximal bases are highlighted in blue and orange. (B) In vitro cleavage assay using ribonucleoprotein particles (RNPs) with the indicated sgRNAs and amplified target sequences. (C) Knockout frequencies in vivo 2 days post-electroporation with the indicated synthetic sgRNAs. (D) sgRNAs produced by in vitro transcription of the indicated sgRNAs and a negative control sgRNA having five Ts at the 3′ end of the targeting sequence (5-T). (E) Scheme of the 3′ end of the targeting sequence and the 5′ end of the scaffold RNA. The four Ts in the scaffold were mutated to the indicated variants (T5A and TT3AA). (F) Knockout frequencies 8 days post-transduction, with sgRNAs consisting of the indicated targeting sequences and variants of scaffold RNAs. (G) Heatmap of the knockout frequencies obtained with the mutated scaffolds as in (F) in three clones (Cl) per condition. (H) In vitro cleavage assay using Ctrl1 and the Ctrl1 target site in the presence of increasing levels (0×, 0.5×, 1×, 2×, 4×, 8×, and 8×) of the indicated competing sgRNAs. (I) Heatmap of the knockout frequencies 8 days post-electroporation, with increasing doses of the indicated synthetic sgRNAs. (J) Quantification of target sites bound to Cas9. Cas9 was immunoprecipitated 16 h post-transfection with sgRNA-encoding plasmids. Data are representative for two independent experiments.