A high-fidelity Cas9 mutant delivered as a ribonucleoprotein complex enables efficient gene editing in human hematopoietic stem and progenitor cells

Abstract

Translation of the CRISPR-Cas9 system to human therapeutics holds high promise. However, specificity remains a concern especially when modifying stem cell populations. We show that existing rationally engineered Cas9 high-fidelity variants have reduced on-target activity when using the therapeutically relevant ribonucleoprotein (RNP) delivery method. Therefore, we devised an unbiased bacterial screen to isolate variants that retain activity in the RNP format. Introduction of a single point mutation, p.R691A, in Cas9 (high-fidelity (HiFi) Cas9) retained the high on-target activity of Cas9 while reducing off-target editing. HiFi Cas9 induces robust AAV6-mediated gene targeting at five therapeutically relevant loci (HBB, IL2RG, CCR5, HEXB, and TRAC) in human CD34⁺ hematopoietic stem and progenitor cells (HSPCs) as well as primary T cells. We also show that HiFi Cas9 mediates high-level correction of the sickle cell disease (SCD)-causing p.E6V mutation in HSPCs derived from patients with SCD. We anticipate that HiFi Cas9 will have wide utility for both basic science and therapeutic genome-editing applications.

Figure 1. On-target activity of high-fidelity Cas9 mutants in human cells with ribonucleoprotein (RNP) delivery.

(a) Editing efficiency of the WT (blue), eSpCas9(1.1) (orange), or SpCas9-HF1 (gray) Cas9 proteins with crRNAs that target EMX1, HEKSite4, or VEGFA3 loci in HEK293 cells. The on-target site “ON” and off-target site “OFF” for each guide are indicated and sequence maps are listed in Fig. 1b. (b) Sequence maps corresponding to the on-target and off-target sites analyzed in Fig. 1a. Underlined sequences correspond to the PAM site and bold sequences indicate nucleotide mismatches. (c) On-target editing efficiency of the WT (blue), eSpCas9(1.1) (orange), or SpCas9-HF1 (gray) Cas9 proteins with crRNAs that target the indicated sites within the HPRT, CTLA4, and PDCD1 loci in HEK293 cells. Bars represent mean ± s.e.m., n=3 independent experiments performed at different times. ****P < 0.0001, NS (not significant) = P ≥ 0.05, two-way analysis of variance (ANOVA) and Tukey’s multiple comparisons test.

Figure 2. Unbiased bacterial selection for cas9 mutants that reduce off-target editing and maintain on-target potency.

(a) A general schematic for the bacterial selection scheme to isolate cas9 mutants with reduced off-target editing and high on-target activity. Approximately 250,000 clones were screened for cleavage of the on-target VEGFA3 toxin plasmid, and avoidance of cleavage of the off-target plasmid. We isolated 875 surviving colonies from the primary screen, and pooled surviving plasmids were screened a second time using EMX1 guide and target sites. Ultimately 163 cas9 mutant plasmids were sequenced with mutations at 94 positions occurring twice or more. (b,c) Discrimination ratio (on/off-target editing efficiency) of WT Cas9 (red bar) and all 94 cas9 point mutations (blue bars) delivered by plasmid into HEK293 cells with the EXM1 (b) or HEKSite4 (c) gRNAs (2-part). Horizontal lines (orange) indicate the minimum discrimination ratios (indicated numerically above bars) used to select mutants for further testing. Mutants that maintained greater than 50% on-target editing and reduced off-target editing beyond the limits of detection were arbitrarily set at 30 (EMX1 only) to indicate that they were carried forward into subsequent screening steps. (d,e) On- and off-target editing efficiency facilitated by WT and mutant Cas9 plasmids from Fig. 2b,c examined with crRNAs that target the EMX1 (d) and HEKSite4 (e) delivered as by lipofection into HEK293 cells. The on-target site “ON” (blue – left Y-axis) and off-target site “OFF” (orange – right Y-axis) for each guide are indicated and sequence maps are listed in Fig. 1b. Bars represent mean ± s.e.m., n=9 independent experiments performed at different times. **P<0.01, ****P < 0.0001, NS (not significant) = P ≥ 0.05, two-way analysis of variance (ANOVA) and Tukey’s multiple comparisons test.

Figure 3. The R691A high fidelity (HiFi) Cas9 mutant maintains editing activity when delivered as an RNP.

(a) On-and off-target editing efficiency of the WT and bacteria-selected mutant Cas9 proteins with crRNAs that target the HEKSite4 (blue – on-target, orange – off-target 1, gray – off-target 2, yellow – off-target 3) and HPRT-38509 (green - on-target) loci in HEK293 cells. (b) On-target editing efficiency of WT Cas9 (blue), eSpCas9(1.1) (orange), SpCas9-HF1 (gray), HypaCas9 (yellow), and R691A (green) mutant proteins examined using 12 crRNAs that target different sites within the HPRT locus. Numbers included in the target site name indicate the first nucleotide of the target site with respect to the transcription start site of HPRT. Bars represent mean ± s.e.m., n=3 independent experiments performed at different times. (c) Box and whiskers plot showing aggregated on-target efficiency data of the eSpCas9(1.1) (orange), SpCas9-HF1 (gray), HypaCas9 (yellow), and R691A (green) mutants examined at the HPRT locus in Fig. 3b. The on-target editing efficiencies for each mutant at each site were normalized as a percent of WT Cas9 to account for varying editing efficiencies between guides. Horizontal lines represent median while showing the maximum and minimum values, n=12 from aggregated data in Fig. 3b. (d) Repair profile plot demonstrating the frequency and location of deletions and insertions relative to the unaltered HPRT-38087 target cleavage site (indicated by “0”). Experiments were performed with cells only (black bars), WT Cas9 (blue bars), eSpCas9(1.1) (orange bars), SpCas9-HF1 (gray bars), HypaCas9 (yellow bars), and HiFi (green bars). The overall INDEL frequencies for each experiment are indicated. Bars represent mean ± s.e.m., n=3 independent experiments performed at different times. For statistical comparisons, compare the edge of both sides of the horizontal lines. *P<0.05, **P<0.01, ***P<0.001, ****P < 0.0001, NS (not significant) = P ≥ 0.05, two-way analysis of variance (ANOVA) and Tukey’s multiple comparisons test.

Figure 4. HiFi Cas9 globally reduces off-target activity with both stable Cas9 expression and RNP delivery.

On-target (orange bars) and off-target editing (blue bars) as determined by NGS for the AR, EMX1, HBB, and HPRT-38087 (top to bottom) gRNAs (4 μM) delivered into HEK293 cells that express WT or HiFi Cas9, or complexed to WT or HiFi Cas9 and delivered as RNP (4 μM) into standard HEK293 cells (left to right). INDEL formation percentages at the on-target loci are indicated directly above the orange on-target bars. All amplicons are rank-ordered (highest to lowest) by INDEL formation percentage as determined for the WT Cas9 stable cell line. Pie charts indicate the fractional percentage of total on-target (orange) and off-target (blue) editing. Fractional on-target editing percentage is indicated in black typeface within the orange on-target portion of the pie chart. The Y-axis is plotted as log-10 scale on both left and right sides of the graph for clarity. The Cas9 protein and delivery method is indicated at the bottom of the graph.

Figure 5. RNP HiFi Cas9 facilitates near-WT on-target editing potency with large OTE reductions in primary CD34⁺ HSPCs.

(a) On-target editing efficiencies of WT Cas9 (normalized dotted line), eSpCas9(1.1) (light blue), SpCas9-HF1 (gray), and R691A (orange) mutant proteins examined using chemically-modified sgRNAs that target 5 clinically-relevant loci. Cas9 proteins and sgRNAs were delivered as RNP (1:2.5 – Cas9:sgRNA) by nucleofection into CD34⁺ HSPCs. INDEL frequencies were calculated by TIDE. Bars represent mean ± s.e.m., n=3 independent experiments performed in three healthy CD34⁺ cord blood donors. (b) Homologous recombination (HR) frequencies of Cas9 variants were examined as in Fig. 5a, except following the formation of site-specific Cas9 DSBs, electroporated cells were transduced with ssAAV6 homologous donor templates as described in the materials and methods. For HBB and CCR5, HR was measured via GFP^high expression via FACS; HR at IL2RG and HEXB was measured by assessing allelic-targeted integration via ddPCR; HR at TRAC locus was measured by tNGFR expression. Bars represent mean ± s.e.m., n=3 independent experiments performed in three CD34⁺ cord blood donors. (c) CD34⁺ HSPCs were electroporated as described above with either WT HBB RNPs or HiFi HBB RNPs and then were immediately transduced with an HBB-specific rAAV6 (UbC-GFP flanked with HBB homology arms). Cells were harvested and then analyzed for GFP^high expression (which is a measure of homologous recombination) via FACS (n =11, number of data points within each group, all from different cord blood donors from at least 3 independent experiments). (d) CD34⁺ HSPCs from 3 healthy donors were electroporated as described above with WT or HiFi HBB-RNPs. HBB (on-target), the top 7 bioinformatically determined and GUIDE-seq validated regions (see Supplementary Fig. 4b) were PCR-amplified with sequencing primers utilized in deep sequencing MiSeq runs. Bars represent mean ± s.e.m., n=3 independent experiments performed in three CD34⁺ cord blood donors. (e) Cord blood-derived CD34⁺ HSPCs were electroporated with WT or HiFi Cas9 HBB RNPs, cultured for 72-96hr post electroporation, gDNA was harvested, and HBB (on target) or a highly complementary off-target site (off-target 1) were PCR amplified. PCR products were gel extracted and INDEL frequencies were calculated using TIDE software (Bars represent mean ± s.e.m., n =6, number of data points within each group, all from different cord blood donors from at least 3 independent experiments performed at different times). (f) HSPCs were electroporated with 300 μg mL⁻¹ WT Cas9 or 300–600 μg mL⁻¹ HiFi Cas9 and half of the cells were transduced with an UbC-GFP ssAAV6 donor and the other half were cultured. Following 72-96 hr post-electroporation, cells were harvested and analyzed for HR by GFP FACS analysis or off-target INDELs by TIDE. Median is depicted, n=5, number of data points within each group, all from different cord blood donors from at least 3 independent experiments performed at different times). *P<0.05, **P<0.01, ***P<0.001, ****P < 0.0001, NS (not significant) = P ≥ 0.05, two-way analysis of variance (ANOVA) and Tukey’s multiple comparisons test.

Figure 6. R691A HiFi Cas9 delivered as RNP mediates robust Glu6Val HBB gene correction in sickle cell disease-CD34⁺ HSPCs while significantly reducing off-target activity.

(a) Sickle cell disease (SCD) patient-derived HSPCs were isolated from peripheral blood and subjected to Glu6Val gene correction methods using HBB RNPs (either WT (blue) or HiFi (orange) Cas9) and a gene corrective ssAAV6. Gene correction frequencies were analyzed by ddPCR™ as described in materials and methods (Bars represent mean ± s.e.m., n =3, number of data points within each group, all from different SCD patients). NS (not significant) = P ≥ 0.05, Two-tailed Student’s T-test. (b) SCD-HSPCs were targeted for Glu6Val HBB gene correction as described above and off-target editing was analyzed by NGS. Bars represent mean ± s.e.m., n=3 SCD patients. ****P < 0.0001, NS (not significant) = P ≥ 0.05, two-way analysis of variance (ANOVA) and Tukey’s multiple comparisons test. (c) Glu6Val targeted WT or HiFi SCD-HSPCs were differentiated down the erythroid lineage ex vivo. At 14 days post-differentiation, cells were harvested and evaluated for the percentage of erythrocytes (CD34⁻/CD45⁻/CD71⁺/CD235a⁺) and reticulocytes (CD235a⁺/CD49d⁻/Band3⁺) by FACS-based immunophenotypic analyses. Bars represent mean ± s.e.m., n=3 SCD patients. (d) Glu6Val targeted erythrocyte differentiated HSPCs were subjected to cation-exchange HPLC analysis of steady-state hemoglobin tetramers. The normalized percentages of fetal (HbF), adult (HbA) and sickle (HbS) hemoglobin are plotted as a function of total hemoglobin tetramers on the HPLC plot (as presented in Fig. 6f). Hemoglobin tetramers were quantified by measuring the area under the curve (AUC) of the absorbance peaks. Bars represent mean ± s.e.m., n=3 SCD patients. (e) Representative HPLC plot from the data presented in Fig. 6d showing Glu6Val correction in SCD-HSPCs results in HbA protein production when using both the WT and HiFi Cas9 HBB RNPs. Experiment is representative of the 3 experiments performed in Fig. 6d with similar results.