Massively parallel kinetic profiling of natural and engineered CRISPR nucleases

Abstract

Engineered SpCas9s and AsCas12a cleave fewer off-target genomic sites than wild-type (wt) Cas9. However, understanding their fidelity, mechanisms and cleavage outcomes requires systematic profiling across mispaired target DNAs. Here we describe NucleaSeq-nuclease digestion and deep sequencing-a massively parallel platform that measures the cleavage kinetics and time-resolved cleavage products for over 10,000 targets containing mismatches, insertions and deletions relative to the guide RNA. Combining cleavage rates and binding specificities on the same target libraries, we benchmarked five SpCas9 variants and AsCas12a. A biophysical model built from these data sets revealed mechanistic insights into off-target cleavage. Engineered Cas9s, especially Cas9-HF1, dramatically increased cleavage specificity but not binding specificity compared to wtCas9. Surprisingly, AsCas12a cleavage specificity differed little from that of wtCas9. Initial DNA cleavage sites and end trimming varied by nuclease, guide RNA and the positions of mispaired nucleotides. More broadly, NucleaSeq enables rapid, quantitative and systematic comparisons of specificity and cleavage outcomes across engineered and natural nucleases.

Fig. 1 ∣. Overview of the integrated NucleaSeq and CHAMP platform.

a, Crystal structures and domain maps of Cas9 and Cas12a RNP complexes (Protein Data Bank: 5F9R and 5B43). Stars: engineered Cas9 mutation sites. Scissors: cleavage sites. b, For NucleaSeq, a CRISPR–Cas nuclease digests a synthesized library of mispaired target DNAs under single-turnover conditions. DNAs contain unique left and right barcodes. Time point barcodes are added before NGS. NGS chips are recovered to profile DNA binding specificity via CHAMP. c, DNA libraries include targets with randomized PAMs or up to two guide-RNA-relative alterations. Right, read distribution by target type for CHAMP. d, A wtCas9 nuclease reaction time course (sgRNA 1) resolved by capillary electrophoresis. Each sample was run separately—two independent replicates for each. e, Cleavage rates are computed by fitting single exponential functions (lines) to uncut DNA depletions (circles). f, Cleavage rate reproducibility for wtCas9-sgRNA1 experiments. The gray area contains targets with rates beyond the experimental dynamic range. r: Pearson’s correlation coefficient excluding gray area. g, Cut DNA fragments from matched DNAs (black in diagram) report the time-dependent distribution of Cas9-generated cut sites in the TSs and NTSs. wtCas9-sgRNA1 cuts bluntly between the 3rd and 4th nucleotides (left). wtCas9-sgRNA2 produces a one-nucleotide 5′ overhang and then trims it off the NTS (right). Colors: cut positions (triangles in diagram). Error bars: median ± s.e.m. of n = 146 guide-RNA-matched library members. h, Ranked relative cleavage rates of all library members for all five nucleases. Limit: relative cleavage rate beyond detection limit. i, CHAMP reports the apparent binding affinity of nuclease-inactive CRISPR enzymes. Library DNAs on the surface of an NGS chip are incubated with increasing concentrations of a fluorescent dCas9 (cyan puncta). Their sequences are bioinformatically determined by comparison to the NGS output. Scale bar, 50 μm; inset, 5 μm. j, ABAs are computed by fitting Hill functions (lines) to mean fluorescence DNA clusters intensities (circles). AU, arbitrary fluorescence units. Median ± s.d. from bootstrap analysis of n ≥ 5 DNA clusters for each target. k, Correlation of dCas9 ΔABAs measured with CHAMP to dCas9 on-rates from a high-throughput assay. ΔABA, change in apparent binding affinity from the matched target, normalized to that of a scrambled DNA. r: Pearson’s correlation coefficient. x axis: median ± s.d. from bootstrap analysis of n ≥ 5 DNA clusters for each target. y axis: median ± s.e.m. of n ≥ 6 for each target DNA.

Fig. 2 ∣. Comprehensive analysis of off-target wtCas9 DNA binding and cleavage.

a, dCas9 ΔABAs for targets with one sgRNA1-relative mismatch. Dashed line: normalized matched target ΔABA (0); solid line: scrambled DNA ΔABA (negative control, 1). Median ± s.d. from bootstrap analysis of n ≥ 5 DNA clusters for each target. b, Cas9 cleavage rates for the same targets as in a. Dashed line: cleavage rate of the matched target; solid line: limit of detection for the slowest-cleaving targets. Error bars: s.d. from 50 bootstrap analysis measurements. c, ΔABAs (upper, grays) and cleavage rates (lower, blues) for targets containing two sgRNA1-relative mismatches. Black boxes expanded in callouts. d, dCas9 ΔABAs (upper, median ± s.d. from bootstrap analysis of n ≥ 5 DNA clusters for each target) and Cas9 cleavage rates (lower, error bars: s.d. from 50 bootstrap analysis measurements) for targets containing one sgRNA1-relative deletion or (e) insertion. f, Normalized reads for the TS and NTS of DNAs containing either a mismatch at position 3 (C3T or A3T) or a deletion at position 1 compared to sgRNA1 (left) or sgRNA2 (right). Error bars: maximum s.d. for cut products from cleavage of 146 matched DNA controls. g, Average cut site positions for each strand (TS and NTS) from DNAs containing one mismatch relative to sgRNA 1 (upper) or sgRNA 2 (lower). Range: earliest time point with more than 33% cut reads (open diamonds) to final time point (filled diamonds). Dashed and solid horizontal lines: mean cut site positions for 146 matched DNAs (M) at early and late time points.

Fig. 3 ∣. Comparison of engineered Cas9 nucleases.

a,b, Two-dimensional density plots correlate Cas9-HF1 ΔABAs (a) and cleavage rates (b) with those from wtCas9, Cas9-Enh and Cas9-Hypa (sgRNA1). Histograms: all ΔABAs or cleavage rates for the respective nuclease. r: Pearson’s correlation coefficient. c, The ratio of Cas9-HF1 to wtCas9 cleavage specificities for targets with two sgRNA1-relative mismatches. Red: slower cleavage by Cas9-HF1; blue: slower cleavage by wtCas9. Black-outlined range expanded in callout. d, Cas9-HF1 cleavage patterns on the TS and NTS of select target DNAs (sgRNA1). Normalized counts of cut products comprising ≥10% of the total cut reads at any time point. Error bars: maximum s.d. for cut products from cleavage of 146 matched DNA controls. e, Average cut site positions generated by Cas9-HF1 for each strand (TS and NTS) for targets containing one sgRNA-relative mismatch. Range: earliest timepoint with more than 33% cut reads (open diamonds) to final time point (filled diamonds). Dashed and solid horizontal lines: mean cut site positions for 146 matched DNAs (M) at early and late time points.

Fig. 4 ∣. Comprehensive analysis of off-target Cas12a cleavage.

a, Cas12a cleavage rates for DNAs containing one crRNA3-relative mismatch. Dashed line: cleavage rate of the matched target. Solid line: limit of detection for the slowest-cleaving targets. Error bars: s.d. from 50 bootstrap analysis measurements. b, Total cleavage rate compared to reported target strand cleavage (left) and R-loop propagation (right) rates. Total cleavage rates error bars: s.d. from 50 bootstrap analysis measurements. TS cleavage and R-loop propagation rate error bars: rate from a hyperbolic fit ± s.d. from n = 3 independent experiments. r: Pearson’s correlation coefficient. c, Cleavage rates for targets with two crRNA3-relative mismatches. Black box expanded in callout. d, Cleavage rates for DNAs containing one crRNA3-relative deletion (upper) or insertion (lower). Error bars: s.d. from 50 bootstrap analysis measurements. Nucleotides inserted to the left of the given positions. e, Normalized reads for the TSs and NTSs of the indicated targets. Parenthesis: crRNA. Error bars: maximum s.d. for cut products from cleavage of 146 matched DNA controls. f, Average cut site positions for each strand (TS and NTS) from DNAs with one crRNA3-relative mismatch (upper), deletion (middle) or insertion (lower). Range: earliest time point with more than 33% cut reads (open diamonds) to final time point (filled diamonds). Dashed and solid horizontal lines: mean cut site positions for 146 matched DNAs (M) at early and late time points.

Fig. 5 ∣. Statistical modeling of CRISPR–Cas nuclease cleavage.

a, AIC values for five biophysical models relying on the indicated sequence parameters. The most detailed model (V) has the lowest AIC (information loss)—that is, the best goodness of fit. R-loop position-specific parameters reduce the AIC most. b, Correlation between measured and modeled cleavage rates for Cas9-HF1 (left, red) and Cas12a (right, purple) using model V. Histograms: distributions of fit or measured values beyond the upper and lower detection limits. Percentages: quantity of data with one or both values beyond detection limits. r: Pearson’s correlation coefficient. c, Base identity-dependent weights for mismatches and insertions averaged across all Cas9 and Cas12a enzymes. See Supplementary Fig. 8 and text for additional information. d, Modeled specificity penalties for one guide-RNA-relative mismatch (upper), insertion (middle) or deletion (lower). PAMs are oriented left for comparison. Arrows and dashed lines: values below the detection limit. e, The predicted reduction in mismatch-dependent cleavage rates correlates with previous high-throughput measurements of reduced edit efficiencies for wtCas9 (blue) and Cas12a (purple). See Methods for associated data. ρ: Spearman’s correlation coefficient. f, The number of off-target sites in the human genome with a predicted cleavage specificity greater than the indicated specificity threshold. For each nuclease, n = 1,000 targets, selected randomly from exomic DNA. The cleavage specificities of the potential off-target cleavage sites across the genome were calculated using model V. Top whisker (maxima): top of 90% confidence interval; top box: third quartile; center line: median; lower box: second quartile; lower whisker (minima): bottom of 90% confidence interval.