Integrase-mediated spacer acquisition during CRISPR-Cas adaptive immunity

Abstract

Bacteria and archaea insert spacer sequences acquired from foreign DNAs into CRISPR loci to generate immunological memory. The Escherichia coli Cas1-Cas2 complex mediates spacer acquisition in vivo, but the molecular mechanism of this process is unknown. Here we show that the purified Cas1-Cas2 complex integrates oligonucleotide DNA substrates into acceptor DNA to yield products similar to those generated by retroviral integrases and transposases. Cas1 is the catalytic subunit and Cas2 substantially increases integration activity. Protospacer DNA with free 3'-OH ends and supercoiled target DNA are required, and integration occurs preferentially at the ends of CRISPR repeats and at sequences adjacent to cruciform structures abutting AT-rich regions, similar to the CRISPR leader sequence. Our results demonstrate the Cas1-Cas2 complex to be the minimal machinery that catalyses spacer DNA acquisition and explain the significance of CRISPR repeats in providing sequence and structural specificity for Cas1-Cas2-mediated adaptive immunity.

Extended Data Figure 1. The integration reaction is dependent on the presence of protospacers, low salt and divalent metal ions

a, In vitro integration assay alongside EcoRI- and Nb.BbvCI nickase-treated pCRISPR. b, Salt-dependence assay using Cas1 or Cas2 only and Cas1+Cas2. The titration corresponds to 0, 25, 50, 100 and 200 nM KCl, on top of the salt carried in from the reaction reagents. c, Integration assays in the presence of 10 mM EDTA, Mg²⁺, Mn²⁺ or no additive. d, Integration assays with increasing protospacer concentrations. e, A comparison of post-reaction treatments as indicated. The data presented in a-e are representative of at least three replicates.

Extended Data Figure 2. Cas1 requires Cas2 for robust protospacer integration

a, Schematic of the integration assays using ³²P-labeled protospacers (PDB code 4P6I for Cas1–Cas2). b, Integration assays in the presence of increasing protein and 10 mM MnCl₂. The titration corresponds to 0, 50, 100 and 200 nM protein. c, Same as b except in the presence of 10 mM MgCl₂. The data presented in b and c are representative of at least three replicates.

Extended Data Figure 3. The catalytic activity of Cas1 is required for integration

a, Close-up view of the Cas1 active site with the conserved residues shown in stick configurations (PDB 4P6I) b, Integration assays of purified Cas1 active site mutants complexed with wild type Cas2. c, The same as b except using radiolabeled protospacers. The data presented in b and c are representative of at least three replicates.

Extended Data Figure 4. Band X corresponds to topoisomers of pCRISPR

a, Agarose gel of purified relaxed and Band X integration products. b, Analysis of the total reaction products, after phenol chloroform extraction and ethanol precipitation, on a pre-stained agarose gel. c, Same as b except ethidium bromide staining was performed after electrophoresis. d, PCR amplification products of various segments of pCRISPR using the relaxed, Band X or pCRISPR template shown in a. The laddering effect of minor products using CRISPR locus primers likely reflects the propensity of CRISPR repeats to form DNA hairpins. The data presented in a-d are representative of at least three replicates.

Extended Data Figure 5. Cas1 catalyzes the disintegration of half-site integrated protospacers

a, Schematic of the four strands constituting the Y DNA substrate used in the disintegration assays. b, Native polyacrylamide gel analysis of the annealing products with either Strand A or Strand C radiolabeled. c, Native polyacrylamide gel analysis of disintegration assay products using Y DNA substrates with Strand A labeled. d, Denaturing gel analysis of the disintegration assay products with Strand A labeled.

Extended Data Figure 6. Cas1–Cas2 can integrate various lengths of double-stranded DNA with blunt- or 3'-overhang ends into a supercoiled target plasmid

a, Integration assays using the indicated lengths of protospacer DNA. b, Integration assays using varying 5' or 3' overhang lengths. c,d, A comparison of integration assays using pCRISPR or Nb.BbvCI-nicked pCRISPR target. e, Integration assay using different target plasmids with or without a CRISPR locus. The green arrows correspond to the relaxed product of each target and the cyan arrows correspond to the Band X product. The data presented in a-e are representative of at least three replicates.

Extended Data Figure 7. Cas1 tyrosine mutants support integration activity in vitro

a, A close-up of the Cas1 active site with the tyrosine residues labeled in blue. b, Structure-based sequence alignment of Cas1 proteins, highlighting the tyrosine residues mutated to alanine in this study. c, Radiolabeled protospacer integration assay of Cas1 tyrosine mutants complexed with WT Cas2. The gel presented in b is representative of at least three replicates.

Extended Data Figure 8. High-throughput sequencing of integration products reveals sequence-specific integration

a, Schematic of the workflow for high-throughput sequencing analysis of the integration sites. b, Raw map of the total reads along pCRISPR before collapsing into single peaks of protospacer-pCRISPR junctions depicted in Fig. 4. c, Same as b, except for the pUC19 target. d, Sequence of the leader-end of the CRISPR locus in E. coli. e,f, WebLogo analysis from the −5 to +5 positions surrounding the protospacer integration sites on the (e) plus and (f) minus of pCRISPR. The arrow points to the nucleotide that is covalently joined to the protospacer. g, h, Same as e,f, except for the pUC19 target.

Extended Data Figure 9. Cas1–Cas2 correctly orients the protospacer DNA during integration

Mapped integration sites along the CRISPR locus of pCRISPR when using protospacer DNA with nucleotide ends (a) “wild type” 3' C and 3' T, (c) 3' A and 3' T, and (e) 3' C and 3' C. The red arrow in c and e points to the nucleotide change in the protospacer DNA compared to the “wild type” sequence in a. The protospacer DNA 3' nucleotide and the CRISPR locus strand biases in a, c, e are plotted in b, d and f, respectively, as percentages of integration events within the CRISPR locus. The black and clear bars represent the (−) and (+) strands of the CRISPR locus, respectively. NS corresponds to not significant and *p<0.0001 by Chi-square test. The n values for b, d and f are 5,623, 5,685 and 12,453 reads along the CRISPR locus, respectively.

Extended Data Figure 10. Model of the CRISPR–Cas adaptive immunity pathway in E. coli.

Mature double-stranded protospacers bearing a 3' C-OH are site-specifically integrated into the leader-end of the CRISPR locus. Correct protospacer integration (left) results in the 5'G/3'C as the first nucleotide of the spacer, proximal to the leader. After transcription of the CRISPR locus and subsequent crRNA processing, foreign DNA destruction is initiated by strand-specific recognition of the 3'-TTC-5' PAM sequence in the target strand by the crRNA-guided Cascade complex. Incorrect protospacer integration (right) cannot initiate foreign DNA destruction due to the inability for the crRNA to recognize the strand with the 3'-TTC-5' PAM. Thus, foreign DNA interference during CRISPR–Cas adaptive immunity relies on the Cas1–Cas2 complex for correctly orienting the protospacer during integration.

Figure 1. The Cas1–Cas2 complex integrates protospacers in vitro

a, Schematic of the in vitro integration assay (PDB code 4P6I for Cas1–Cas2). b, The presence of Cas1, Cas2 and a protospacer results in the conversion of the supercoiled pCRISPR into relaxed, linear and Band X products. c, Neither the Cas1 H208A active site mutant nor and the complex formation-defective Cas2 β6–β7 deletion mutant support the reaction. The Cas2 E9Q active site mutant (lane 5 from the marker) is as active as the wild-type. d, Salt- and metal-dependence of radiolabeled protospacer integration into pCRISPR. e, Same as c except using radiolabeled protospacers. The data presented in b-e are representative of at least three replicates.

Figure 2. Half-site, full-site integration and pCRISPR topoisomer products

a, Schematic of half-site and full-site integration products. b, Linearization of the integration products (lane 4). Lane 3 is the un-treated reaction products. c, Linearization of integration products from radiolabeled protospacer reactions. d, The time course reveals the initial formation of relaxed products, followed by Band X. The inset reveals the products detected using ³²P-labeled protospacers. e,f, Analysis of gel-purified relaxed and Band X on agarose gels pre-stained with ethidium bromide (e) or post-stained after electrophoresis (f). g, Schematic of the disintegration reaction. h, Native polyacrylamide gel analysis of the disintegration reaction. The data presented in b-f, h are representative of at least three replicates.

Figure 3. Integration requires 3'-OH protospacer ends and supercoiled target DNA

a,b, Integration assays using single-stranded DNAs and either –OH or –PO₄ at the 3' or 5' ends of (a) unlabeled or (b) radiolabeled protospacers. S1 corresponds to one strand of the protospacer and S2 corresponds to the complementary strand. c, Comparison of protospacer integration into different DNA targets. d,e, Restriction enzyme digestion of pCRISPR, either in a pUC19 (d) or pACYC backbone (e), after the integration assay detects integration into the CRISPR fragment (green arrows). The data presented in a-e are representative of at least three replicates.

Figure 4. Protospacers are specifically integrated into the CRISPR locus

a, Integration sites along pCRISPR. b, Magnified view of the integration sites along the ~1 kb CRISPR locus. The cyan peaks represent positions where the 3' T of the protospacer DNA was integrated whereas the black peaks represent the C 3'-OH integration events. The protospacer sequence is depicted above the plot. c, Integration sites along pUC19. d, Comparison of C 3'-OH or T 3'-OH selection in the total reads from pCRISPR and pUC19 targets (n=7,866 reads for pCRISPR and n=5,524 reads for pUC19, Chi-square test, *p<0.0001). e, Schematic of DNA cruciform formation of the repeat sequences. The orange arrows depict the cleavage sites.

Figure 5. Model of protospacer integration during CRISPR–Cas adaptive immunity

The first nucleophilic attack occurs on the minus strand of the first repeat, distal to the leader, by the C 3'-OH end of the protospacer. After half-site intermediate formation, the second integration event occurs on the opposite strand at the leader-repeat border. The resulting single-stranded DNA gaps are repaired by yet uncharacterized mechanisms and the protospacer is fully integrated with the G as the first nucleotide at its 5' end. The asterisk denotes the duplication of the first repeat, as previously observed in vivo^-.