Diversity and evolution of class 2 CRISPR-Cas systems

Abstract

Class 2 CRISPR-Cas systems are characterized by effector modules that consist of a single multidomain protein, such as Cas9 or Cpf1. We designed a computational pipeline for the discovery of novel class 2 variants and used it to identify six new CRISPR-Cas subtypes. The diverse properties of these new systems provide potential for the development of versatile tools for genome editing and regulation. In this Analysis article, we present a comprehensive census of class 2 types and class 2 subtypes in complete and draft bacterial and archaeal genomes, outline evolutionary scenarios for the independent origin of different class 2 CRISPR-Cas systems from mobile genetic elements, and propose an amended classification and nomenclature of CRISPR-Cas.

Figure 1. The updated classification scheme for class 2 CRISPR–Cas systems

The class 1 systems are collapsed; all other systems shown are class 2 systems. New class 2 systems that were discovered using the computational pipeline in this study (see BOX 1) are indicated with blue circles for those that were described previously and with red circles for those that are presented here for the first time. For each class 2 system subtype, as well as for the five distinct variants of the provisional V-uncharacterized (V-U) subtype, the locus organization and the domain architecture of the effector and accessory proteins are schematically shown. RuvC-I, RuvC-II and RuvC-III are the three distinct motifs that contribute to the nuclease catalytic centre; numerals in the figure correspond to the respective RuvC motif. The portions of Cas9 proteins that roughly correspond to the recognition lobe and the protospacer-adjacent motif (PAM)-interacting domain are shown by maroon and pink shapes, respectively. The proposed new systematic gene names are shown in bold type in red boxes. Provisional gene names for effector protein candidates are shown below the respective shapes as follows: C2c1–10, class 2 candidate proteins 1–10; for subtype V-A, the previously introduced vernacular cpf1 is indicated. For subtype VI-A, cas1 and cas2 are shown with dashed contours to indicate that only some of these loci include the adaptation module. For the V-U5 variant, the inactivation of the RuvC-like nuclease domain is indicated by a cross. The specific strains of bacteria in which these systems were identified and locus tags for the respective protein-coding genes are also indicated. The abbreviation TM indicates a predicted transmembrane helix. The predicted type of target, namely DNA or RNA, is indicated for each subtype. A question mark next to the target indicates that the activity is only predicted and has not been demonstrated experimentally. The target is not indicated for the type V-U systems because their RNA-guided interference capacity is questionable, which is additionally emphasized by shading. tracrRNA, trans-acting CRISPR RNA.

Figure 2. The domain architecture of class 2 CRISPR effector proteins

For the type II and subtype V-A effectors, the crystal structures (indicated here by their RCSB Protein Data Bank (PDB) accession numbers (5CZZ and 5B43, respectively)) are available and the corresponding domain architectures are shown in detail. For the remainder of the proteins, the grey areas indicate structurally and functionally uncharacterized portions. RuvC-I, RuvC-II and RuvC-III, as well as higher eukaryotes and prokaryotes nucleotide-binding I (HEPN I) and HEPN II, denote the catalytic motifs of the respective nuclease domains of the CRISPR effectors. The bridge helix corresponds to an arginine-rich region that follows the RuvC-I motif. Other domains shown in the figure are denoted as follows: PAM interacting, protospacer-adjacent motif (PAM)-interacting domain; HNH, HNH family endonuclease domain, zinc finger domain with a CXXC.. CXXC motif (dots represent the variable distance between the two pairs of cysteines); HTH, putative DNA-binding helix–turn–helix domain; NUC, nuclease domain. The proteins and domains are shown approximately to scale. For each protein, the corresponding number of amino acids is indicated, and a ruler is shown on top of the figure to guide the eye. For the functionally characterized full-length effectors, the proposed new nomenclature (Cas12 and Cas13) is indicated, whereas for the uncharacterized putative effectors of type V-uncharacterized (V-U), only the provisional names are indicated. When, and if, functional evidence of a bona fide CRISPR response is reported for these effectors, they should be referred to as Cas12 proteins with the corresponding specifying letters. The putative V-U1, V-U2 and V-U5 effectors are larger than the typical TnpB proteins, whereas the V-U3 and V-U4 effectors are in the characteristic size range of TnpB. The asterisk at C2c5 indicates that this putative effector protein contains replacements of the catalytic residues of the RuvC-like nuclease domain and lacks the zinc finger.

Figure 3. Phylogenies of the type V and type VI-B effectors

a | A maximum-likelihood phylogenetic tree of TnpB nucleases, including the putative type V-uncharacterized (V-U) effectors that have a predicted active RuvC domain (Supplementary information S1 (box)). The major subtrees of transposon-encoded TnpB proteins are collapsed and indicated by triangles; some of these large groups include tnpB genes that are adjacent to CRISPR arrays, but these do not show evolutionary stability and thus cannot be identified as effectors. The four distinct evolutionarily stable groups of CRISPR-associated TnpB assigned to subtype V-U are shown by red triangles. Altogether, the tree includes 1,770 unique TnpB sequences, 403 of which are TnpB proteins that are encoded next to TnpA (autonomous transposons); 168 of these tnpB genes are adjacent to CRISPR arrays, and of these, 49 are assigned to four variants of subtype V-U (none of these belongs to autonomous transposons). In the subtrees that include the subtype V-U variants, bootstrap values (percentages) are shown for those subtrees that include the distinct V-U variants. For each type V-U variant, the bacterial taxa that harbour the majority of the respective loci are indicated. Dominant bacterial or archaeal lineages, if there are any, are indicated in the triangles. For the complete tree and accession numbers of all sequences, see Supplementary information S2 (box), part c and part h. b | Phylogenetic tree of the subtype VI-B Cas13b effector proteins. The tree was constructed as in part a, and the bootstrap values that are larger than 70% are indicated. The organization of typical cas13b loci for selected representatives (specifically those that are shown in bold) is schematically shown on the right. Variant 1 and variant 2 correspond to the two major branches of the tree and differ with respect to the domain architectures of the second smaller protein encoded in the locus; the domain architectures of these putative accessory proteins are shown above (for variant 1) and below (for variant 2) the respective loci schematics. The CRISPR arrays are shown schematically in brackets. TM indicates a predicted transmembrane domain, shown by blue boxes. Higher eukaryotes and prokaryotes nucleotide-binding (HEPN) domains are shown as maroon boxes. A, diverse archaea; B, diverse bacteria.

Figure 4. Possible routes of evolution for class 2 CRISPR–Cas systems

The figure depicts the three-step pathway of the evolutionary ‘maturation’ of type II, type V and type VI CRISPR–Cas systems. The systematic and/or provisional gene names are indicated below the respective ‘mature’ effector protein schematics and the proposed intermediate forms of type V systems. The first step involves the random insertion of a TnpB-encoding or insertion sequences Cas9-like protein B (IscB)-encoding transposon or a higher eukaryotes and prokaryotes nucleotide-binding (HEPN) domain RNase-encoding gene next to a CRISPR cassette for type II, type V and type VI systems, respectively. During the second step, the functional connection between this protein and the CRISPR array is established and co-evolution begins, in particular, in the form of the accumulation of specific insertions that facilitate CRISPR RNA (crRNA) binding. For type V systems, the intermediate forms that correspond to the first and second step are identified as different type V-uncharacterized (V-U) variants. Additional components of the system could have originated during the second step, such as trans-acting CRISPR RNA (tracrRNA) in the case of type II systems. During the third step, further insertions lead to increased specificity of crRNA and target binding, and enable interactions with accessory proteins, such as Csn2 for type II-A and a protein with predicted transmembrane (TM) domains for type VI-B. The adaptation module is only inserted into some of the class 2 CRISPR–cas loci during the third step. TS, target site.

Figure 5. Functional diversity of the experimentally characterized class 2 CRISPR–Cas systems

For each type of the class 2 CRISPR–Cas systems (and two subtypes in the case of type V), a schematic of the complex between the effector protein, the target, crRNA and, in the case of type II and type V-B systems, trans-acting CRISPR RNA (tracrRNA), is shown. The position of the protospacer adjacent motif (PAM) or the protospacer flanking site (PFS) is indicated by a red bar. The small red triangles show the position of the cut, or cuts, in the target DNA or RNA molecule. dsDNA, double-stranded DNA; ssRNA, single-stranded RNA.