Heritable and precise zebrafish genome editing using a CRISPR-Cas system

Abstract

We have previously reported a simple and customizable CRISPR (clustered regularly interspaced short palindromic repeats) RNA-guided Cas9 nuclease (RGN) system that can be used to efficiently and robustly introduce somatic indel mutations in endogenous zebrafish genes. Here we demonstrate that RGN-induced mutations are heritable, with efficiencies of germline transmission reaching as high as 100%. In addition, we extend the power of the RGN system by showing that these nucleases can be used with single-stranded oligodeoxynucleotides (ssODNs) to create precise intended sequence modifications, including single nucleotide substitutions. Finally, we describe and validate simple strategies that improve the targeting range of RGNs from 1 in every 128 basepairs (bps) of random DNA sequence to 1 in every 8 bps. Together, these advances expand the utility of the CRISPR-Cas system in the zebrafish beyond somatic indel formation to heritable and precise genome modifications.

Figure 1. Engineered RGNs induces heritable gene disruption.

(A) Schematic illustration of the RGN system. Engineered sgRNA:Cas9 system is depicted here based on the target sequence of the fh gene. sgRNA interacts with the complementary strand of the DNA target site harboring a 3′ protospacer adjacent motif (PAM) sequence (NGG) (yellow and red underlined text, respectively). sgRNA also interacts with Cas9 endonuclease (blue shape), resulting in DNA double-strand breaks (DSBs) at the target site. The reverse complement of the target site is highlighted as green text and the reverse complement of the PAM site is shown as red underlined text. The potential cleavage sites of Cas9 are indicated by arrowheads. This graphic representation is modified from a previous publication . (B) Mutation frequencies in the germline induced by engineered RGNs. Fish that have been injected with sgRNA and Cas9 mRNA at the 1-cell stage were screened for founders. The concentrations of the sgRNA and the Cas9 mRNA are as indicated. The somatic mutation rates induced by these combinations have been reported previously . The percentages of the injected embryos that developed normally at 1 day post-fertilization are shown. The sequences of the indel mutations identified in the germline are shown in Figure 2.

Figure 2. Germline mutation frequencies and sequences induced by engineered RGNs at the fh, gsk3b and apoea genes.

Fish that had been previously injected with engineered RGNs were screened for founders carrying heritable mutations. The tables summarize the founder screening results. The concentrations of sgRNA and Cas9 mRNA used for microinjection are indicated on top of each table. In the last column of each table, the numbers of embryos that possess indel mutations are shown outside of the parentheses, and the sizes of the indels are shown inside the parentheses.+, insertion; −, deletion. The mutant sequences identified in the germline are shown beneath each table. The wild-type sequence is shown at the top with the target sites highlighted in yellow and the PAM sequence highlighted as red underlined text. For some genes, the target site is on the reverse complement strand and in these cases the reverse complement of the target site is highlighted in green and the reverse complement of the PAM site is highlighted as red underlined text. Deletions are shown as red dashes highlighted in grey and insertions as lower case letters highlighted in blue. The net change in length caused by each indel mutation is to the right of each sequence (+, insertion; –, deletion). Note that some alterations have both insertions and deletions of sequence and in these instances the alterations are enumerated in the parentheses.

Figure 3. Targeted insertions achieved by co-injection of single-stranded oligonucleotides (ssODNs) and the RGN system.

The sgRNAs targeting fh and gsk3b have been described previously . For each gene, the wild-type sequence is shown at the top with the target site highlighted in yellow and the PAM sequence highlighted as red underlined text. For some cases the target sites are highlighted in green if the target sequences are in the reverse complement strand. The ssODNs containing 3–4 nucleotide (nt) insertions are shown beneath the wild-type sequences. The targeted insertions are highlighted as blue underlined capital letters. The target gene sequences identified in the injected embryos are shown beneath the ssODN sequences. Some of them contain only the precise intended changes (labeled as “precise” in parentheses on the right), while others contain additional indel mutations (deletions are shown as red dashes highlighted in grey and insertions as lower case letters highlighted in blue). The number of times each mutant sequence was isolated is shown in brackets.

Figure 4. Single-nucleotide substitution achieved by co-injection of single-stranded oligonucleotides (ssODNs) and the RGN system.

ssODNs carrying 1-nucleotide (nt) sequence substitutions (fh_MscI.S, fh_AgeI.S and fh_mPAM.S) were co-injected with Cas9 mRNA and the sgRNA targeting the fh gene. The wild-type fh sequence is shown at the top with the target site highlighted in yellow and the PAM sequence highlighted as red underlined text. The intended modifications are highlighted as blue underlined capital letters. The target gene sequences identified in the injected embryos are shown beneath the ssODN sequences. Some of them contain only the precise intended changes (labeled as “precise” in parentheses on the right), while others contain additional indel mutations (deletions are shown as red dashes highlighted in grey and insertions as lower case letters highlighted in blue). One of the identified sequence has a 1-bp point mutation (highlighted in bold and by an underline) in addition to the intended sequence. The number of times each mutant sequence was isolated is shown in brackets.

Figure 5. Somatic mutation frequencies induced by RGNs.

(A) GGN18 and GGN20 sgRNAs and their genomic target sequences. Sequences of the variable regions of the sgRNAs are shown here. These sgRNAs contain 1–2 nt mismatches to their genomic target sequences at the 5′ end. sgRNAs bind to the reverse complement strand of the DNA that possess the genomic target sequences (see illustration in Figure 1A). Matching genomic and sgRNA sequences are marked in red, while the mismatches are marked in blue. PAM is underlined. (B) The indel mutation frequencies were assess using the T7EI assay.