CRISPR interference directs strand specific spacer acquisition

Abstract

Background: CRISPR/Cas is a widespread adaptive immune system in prokaryotes. This system integrates short stretches of DNA derived from invading nucleic acids into genomic CRISPR loci, which function as memory of previously encountered invaders. In Escherichia coli, transcripts of these loci are cleaved into small RNAs and utilized by the Cascade complex to bind invader DNA, which is then likely degraded by Cas3 during CRISPR interference.

Results: We describe how a CRISPR-activated E. coli K12 is cured from a high copy number plasmid under non-selective conditions in a CRISPR-mediated way. Cured clones integrated at least one up to five anti-plasmid spacers in genomic CRISPR loci. New spacers are integrated directly downstream of the leader sequence. The spacers are non-randomly selected to target protospacers with an AAG protospacer adjacent motif, which is located directly upstream of the protospacer. A co-occurrence of PAM deviations and CRISPR repeat mutations was observed, indicating that one nucleotide from the PAM is incorporated as the last nucleotide of the repeat during integration of a new spacer. When multiple spacers were integrated in a single clone, all spacer targeted the same strand of the plasmid, implying that CRISPR interference caused by the first integrated spacer directs subsequent spacer acquisition events in a strand specific manner.

Conclusions: The E. coli Type I-E CRISPR/Cas system provides resistance against bacteriophage infection, but also enables removal of residing plasmids. We established that there is a positive feedback loop between active spacers in a cluster--in our case the first acquired spacer--and spacers acquired thereafter, possibly through the use of specific DNA degradation products of the CRISPR interference machinery by the CRISPR adaptation machinery. This loop enables a rapid expansion of the spacer repertoire against an actively present DNA element that is already targeted, amplifying the CRISPR interference effect.

Figure 1. Graphical representation of spacers integrated in the various PIMs.

Both CRISPR locus 2.1 and 2.3 of each PIM are displayed. The newly acquired spacer positions (−3, −2, −1) and original spacer positions (1, 2, 3) correspond to the order of spacers downstream from the leader sequence (displayed as black triangle). White and red spacer boxes indicate that the corresponding protospacer is located on the – or + strand of the plasmid, respectively. PIMs clustered in grey boxes possibly share a common ancestor. Spacers have an AAG PAM unless indicated otherwise. Additional information on spacers is given in Table S1.

Figure 2. Effect of integrated spacers on retransformation efficiency.

Transformation efficiencies of various PIMs and the control (Wild type E. coli K12 W3110) are given in a logarithmic scale as colony forming units (CFU) per µg of pRSF-1b plasmid DNA. For each PIM, the number of spacers integrated in either CRISPR locus 2.1 or 2.3 is given. All spacers have an AAG PAM, unless indicated otherwise. The exact spacer composition of each PIM is given in Table S1.

Figure 3. Linear display of pRSF-1b and locations of protospacers.

The (+) and (−) strands and corresponding protospacers are coloured red and black, respectively. Kanamycin marker (Kan), Origin of replication (Ori) and lacI (LacI) are shown as arrows. Protospacers have an AAG PAM unless indicated otherwise.

Figure 4. Graphical representation of AG and GC contents of each observed and possible spacer.

Observed spacers (⧫) are spacers integrated in CRISPR loci 2.1 and 2.3 (Table S1). These spacers are 32 or 33-mers with various PAMs. Possible spacers (Ο) are all 32-mers found on pRSF-1b directly downstream of an AAG PAM.

Figure 5. PAM and repeat-end correlation.

(A): PAMs of observed spacers and the co-occurring trinucleotide repeat-ends associated with these spacers. Notice that the spacer-proximal nucleotide of the repeat end is identical to the protospacer-proximal nucleotide of the PAM. (B): Schematic of the proposed mechanism for spacer acquisition during CRISPR adaptation. A protospacer with specific PAM is selected after which it is processed into the pre-spacer (at least 33–34 bp), which contains the last nucleotide of the PAM (the pre-spacer could be single-stranded or double-stranded). The pre-spacer is than integrated at the leader proximal end of the CRISPR locus. The nucleotide derived from the PAM forms the last nucleotide of the repeat. (C): R-loop formation by mature crRNA (61 nucleotides) during CRISPR interference. Notice that the last nucleotide of the repeat (the nucleotide derived from the PAM) is complementary to the target DNA sequence. It remains unknown whether base-pairing between these nucleotides is important for interference.

Figure 6. Model of the strand specific positive feedback loop.

Cells with a spacer against a known and actively present invader DNA produce targeting Cascade complexes in the expression stage. In the interference stage, Cascade binds the target dsDNA after which the target is cleaved and degraded by Cas3 . DNA degradation products generated by Cascade and Cas3 (which could be ssDNA or dsDNA) act as precursors for new spacers in the adaptation phase in a strand-specific manner. By integration of these strand-specific precursors, the spacer repertoire against an actively present invader is expanded, completing the positive feedback loop.