A randomized multiplex CRISPRi-Seq approach for the identification of critical combinations of genes

Abstract

Identifying virulence-critical genes from pathogens is often limited by functional redundancy. To rapidly interrogate the contributions of combinations of genes to a biological outcome, we have developed a multiplex, randomized CRISPR interference sequencing (MuRCiS) approach. At its center is a new method for the randomized self-assembly of CRISPR arrays from synthetic oligonucleotide pairs. When paired with PacBio long-read sequencing, MuRCiS allowed for near-comprehensive interrogation of all pairwise combinations of a group of 44 Legionella pneumophila virulence genes encoding highly conserved transmembrane proteins for their role in pathogenesis. Both amoeba and human macrophages were challenged with L. pneumophila bearing the pooled CRISPR array libraries, leading to the identification of several new virulence-critical combinations of genes. lpg2888 and lpg3000 were particularly fascinating for their apparent redundant functions during L. pneumophila human macrophage infection, while lpg3000 alone was essential for L. pneumophila virulence in the amoeban host Acanthamoeba castellanii. Thus, MuRCiS provides a method for rapid genetic examination of even large groups of redundant genes, setting the stage for application of this technology to a variety of biological contexts and organisms.

Keywords: Legionella pneumophila; genetics; genomics; infectious disease; intracellular pathogen; legionella pneumophila; microbiology; translocated effectors.

Figure 1.. Intracellular growth of Lp02(dcas9) upon CRISPRi gene silencing with predetermined 10-plex arrays.

(A) Gene silencing efficiency assay. Each of the ten genes targeted by one of the six indicated MC arrays was assayed for gene repression by quantitative polymerase chain reaction (qPCR). RNA levels in the Lp02(dcas9) strain bearing the CRISPR array were compared to that bearing an empty vector. Data are a summary of two replicates shown side-by-side. Horizontal bars indicate mean fold repression of all targets of the array. (B) L. pneumophila intracellular growth assay. Host cells were challenged at a multiplicity of infection (MOI) of 0.05 (U937 macrophages) or 0.03 (Acanthamoeba castellanii) with Lp02(dcas9) bearing the indicated MC arrays. Colony forming units (CFUs) of samples taken 2 hr post infection (hpi) and either 72 (U937 macrophages) or 48 (A. castellanii) hpi were determined, and fold growth of Lp02(dcas9) bearing the indicated MC arrays relative to that of Lp02(dcas9) bearing the empty vector was plotted. Numbers below 1 indicate a growth defect upon gene silencing. BD, below detection (arbitrarily set to –100). Horizontal bars indicate mean fold growth vs. vector using data from three replicates.

Figure 2.. Cloning strategy for de novo self-assembly of CRISPR array libraries.

(A) Nucleotide sequence of R-S-R building blocks. Each R-S-R element is composed of a top and bottom oligonucleotide. The 24 bp spacer sequence (black font; shown for crRNA^mavN as an example) is flanked by sequences of the upstream (red) and downstream (blue) repeat element, with each end containing sticky overhangs (green). (B) Nucleotide sequence of attB4r-R and R-attB3r ‘dead ends’ with only one sticky overhang each (green). (C) Array self-assembly, size selection, and cloning. R-S-Rs and ‘dead end’ elements were allowed to self-assemble in a single tube and then ligated together and incorporated into an interim cloning vector. Arrays excised from an interim cloning vector were subjected to gel electrophoresis to separate them according to size. RE, restriction enzyme. After gel extraction, arrays of 550–650 bps and 650–800 bps in size were cloned into a donor plasmid such that three additional elements, namely the tracrRNA, a tet promoter, and a rrnB T1 terminator, could assemble with the arrays into the destination vector by Invitrogen Multisite Gateway Pro cloning. Final constructs were introduced into Lp02(dcas9) by electroporation.

Figure 2—figure supplement 1.. Model of the Legionella-containing vacuole bearing transmembrane effectors.

L. pneumophila translocates >300 effector proteins via a T4SS into a host cell to re-wire cellular pathways to evade the lysosome and establish a replication vacuole known as the Legionella-containing vacuole (LCV). It is hypothesized that transmembrane effectors are incorporated into the LCV for nutrient acquisition, detoxification, and membrane fusion. Diagram made using BioRender (https://biorender.com).

Figure 3.. Self-assembled CRISPR arrays are diverse in length and spacer composition.

(A) Two CRISPR array libraries were built from 44 R-S-R building blocks. Vectors from each library were harvested four times and sequenced. Venn diagrams show the overlap of unique spacer combinations, with the requirement of five or more raw (pre-sequence-depth normalized) read counts per array in each round of sequencing. (B) The distribution of plex-ness (spacer count) for arrays found in all four rounds of sequencing. (C) Chord diagrams link transmembrane effector (TME) genes, listed around the outside of the circle, each time spacers targeting each is present in an array. Link line width is weighted according to the number of times the combination of spacers was observed. Link line color is unique for each spacer and is constant between the two diagrams.

Figure 3—figure supplement 1.. Spacer abundance post CRISPRi induction.

The occurrence of each spacer within the plasmid libraries was quantified 24 hr post induction of expression. The fact that each spacer was well represented within the library indicated that the crRNA products of these spacers were not toxic to axenic L. pneumophila growth.

Figure 4.. Schematic overview of the experimental and bioinformatics pipeline of MuRCiS.

(A) During MuRCiS, a pooled population of L. pneumophila (dcas9) bearing the multiplex random CRISPR arrays were subjected to a selective pressure (intracellularity). Vectors were purified from both input and output bacteria populations, linearized, and submitted for long-read PacBio Sequel sequencing. For simplification, an array of mixed spacer population is shown as a single stretch of color, each color representing a different combination of spacers. In this example, the yellow and red arrays are lost in the output suggesting they silence critical combinations of genes. (B) Overview of the custom bioinformatics pipeline used to identify unique spacer combinations causing growth attenuation as defined by a fold reduction of five or more (https://github.com/GLBRC/MuRCiS_pipeline,copy archived at Myers and Donohue, 2023).

Figure 5.. Discovery of L. pneumophila gene combinations critical for growth in U937 macrophages.

(A) Correlation grid plotting all pairwise spacer combinations. The number of times two unique spacers were present in the sequenced array library is indicated by color-coding, ranging from light (rare) to dark (abundant). Black boxes, same spacer. (B) Total number of reads bearing the spacer which encodes crRNA^mavN. Counts in technical output replicates were summed. (C) Flowchart going from the number of total spacer combinations to the number of critical combinations identified. (D) Histogram indicating the plex-ness of all critical spacer combinations identified. (E) A list of virulence-critical combinations of genes and the corresponding fold reduction observed for each in each experiment. Library 1 results are shown above Library 2 results. (F) Intracellular growth assays of strains with deletions in the indicated genes. Results are given as fold growth (colony forming units [CFUs] harvested 72 hr post infection (hpi) vs. 2 hpi) compared to that of Lp02 (WT). Horizontal bars indicate mean fold growth of the deletion strain vs. WT strain for two or more experimental replicates. NG, no growth (arbitrarily set to –1000). (G) Intracellular growth assays of deletion strains that do not have a synergistic phenotype.

Figure 6.. Discovery of L. pneumophila gene combinations critical for growth in A. castellanii.

(A) Correlation grid plotting all pairwise spacer combinations. The number of times two unique spacers were present in the sequenced array library is indicated by color-coding, ranging from light (rare) to dark (abundant). Black boxes, same spacer. (B) Flowchart going from the number of total spacer combinations to the number of critical combinations identified. (C) Histogram indicating the plex-ness of all critical spacer combinations identified. (D) A list of virulence-critical combinations of genes and the corresponding fold reduction observed for each in each experiment. Library 1 results are shown above Library 2 results. (E) Intracellular growth assays of strains+pMME2400 with deletions in the indicated genes. Results are given as fold growth (colony forming units [CFUs] harvested 48 hr post infection [hpi] vs. 2 hpi) compared to that of Lp02+pMME2400 (WT). Horizontal bars indicate mean fold growth of the deletion strain vs. WT strain for two or more experimental replicates. BD, below detection (arbitrarily set to –100,000). (F) Intracellular growth assays of strains with deletions in the indicated genes having been identified in single-round CRISPRi experiments.