Novel gRNA design pipeline to develop broad-spectrum CRISPR/Cas9 gRNAs for safe targeting of the HIV-1 quasispecies in patients

Abstract

The CRISPR/Cas9 system has been proposed as a cure strategy for HIV. However, few published guide RNAs (gRNAs) are predicted to cleave the majority of HIV-1 viral quasispecies (vQS) observed within and among patients. We report the design of a novel pipeline to identify gRNAs that target HIV across a large number of infected individuals. Next generation sequencing (NGS) of LTRs from 269 HIV-1-infected samples in the Drexel CARES Cohort was used to select gRNAs with predicted broad-spectrum activity. In silico, D-LTR-P4-227913 (package of the top 4 gRNAs) accounted for all detectable genetic variation within the vQS of the 269 samples and the Los Alamos National Laboratory HIV database. In silico secondary structure analyses from NGS indicated extensive TAR stem-loop malformations predicted to inactivate proviral transcription, which was confirmed by reduced viral gene expression in TZM-bl or P4R5 cells. Similarly, a high sensitivity in vitro CRISPR/Cas9 cleavage assay showed that the top-ranked gRNA was the most effective at cleaving patient-derived HIV-1 LTRs from five patients. Furthermore, the D-LTR-P4-227913 was predicted to cleave a median of 96.1% of patient-derived sequences from other HIV subtypes. These results demonstrate that the gRNAs possess broad-spectrum cutting activity and could contribute to an HIV cure.

Figure 1

Workflow for CRISPR gRNA design. Whole blood was collected from a total of 269 HIV-1-infected samples from 168 patients enrolled in the Drexel CARES Cohort. Genomic DNA was isolated from PBMCs and a two round, nested PCR amplified the HIV-1 LTR as described in the Methods. These LTR amplicons were then deep-sequenced. The resulting sequence was then examined as follows for gRNA design: (1) The training set (100 samples) was scanned for all possible 20-mer protospacers; (2) an off-target search filtered out potentially dangerous gRNAs present in the human genome; (3) all remaining protospacers were evaluated against the training dataset to; (4) rank all gRNAs by their in silico efficiency; (5) package the top ranking gRNAs; and (6) validate the selected gRNAs against a held-out testing set (169 samples).

Figure 2

The distribution of Drexel gRNAs across the HIV-1 LTR. (A) The first 20 nucleotides of a gRNA bind to its complementary target sequence with variable tolerance to mismatches at different positions. Positions distal from the PAM have a higher tolerance to mismatches than proximal positions as indicated by the penalty score. The position-specific penalty score associated with mismatches between a gRNA and its target site was previously defined by Hsu et al. and others^,. (B) The chart contains the sequence of the top 10 Drexel gRNAs (D-LTR) predicted to have broad-spectrum activity against diverse HIV-1 LTRs and their location within the HIV-1 HXB2 reference genome. The PAM indicates the direction of gRNA targeting. *Temple LTR-A, B, C, and D gRNA sequences (now referred to as T-LTR-237050, LTR-158980, LTR-158121 and LTR-119555) were obtained from Hu et al. for comparison. Shuffle-LTR-268210 was used as a negative control. (C) The LTR schematic depicts the location of the Drexel gRNAs and the comparison gRNAs used in reference to the HXB2 LTR in relation to its structural features and common transcription factor binding sites.

Figure 3

In silico predicted cleavage for the Drexel gRNAs predict 100% efficacy against patient-derived HIV-1 subtype B sequences from the held-out test cohort. (A) Depicts the predicted efficacy of each individual gRNA to cleave patient-derived HIV sequences. Each point represents the percentage of a patient’s vQS that are predicted to be cleaved by each gRNA for the 169 samples in the held-out cohort. The boxplots denote the quartiles, median and 95% confidence intervals. (B) Indicates the fraction 169 held-out samples with at least one gRNA predicted to cleave at least 70% of the sample. Column 1 represents the best performing gRNA as presented in (A). Column two represents the combination of the best and second-best gRNA combined. D-LTR-P4-227913 and D-LTR-P10-287206 denote combinations of the top-4 and top-10 gRNAs respectively. (C) Depicts the number of predicted samples cut from the test cohort with an increasing number of gRNAs across the 169 held-out samples. A threshold is indicated where the number of efficacious gRNAs was maximized. The grey box is expanded in (D). (D) An expanded view of the grey box from (C) demonstrates that D-LTR-P4-227913 and D-LTR-P10-287206 were predicted to specifically cleave more samples than by chance alone. (E) Indicates the percentage of times each gRNA was found to be in the top-10 best performing gRNAs in the validation cohort across 1000 iterations of randomly choosing 100 training samples and 169 testing samples.

Figure 4

Treatment with Drexel gRNAs individually and together resulted in a significant reduction in LTR-driven transactivation. The HIV reporter cell lines TZM-bl (A) and P4R5 (B) were transfected with Cas9 and individual or packages of gRNAs concurrently with TatIIIB for 48 hr. Cells were then measured for viability (MTT, red bars) and reduction in LTR-driven ß-gal expression. In both cell types, Drexel gRNAs individually or together were able to effectively target and reduce LTR driven activity. C) P4R5 cells were transfected with Cas9 and different gRNAs concurrently with the fully infectious HIV-1 molecular clone pLAI. Cells were then measured for viability and reduction in LTR-driven ß-gal expression. Similarly, the Drexel gRNAs, individually or all together, were able to reduce viral gene expression and LTR driven expression through a number of proposed mechanisms. Statistical significance between Cas9/EV and experimental gRNAs was determined using a one-tailed, one-sample T-test and an *indicated p-values <0.05. Statistical significance between two gRNAs was determined by 2-tailed T-test comparing each item to the Cas9/EV samples. Each dot represents the average of four technical replicates.

Figure 5

Drexel gRNAs target the LTR and alter the TAR stem-loop. TZM-bl cells were treated individually with D-LTR-268145, D-LTR-113493, D-LTR-259783 and D-LTR-560262. Next generation sequencing of LTRs was performed to determine the predicted secondary structure of the TAR stem-loop. Depicted here is a randomly selected secondary TAR structure for each Drexel gRNA in comparison to HXB2 TAR. See additional secondary TAR structures in Fig. S4.

Figure 6

D-LTR-268145 can account for the genetic diversity of the vQS from patient-derived subtype B HIV sequences better than a previously published gRNA in a high sensitivity in vitro CRISPR/Cas9 cleavage assay. (A) LTR clones from Drexel CARES Cohort patients were amplified from PBMC genomic DNA, cloned, and sequenced. Mismatches between the D-LTR-268145 and T-LTR-237050 gRNA and the patient LTR target sites were aligned. The activity score indicated the predicted likelihood that the gRNA would cleave the target sequences with that particular mismatch or combination of mismatches. (B) In vitro CRISPR/Cas9 cleavage results of patient-derived HIV sequences representing the vQS. The number of clones in the vQS indicates the number of individual plasmids that were mixed in equal ratios. For example, patient sample A107 had 6 plasmid clones to make the vQS (clone A107-5, A107-13, A107-15, A107-16, A107-52 and A107-65) and mismatches within the target site for each clone was represented in subpanel A. Statistical significance was determined using Kolmogorov–Smirnov test and an * indicated p-values <0.05. (C) The scatter plot represents the correlation of the observed percent cleaved in the in vitro assay shown in B versus the predicted cleavage from the MIT activity score.

Figure 7

Drexel gRNAs are predicted to be highly effective at cleaving multiple HIV-1 subtypes in silico. (A) The number of patient-derived sequences from each subtype in the LANL database that overlap the gRNA binding site. Only those subtypes with at least 50 sequences across all binding sites are shown. (B) The percentage of patient-derived samples from each subtype that are predicted to be cleaved by the anti-HIV-1 gRNA. It is important to note that the gRNAs tested were designed using only subtype B sequences.