Developing, characterizing and modeling CRISPR-based point-of-use pathogen diagnostics

Abstract

Recent years have seen intense interest in the development of point-of-care nucleic acid diagnostic technologies to address the scaling limitations of laboratory-based approaches. Chief among these are combinations of isothermal amplification approaches with CRISPR-based detection and readouts of target products. Here, we contribute to the growing body of rapid, programmable point-of-care pathogen tests by developing and optimizing a one-pot NASBA-Cas13a nucleic acid detection assay. This test uses the isothermal amplification technique NASBA to amplify target viral nucleic acids, followed by Cas13a-based detection of amplified sequences. We first demonstrate an in-house formulation of NASBA that enables optimization of individual NASBA components. We then present design rules for NASBA primer sets and LbuCas13a guide RNAs for fast and sensitive detection of SARS-CoV-2 viral RNA fragments, resulting in 20 - 200 aM sensitivity without any specialized equipment. Finally, we explore the combination of high-throughput assay condition screening with mechanistic ordinary differential equation modeling of the reaction scheme to gain a deeper understanding of the NASBA-Cas13a system. This work presents a framework for developing a mechanistic understanding of reaction performance and optimization that uses both experiments and modeling, which we anticipate will be useful in developing future nucleic acid detection technologies.

Fig. 1 ∣. In-house NASBA formulation provides flexibility for reaction optimization.

a, Schematic overview of NASBA, which uses cycles of reverse transcription, RNase H-mediated degradation and T7 transcription to convert and amplify an input RNA into an antisense activator RNA. The antisense activator serves as an input to Cas13a-based detection which generates a fluorescent output signal. In-house NASBA formulation enables screening of different reverse transcriptases (RTs). One-pot in-house NASBA-Cas13a targeting the ORF1ab of the SARS-CoV-2 genome, with 0, 2 or 20 fM synthetic SARS-CoV-2 genome and 1 U/μL of b, avian myeloblastosis virus (AMV) RT, c, ProtoScript II RT, or d, Moloney murine leukemia virus (M-MuLV) RT. Readout was observed only with M-MuLV RT. e, Schematic of the steps in NASBA with a cartoon of viral genome structures that could influence where NASBA primers bind and impact NASBA efficiency. f, To test different primer sets, RNA products were extracted from one- pot NASBA (lacking Cas13a) and analyzed by urea-PAGE. Reactions were initiated using 2.5 U/μL M-MuLV RT with 0 (−) or 20 (+) fM synthetic SARS-CoV-2 genome. The expected RNA product for each primer set is boxed and its length is indicated, unless the band was not present as in the case of sets 1 and 6 (expected products 104 nt and 164 nt, respectively). Data in b–d are n=3 independent biological replicates, each plotted as a line with raw fluorescence standardized to MEF. Shading in b–d indicates the average of the replicates ± standard deviation. Data in f are one representative of n=3 independent biological replicates; the other replicates and the uncropped, unprocessed image in f are in Supplementary Data 2. Sequences of primers and gRNAs are listed in Supplementary Data 1.

Fig. 2 ∣. Screening of LbuCas13a gRNAs identifies factors that could impact cleavage efficiency.

a, Predicted secondary structure of activator RNA 7 generated from NASBA with Primer Set 7. Regions targeted by gRNAs are shaded in different colors. Fluorescence kinetics from NASBA-Cas13a at varying concentrations of synthetic SARS-CoV-2 genome with b, gRNA 7–1, c, gRNA 7–2, or d, gRNA 7–3 with predicted secondary structures of each gRNA shown above. e, Predicted secondary structure of activator RNA 8 generated from NASBA with Primer Set 8. Regions targeted by gRNAs are shaded in different colors. Fluorescence kinetics from NASBA-Cas13a at varying concentrations of synthetic SARS-CoV-2 genome with f, gRNA 8–1, g, gRNA 8–2, or h, gRNA 8–3 with predicted secondary structures of each gRNA shown above. Data are n=3 independent biological replicates, each plotted as a line with raw fluorescence standardized to MEF. Shading indicates the average of the replicates ± standard deviation.

Fig. 3 ∣. High-throughput screening of the enzyme concentration landscape suggests model assumptions and reveals reaction design principles, shown for Data Set 2.

a, Different amounts of input RNA, RT, T7 RNAP, RNase H, and Cas13a-gRNA were dispensed in triplicate (independent replicates) using an Echo liquid handling platform. Assembled NASBA-Cas13a reactions were run and fluorescence data collected and averaged across triplicate measurements to arrive at a mean dynamic trajectory. The dynamic trajectory was then normalized by the maximum readout value, such that the maximum readout value across the entire experiment (all conditions) was set to 1. b, Hill functions were fit to each normalized time course trajectory, and summary metrics (n, t_1/2, F₀, and F_max) were parameterized. A representative time course trajectory and Hill plot is shown as an example. c, For each time course, R² values for the normalized experimental data (points) and Hill fit (dotted line) were calculated and plotted as a histogram. Histograms of values across all conditions were computed for: d, t_1/2 , and e, F_max. f–h, Time course trajectories for data subsets varying: f, RT, g, T7 RNAP, and h, RNase H, each using two different input RNA concentrations. Shading indicates the average of the triplicates ± standard deviation. This process was repeated for each experimental data set, but Data Set 2 is highlighted here because it was in closest alignment with all modeling objectives.

Fig. 4 ∣. Mathematical modeling recapitulates key experimental observations.

a, Schematic of key reaction stages (top) and mechanisms (bottom) in the model. A more detailed depiction of the model is in Supplementary Fig. 21. b, Key mechanisms included in the model. Each mechanism is involved in the reaction stage indicated to the left of each mechanism description. c-e, Hill-like functions were fit to each simulated time course trajectory, and summary metrics (n, t_1/2, F₀, and F_max) were parameterized (Fig. 3b is a visual representation of these metrics). c, For each time course, R² for the normalized simulated data and Hill fit was calculated; values are plotted as a histogram. Histograms of values across all conditions in the simulated training data set were calculated for: d, t_1/2, and e, F_max, f–h, Time course trajectories for simulated data subsets: f, mid-range RNase H and T7 RNAP and high Cas13a-gRNA, g, mid-range RNase H and RT and high Cas13a-gRNA, and h, mid-range T7 RNAP and RT and high Cas13a-gRNA.

Fig. 5 ∣. Limit of detection analysis.

Fluorescence values at 150 minutes from NASBA-Cas13a with varying concentrations of synthetic SARS-CoV-2 genome using a, gRNA 2–1, b, gRNA 7–1, c, gRNA 7–2, or d, gRNA 8–1. Data are n=3 independent biological replicates, each plotted as a point with raw fluorescence values standardized to MEF. Bar height represents the average of the replicates. Error bars indicate the average of the replicates ± standard deviation. Input RNA concentrations for which signal is distinguishable from background (without input RNA) were determined using a two-sided, heteroscedastic Student’s t-test. ***P < 0.001, **P = 0.001–0.01, *P = 0.01–0.05). P values and degrees of freedom are listed in Supplementary Data 3.