Deployable CRISPR-Cas13a diagnostic tools to detect and report Ebola and Lassa virus cases in real-time

Abstract

Recent outbreaks of viral hemorrhagic fevers (VHFs), including Ebola virus disease (EVD) and Lassa fever (LF), highlight the urgent need for sensitive, deployable tests to diagnose these devastating human diseases. Here we develop CRISPR-Cas13a-based (SHERLOCK) diagnostics targeting Ebola virus (EBOV) and Lassa virus (LASV), with both fluorescent and lateral flow readouts. We demonstrate on laboratory and clinical samples the sensitivity of these assays and the capacity of the SHERLOCK platform to handle virus-specific diagnostic challenges. We perform safety testing to demonstrate the efficacy of our HUDSON protocol in heat-inactivating VHF viruses before SHERLOCK testing, eliminating the need for an extraction. We develop a user-friendly protocol and mobile application (HandLens) to report results, facilitating SHERLOCK's use in endemic regions. Finally, we successfully deploy our tests in Sierra Leone and Nigeria in response to recent outbreaks.

Fig. 1. Detection of EBOV.

a Schematic of the SHERLOCK EBOV assay. b, c Detection of a serial dilution of EBOV synthetic DNA using (b) mean fluorescence of three technical replicates and (c) lateral flow readouts. Error bars indicate ±1 SD for three technical replicates. d Test of cross-reactivity using MARV, EBOV, and LASV viral seedstock cDNA. Heat map is measured in Fluorescence (a.u.). e SHERLOCK testing of cDNA extracted from 12 confirmed EBOV-positive and 4 confirmed EBOV-negative samples collected from suspected EVD patients during the 2014 outbreak in Sierra Leone. Error bars indicate 95% confidence interval. f Four of the samples from e were also tested by collaborators using lateral flow detection. g, h Detection of serial dilution of synthetic RNA from Ituri, DRC and Makona, Sierra Leone using (g) fluorescence where error bars indicate ±1 SD for three technical replicates and (h) lateral flow readouts carried out at USAMRIID. Source data are in the Source Data file.

Fig. 2. Detection of LASV clade II and IV.

a Schematic of LASV SHERLOCK assays targeting the two most common clades of LASV: clades II (LASV-II assay) and IV (LASV-IV assay). For the LASV-II assay, three crRNAs were designed and tested. Two crRNAs are multiplexed to encompass the clade’s genetic diversity (IIA/IIB or IIA/IIC). Each crRNA was tested using three technical replicates. b–d Heat maps are measured in fluorescence (a.u.). b Detection of LASV RNA from suspected LF clinical samples using crRNAs IIA, IIB, IIC, or a combination of crRNAs. c Test of cross-reactivity between different viral species using MARV, EBOV, and LASV viral seedstock cDNA. The LASV-II and LASV-IV assays do not cross-react with MARV or EBOV seed stocks. d Test of cross-reactivity between LASV clade-specific assays using clinical samples from recent outbreaks in Nigeria and Sierra Leone. The LASV-II and LASV-IV assays provide clade-specific detection. e SHERLOCK testing using the LASV-II assay of RNA extracted from seven confirmed LASV-positive and three confirmed LASV-negative samples collected from suspected LF patients in Nigeria during the 2018 outbreak. Error bar indicates 95% confidence interval. f Results from e were compared head-to-head to those from the gold standard Nikisins RT-qPCR assay, next-generation sequencing (genome assembled), and lateral flow detection. g SHERLOCK testing using the LASV-IV assay of RNA extracted from seven confirmed LASV-positive and three confirmed LASV-negative samples collected from suspected LF patients in Sierra Leone. Error bar indicates 95% confidence interval. h Results from g were compared head-to-head to those from the gold standard Nikisins RT-qPCR assay, a second Broad RT-qPCR, NGS, and lateral flow detection. Source dare are in the Source Data file.

Fig. 3. HUDSON safety testing.

a Schematic overview of the HUDSON, SHERLOCK inactivation validation. Viral inactivation includes dilution with EDTA : TCEP and a 20 min 37 °C inactivation of nucleases. All final results were determined using lateral flow due to the inability to carry out appropriate fluorescent analysis in the BSL4 facility. b Lateral flow detection of spiked blood, urine, and saliva inactivated at either 70 °C or 95 °C. Serial dilution shown are PFU/mL. All assays were carried out in the BSL4 facility.

Fig. 4. Quantification of SHERLOCK lateral flow strips using HandLens, an Android app prototype.

Internal image analysis pipeline of the SHERLOCK detector app (HandLens). a Images of two positive sample lateral flow strips are imported to the app. b The relevant signal regions of the lateral flow strips are detected and demarcated by red bounding boxes. c Bilateral filtering is used to extract and smoothen the signal regions from the raw input image. d Contrast within the image is increased by applying contrast limited adaptive histogram equalization (CLAHE). e The signal is linearized for downstream signal processing; the red curves indicate the signal extracted after applying CLAHE, whereas the blue curves indicate the signal levels if the CLAHE step is skipped. f The strip reader app works by allowing the user to take a picture of the test strips where a rectangle can be used to select the control strip on the leftmost side. The raw image data is sent to a backend server that runs the signal detection algorithm and returns the binary and semi-quantitative predictions for each strip.