Rapid genetic screening with high quality factor metasurfaces

Abstract

Genetic analysis methods are foundational to advancing personalized medicine, accelerating disease diagnostics, and monitoring the health of organisms and ecosystems. Current nucleic acid technologies such as polymerase chain reaction (PCR) and next-generation sequencing (NGS) rely on sample amplification and can suffer from inhibition. Here, we introduce a label-free genetic screening platform based on high quality (high-Q) factor silicon nanoantennas functionalized with nucleic acid fragments. Each high-Q nanoantenna exhibits average resonant quality factors of 2,200 in physiological buffer. We quantitatively detect two gene fragments, SARS-CoV-2 envelope (E) and open reading frame 1b (ORF1b), with high-specificity via DNA hybridization. We also demonstrate femtomolar sensitivity in buffer and nanomolar sensitivity in spiked nasopharyngeal eluates within 5 minutes. Nanoantennas are patterned at densities of 160,000 devices per cm², enabling future work on highly-multiplexed detection. Combined with advances in complex sample processing, our work provides a foundation for rapid, compact, and amplification-free molecular assays.

Fig. 1. Design of high-Q sensors.

a Metasurface arrays of high-Q guided mode resonators consisting of perturbed chains of silicon blocks interfaced with DNA probes for targeted gene detection. Geometrical parameters of the resonators are height (h) = 500 nm, w₀ = 600 nm, thickness (t) = 160 nm, block spacing (a_y = 330 nm), inter-chain spacing (a_x = 10 μm), and Δw varied between 30–100 nm. b Simulated electric near-field enhancements for a resonator with Δw = 50 nm. c Simulated cross-polarized transmission response of metasurface illuminated with normally incident linearly polarized plane waves. Responses normalized to intensity maximum of the perturbed resonator. d SEM micrographs of metasurface devices composed of multiple individually monitored and tuned resonators. e Spectral image from the array with 7 resonators where C denotes nanostructures with no perturbation Δw = 0 nm and R1-R5 having perturbation Δw = 50 nm. Resonance positions are modulated by adjusting block length where w₀ = 595 nm for R1 & R5, w₀ = 600 nm for R2 & R4, and w₀ = 605 nm for R3 to form the observed chevron pattern. f Row averaged transmitted intensities corresponding to (e).

Fig. 2. Fluid cell characterization of metasurfaces.

a Photo of metasurface chip enclosed in fluid cell. b Representative spectra from resonators with varying Δw. Solid lines represent fits to a Lorentzian oscillator. c Quality factor of resonances with different Δw. Bold markers and error bars are the mean and standard deviation for N = 30 resonators at each condition. Stars represent simulated values and the dashed line is a fit to predicted values from coupled mode theory (Supplementary Note 3). d Quality factor as a function of resonator spacing where mean and standard deviation are for N = 5 resonators at each condition.

Fig. 3. DNA monolayer functionalization and resonant wavelength shift measurement.

a Schematic of chemical components utilized in immobilizing DNA self-assembled monolayers (SAM) onto the silicon nanostructures. Target DNA fragments for this study are portions of the E and ORF1b genes from the SARS-CoV-2 virus. b Experimentally measured and c simulated resonance wavelength shift responses with the addition of each molecular layer in the SAM, including complementary nCoV.E target binding. Markers in (b) correspond to measured data points while solid lines show fits to a Lorentzian oscillator. The difference in absolute wavelength values between experimental and simulated spectra can be attributed to slight dimension variations in the fabricated structures. d Total resonant wavelength shift during SAM functionalization and DNA sensing as referenced from initial measurements on bare silicon structures. Markers represent individual measurements from N = 75 independent resonator devices and bolded markers and error bars are the mean and standard deviation of the measurements.

Fig. 4. Biosensing demonstration with SARS-CoV-2 gene fragment targets.

a Measured spectra from individual resonators indicate significant wavelength shifts of ~ 0.2 nm with complementary DNA binding and minimal signal changes when introduced to non-complementary sequences. b Concentration-dependent binding responses for both nCoV.E and HKU.ORF1 targets incubated on metasurface devices functionalized with only nCoV.E complementary probes. Error bars indicate standard deviations of measurements from N = 20 measurements from distinct resonators for each target and concentration condition. The limit of detection is estimated based on the mean + 3 standard deviations of the blank measurements. Dashed lines show fits to the Hill equation (Supplementary Note 8).

Fig. 5. Kinetic binding response and measurement in clinical nasopharyngeal samples.

a Time-dependent binding responses from 10 distinct resonators exposed to 1 fM, 1pM, 1nM, and 1μM concentrations of nCoV.E target molecules. b Demonstration of gene fragment detection in clinical nasopharyngeal eluates. Negative samples contain random and scrambled genetic material from nasopharyngeal swabs that have been confirmed negative for SARS-CoV-2 via RT-PCR. Target nCoV.E molecules are spiked into the negative nasopharyngeal eluates at a concentration of 100 nM for the positive sample. Schematics in Fig. 5b were created with BioRender.com.