Comparative Evaluation of Genetically Encoded Voltage Indicators

Abstract

Imaging voltage using fluorescent-based sensors could be an ideal technique to probe neural circuits with high spatiotemporal resolution. However, due to insufficient signal-to-noise ratio (SNR), imaging membrane potential in mammalian preparations is still challenging. In recent years, many genetically encoded voltage indicators (GEVIs) have been developed. To compare them and guide decisions on which GEVI to use, we have characterized side by side the performance of eight GEVIs that represent different families of molecular constructs. We tested GEVIs in vitro with 1-photon imaging and in vivo with 1-photon wide-field imaging and 2-photon imaging. We find that QuasAr2 exhibited the best performance in vitro, whereas only ArcLight-MT could be used to reliably detect electrical activity in vivo with 2-photon excitation. No single GEVI was ideal for every experiment. These results provide a guide for choosing optimal GEVIs for specific applications.

Keywords: 1-photon microscopy; 2-photon microscopy; genetically encoded voltage indicators; in vitro; in vivo; optical field potential; single cell; wide-field imaging.

Figure 1.. Optical Responses to Depolarizing Voltage Steps with GEVIs In Vitro

(A) Schematic drawings of voltage indicators. ER, endoplasmic reticulum export sequence; TS, Golgi export trafficking signal. (B) Schematic drawing of voltage imaging strategy with 1-photon microscopy in vitro. (C–J) Representative averaged optical traces of ArcLight Q239 (C), ArcLight-MT (D), ASAP1 (E), ASAP2f (F), ASAP2s (G), Ace2N-4AA-mNeon (H), QuasAr2 (I), and Archerl (J) during depolarizing steps (from −70 to 30 mV). Five trials were averaged for each neuron. Shaded area represents SD of the mean. (K–N) Peak amplitude (K), SNR (L), rise time constants (M), and decay time constants (N) of ArcLight Q239 (n = 5 cells), ArcLight-MT (n = 5 cells), ASAP1 (n = 6 cells), ASAP2f (n = 5 cells), ASAP2s (n = 5 cells), Ace2N-4AA-mNeon (n = 5 cells), QuasAr2 (n = 4 cells), and Archerl (n = 5 cells) from the single exponential fits. Means ± SEMs are presented.

Figure 2.. Imaging Single Action Potential Responses In Vitro

(A–H) Average optical waveform of ArcLight Q239 (A), ArcLight-MT (B), ASAP1 (C), ASAP2f (D), ASAP2s (E), Ace2N-4AA-mNeon (F), QuasAr2 (G), and Archerl (H) in response to single action potentials induced by current injections. Ten trials were averaged for each neuron. Shaded areas represent the SD of the mean. (I–L) Comparison of GEVIs’ peak amplitude (I), SNR (J), rise time (K), and decay time (L) of ArcLight Q239 (n = 5 cells), ArcLight-MT (n = 6 cells), ASAP1 (n = 6 cells), ASAP2f (n = 5 cells), ASAP2s (n = 6 cells), Ace2N-4AA-mNeon (n = 5 cells), QuasAr2 (n = 5 cells), and Archerl (n = 5 cells). Means ± SEMs are presented. See also Figures S1, S2, and S3.

Figure 3.. Imaging Spike Trains Responses of GEVIs In Vitro

(A–H) Representative single electrical (top) and optical traces (bottom) in response to 10 Hz (left), 40 Hz (center), and 100 Hz (right) series of 10 action potentials. Optical traces of ArcLight Q239 (A), ArcLight-MT (B), ASAP1 (C), ASAP2f (D), ASAP2s (E), Ace2N-4AA-mNeon (F), QuasAr2 (G), and Archer1 (H) are shown. (I–K) Ratio of peak amplitude of GEVIs’ responses (means ± SEMs) as a function of spike number during trains of spikes evoked at 10 Hz (I), 40 Hz (J), and 100 Hz (K) (n = 10 trials of each GEVI).

Figure 4.. Photostability Analysis of GEVIs

(A) One-photon photobleaching kinetics of GEVIs. Cultured neurons expressing ArcLight Q239 (n = 6 cells), ArcLight-MT (n = 6 cells), ASAP1 (n = 6 cells), ASAP2f (n = 7 cells), ASAP2s (n = 9 cells), Ace2N-4AA-mNeon (n = 7 cells), QuasAr2 (n = 11 cells), and Archer1 (n = 8 cells) are continuously illuminated with a mercury arc lamp. (B) Time constants by 1-photon illumination (means ± SEMs). (C) Two-photon photobleaching kinetics of GEVIs. Cultured neurons expressing ArcLight Q239 (n = 8 cells), ArcLight-MT (n = 7 cells), ASAP1 (n = 6 cells), ASAP2f (n = 9 cells), ASAP2s (n = 11 cells), and Ace2N-4AA-mNeon (n = 8 cells) are continuously scanned at 30 Hz. (D) Time constants by 2-photon illumination (means ± SEMs). See also Figure S2

Figure 5.. One-Photon Wide-Field Voltage Imaging In Vivo

(A) One-photon images of the primary visual cortex expressing GEVIs or EGFP. Scale bar, 1 mm. (B) Two-photon images of the areas shown with the yellow square in (A). Scale bar, 100 μm. (C) Representative single-trial optical traces. Black lines indicate timing of visual stimulus using flash of light illumination for 10 ms. (D) Average visually evoked optical response over 10 trials. Black lines indicate the timing of the visual stimulus. (E and F) Peak fluorescence change (E) and SNR (F) of single trials measured with each GEVI or EGFP. Means ± SEMs are presented. (G and H) Peak fluorescence change (G) and SNR(H) of stimulus-triggered average. Means ± SEMs are presented, n = 5 field of views (FOVs) (EGFP, Ace2N-4AA-mNeon), 6 FOVs (ArcLight-MT, ASAP1, ASAP2s). One FOV was imaged in 1 mouse. ***p < 0.001 compared with EGFP, Dunnett test. See also Figure S4.

Figure 6.. Two-Photon Voltage Imaging with Cellular Resolution In Vivo

(A) Two-photon images of layer 2/3 pyramidal neurons in the visual cortex expressing GEVIs or EGFP in vivo. Scale bar, 40 μm. Arrows indicate cells whose optical signals are shown in (B) and (C). (B) Representative traces of each GEVI. Black lines indicate the timing of the visual stimuli. Ten visual stimuli were applied during each recording. (C) Average GEVI optical waveform in response to visual stimulus over 10 trials, with the shaded area representing the SD of the mean. Black lines indicate the timing of the visual stimuli. (D and E) Peak amplitude (D) and SNR (E) of single trials. Means ± SEMs are presented. (F and G) Peak amplitude (F) and SNR (G) of stimulus-triggered average. Means ± SEMs are presented, n = 18 cells from 5 mice (EGFP), 12 cells from 5 mice (ArcLight-MT), 19 cells from 7 mice (ASAP1), 20 cells from 6 mice (ASAP2s), and 25 cells from 5 mice (Ace2N-4AA-mNeon). ***p < 0.001 compared with EGFP. Dunnett test. See also Figures S4, S5, and S6.

Figure 7.. Two-Photon Optical Field Potential Imaging with GEVIs

(A) Two-photon images of primary visual cortex expressing GEVIs. Scale bar, 50 μm. (B) Representative traces of LFPs (black traces) and OFPs (colored traces). Fluorescent changes were imaged from all FOVs as a population. Black lines indicate the timing of the visual stimuli. (C) Average LFP (black traces) and optical waveform (colored traces) in response to visual stimuli over 10 trials, with shaded areas representing SD of the mean. The black lines indicate the timing of the visual stimuli. (D and E) Peak amplitude (D) and SNR (E) of single trials. Means ± SEMs are presented. (F and G) Peak amplitude (F) and SNR (G) of stimulus-triggered average. Means ± SEMs are presented, n = 10 FOVs from 5 mice (EGFP), 11 FOVs from 6 mice (ArcLight-MT), 9 FOVs from 7 mice (ASAP1), 9 FOVs from 4 mice (ASAP2s), and 12 FOVs from 6 mice (Ace2N-4AA-mNeon). **p < 0.01, ***p < 0.001 compared with EGFP. Dunnett test. See also Figure S7.