Systematic characterization of maturation time of fluorescent proteins in living cells

Abstract

The slow maturation time of fluorescent proteins (FPs) limits the temporal accuracy of measurements of rapid processes such as gene expression dynamics and effectively reduces fluorescence signal in growing cells. We used high-precision time-lapse microscopy to characterize the maturation kinetics of 50 FPs that span the visible spectrum at two different temperatures in Escherichia coli cells. We identified fast-maturing FPs from this set that yielded the highest signal-to-noise ratio and temporal resolution in individual growing cells.

Figure 1. Maturation kinetics and its impact on fluorescence signal in growing cells

(a), (b) and (c). Fraction of immature protein as a function of time after translational arrest with chloramphenicol in single cells. (a) mEGFP maturation kinetics shows a single exponential decay (dashed line). (b) mGFPmut2 exhibits a more complex maturation process with two kinetic steps (dashed lines). (c) wtGFP matures with a slow non-exponential rate that increases with time. Dashed red lines indicate the time it takes for 50%, t₅₀, and 90%, t₉₀, of FP to mature, respectively. (d) Fluorescence signal in growing cells vs F_{in vitro}=QY·ε multiplied by F_expression=amount of protein. Fluorescence signal is the mean fluorescence of single-cells (exponential growth in single-cell chemostat, M9 rich media, 37°C, mean from 70±20 cells, ±SEM). QY and ε are the values reported when the FPs were first published except for mVenusME and mCeruelanME; for these two FPs, we used our own in vitro data, see Online Methods. F_expression was estimated using SDS-PAGE gel densitometry (±SD, see Online Methods). For green FPs, data normalized by sfGFP data; for yellow FPs, by moxVenus data; for blue FPs, by SCFP3A data; and for red FPs by mRFP1*. Dotted line is the identity. Dilution is given by the doubling time of E. coli, t_gr=28.5±2min. (e) Fluorescence signal in growing cells vs F_{in vitro} × F_expression multiplied by F_mat=1/(1 + t₅₀/t_gr). Fluorescence signal data is the same as in (d). QY and ε were quantified in our laboratory independently, except for in vitro data of red FPs, see Online Methods. We have assumed that the in vitro brightness of mRFP1* and mCherry-L is the same as the in vitro brightness of mRFP1 and mCherry, respectively, because amino acid differences are not part of the β-barrel. Error bars calculated by propagation of QY, ε and t₅₀ errors.

Figure 2. Impact of maturation time on transcription dynamics

In growing cells, fluorescence signal associated with fast-maturing FPs can exhibit greater intensity and dynamic range than equally bright slow-maturing FPs. (a) Left: cartoon of a kymograph of a linear colony. Kymograph composed from the fluorescence channel of the time-lapse movie. Cells express stochastic bursts of an FP; intensity decreases because of dilution due to growth, thus creating the dark and bright bands in the kymograph. Right: kymograph made from the fluorescence channel showing that a fast FP reports brighter transcriptional events than a slower FP even when both fluorophores have the same in vitro brightness. Upper half, fast FP (mGFPmut2, ε·QY=39.3, t₅₀=5.6min); lower half, slow FP (mEGFP, ε·QY=45.5, t₅₀=14.5min); expression driven by the repressed P_lacZ promoter. (b) Distribution of fluorescence signal per cell for the fast (light green, n_cell=2489) and the slow FP (dark green, n_cell= 2310). Signal from the fast FP is always higher than that from the slow FP (Supplementary Fig. 14). Inset. In vitro brightness, fluorescence signal in growing cells, and dynamic range of the fast relative to the slow FP (Supplementary Fig. 15). (c) Black solid line: transcriptional burst that yields the same amount of either fast- or slow-maturing FP. (d) Time traces of the fluorescence production rate of the repressed P_lacZ using the fast or the slow FP. The detection limit (dashed line) is 3σ units above autofluorescence production rate; black dots indicate cell division, t_div=33min at 37 °C. Shaded bands indicate periods of promoter activity below the detection limit. (e) Autocorrelation of fluorescence production rate for the slow and the fast FP variants (characteristic decay times t_slowFP=24.5min and t_fastFP=6.3min). Both FPs are driven by the same promoter thus using the fast FP increases temporal resolution.