Quantitative Cell Cycle Analysis Based on an Endogenous All-in-One Reporter for Cell Tracking and Classification

Abstract

Cell cycle kinetics are crucial to cell fate decisions. Although live imaging has provided extensive insights into this relationship at the single-cell level, the limited number of fluorescent markers that can be used in a single experiment has hindered efforts to link the dynamics of individual proteins responsible for decision making directly to cell cycle progression. Here, we present fluorescently tagged endogenous proliferating cell nuclear antigen (PCNA) as an all-in-one cell cycle reporter that allows simultaneous analysis of cell cycle progression, including the transition into quiescence, and the dynamics of individual fate determinants. We also provide an image analysis pipeline for automated segmentation, tracking, and classification of all cell cycle phases. Combining the all-in-one reporter with labeled endogenous cyclin D1 and p21 as prime examples of cell-cycle-regulated fate determinants, we show how cell cycle and quantitative protein dynamics can be simultaneously extracted to gain insights into G1 phase regulation and responses to perturbations.

Keywords: G1 phase regulation; automated image analysis; cell cycle; cell cycle reporter; cell fate decisions; cyclin D1; cyclin oscillations; p21; quantitative single cell imaging; quiescence.

Graphical abstract

Figure 1

Dynamic Expression of Endogenous mRuby-PCNA (A) N-terminal targeting of endogenous PCNA with mRuby. (B) Cell cycle phase-dependent localization of endogenous mRuby-PCNA and histone 3.1-mTurquoise2. (C) Western blot analysis of a release from 24 hr serum starvation (SS), showing that untagged and tagged PCNA have similar expression kinetics; AS, asynchronously growing cells. Note that PCNA and mRuby-PCNA blots were imaged at different intensities to better illustrate the similar increase in PCNA expression. (D) Quantification of data shown in (C) represented as mean ± SEM from four independent experiments. (E) Single-cell tracks aligned to the beginning of S phase (t = 0 hr; see methodology), showing mRuby-PCNA levels during a complete cell cycle. (F) Single cell tracks as in (E), showing that the dynamic behavior of mRuby-PCNA is conserved in non-transformed and transformed human and murine cells. See also Figure S1.

Figure 2

Loss of mRuby-PCNA Is an Early Marker of Cell Cycle Exit and Quiescence (A) Images and quantification of asynchronously growing (AS) or 48 hr SS RPE-1 cells expressing endogenous mRuby-PCNA and histone 3.1-mTurqouise2. (B) Single-cell tracks showing the decline of mRuby-PCNA levels during 48 hr of serum starvation. (C) Western blot analysis of cells treated as in (A), showing the decrease of untagged and tagged PCNA in response to 48 hr of serum starvation. (D) Quantification of pRb780 positivity in cells treated as in (A) represented as mean ± SEM from two independent experiments with greater than five technical replicates. (E) Images showing the decrease of mRuby-PCNA in non-transformed human and murine cells, but not in HeLa cells, in response to contact inhibition. See also Figure S1.

Figure 3

Robust Cell Cycle Classification Based on mRuby-PCNA (A) Cell cycle phase-dependent localization of endogenous mRuby-PCNA, histone 3.1-mTurquoise2, and cyclin A2-mVenus in living RPE-1 cells. (B and C) Representative single cell track (B) and scatterplot (C), illustrating the correlated onset of mRuby-PCNA and cyclin A2-mVenus expression. Note that mRuby-PCNA precedes cyclin A2-mVenus on average by 45 min (insert) and is used to define the beginning of S phase (n = 591). See also Movie S2. (D) Distribution of mRuby-PCNA intensity before (dark red) and at the end (light red) of S phase. (E) The distribution width of mRuby-PCNA intensity is indicative of the S/G2 transition. (F) The maximum distribution width of histone 3.1-mTurquoise2 indicative of mitosis coincides with a drop in mRuby-PCNA intensity due to redistribution of mRuby-PCNA to the cytoplasm after nuclear envelope breakdown. (G) Difference in estimated time of G2/M transition based on histone and PCNA levels as illustrated in (F). (H) Representative single-cell track with classification of cell cycle phases. See also Figure S2.

Figure 4

mRuby-PCNA as an All-in-One Cell Cycle Reporter (A) Representative single-cell trajectories for comparison of segmentation and tracking on histone 3.1-mTurquoise2 (blue) or mRuby-PCNA (red) images. (B–D) Representative time courses and quantified differences between the two segmentation approaches in area (B), mRuby-PCNA (C), and cyclin A2-mVenus levels (D). Though segmented areas can differ, especially for low levels of PCNA during G1 (B), the time point of G1/S transition is estimated very precisely with no deviation of >0.5 hr (C) and cyclin A2-mVenus levels can be robustly quantified with <10% deviation for almost 90% of the time points with positive signal (D; n = 36 cells). See also Figure S2 and Movie S1.

Figure 5

Quantitative Analysis of Cyclin Oscillations and Response of p21, Cyclin D1, and PCNA to DNA Damage (A–C) Quantitative cyclin dynamics of cyclins A2 (A), B1 (B), and D1 (C) in the nucleus or cytoplasm during a complete cell cycle. Average curves represent the combined levels of tagged and untagged cyclins A2, B1, and D1 according to quantitative western blot analysis (Figures S4A and S4B) and quantitative imaging (Figures S4D and S4E). Bands around the average curves show 95% of the values. Exemplary single-cell time courses are shown in Figure S5 and Movies S2, S3, and S4. (D and E) Histograms illustrating when cyclin D1 levels start decreasing in the nucleus (D) and the slope of cyclin D1-mVenus intensity in the cytoplasm at this time (E). The mean slope of almost 0 is in agreement with the constant levels of cytoplasmic cyclin D1 observed from mitosis to mitosis; n = 567 cells. (F) Representative single-cell tracks showing distinct dynamics of p21-mTurquoise2, mRuby-PCNA, and cyclin D1-mVenus in response to 1 μM etoposide. (G) Cumulative behavior of >2,500 single living cells treated as in (F). See also Figures S3, S4, and S6.

Figure 6

Cyclin D1 Maintains G1 Phase and Prevents the Transition into Quiescence (A) Normalized proliferation of RPE-1 cells treated with the indicated esi-RNAs represented as mean ± SEM from three independent experiments. (B) Scatterplot showing maternal cyclin D1 levels before mitosis in relation to G1 phase length in daughter cells of cyclin D1-mVenus- (gray) and cyclin D1-CDK4-mVenus (green)-expressing cells. Note that the expression of constitutively active cyclin D1-CDK4-mVenus does not shorten G1 phase beyond a minimum time that is also supported by endogenous levels of cyclin D1. (C) Correlation between expression level and G1 length of daughter cells derived from the experiment shown in (B). (D) Scatterplot showing nucleoplasmic and cytoplasmic levels of DHB-Venus in control and cyclin D1-depleted cells. Note nuclear DHB-Venus indicates inactive CDK2, a hallmark of CDK2^low cells. (E) Scatterplot showing pRb and Ki67 staining versus mRuby-PCNA levels in cells treated with the indicated esi-RNAs for 48 hr. (F) Representative single-cell tracks of nucleoplasmic and cytoplasmic cyclin D1 levels grouped into two classes according to cyclin D1 dynamics during G1 phase. (G) G1 phase length and initial nuclear level of cyclin D1 after mitosis in cells belonging to class I and II as defined in (F). (H) Scatterplot showing the relation of G1 phase length and classification as defined in (F) in sister cells. (I) Scatterplot illustrating the amount of maternally inherited cyclin D1 in between sister cells. Gray and dark green dots represent sister cells as defined in (H). Note that the initial level of cyclin D1 in sister cells is highly correlated independently of their class.