Deep-learning microscopy image reconstruction with quality control reveals second-scale rearrangements in RNA polymerase II clusters

Abstract

Fluorescence microscopy, a central tool of biological research, is subject to inherent trade-offs in experiment design. For instance, image acquisition speed can only be increased in exchange for a lowered signal quality, or for an increased rate of photo-damage to the specimen. Computational denoising can recover some loss of signal, extending the trade-off margin for high-speed imaging. Recently proposed denoising on the basis of neural networks shows exceptional performance but raises concerns of errors typical of neural networks. Here, we present a work-flow that supports an empirically optimized reduction of exposure times, as well as per-image quality control to exclude images with reconstruction errors. We implement this work-flow on the basis of the denoising tool Noise2Void and assess the molecular state and 3D shape of RNA polymerase II (Pol II) clusters in live zebrafish embryos. Image acquisition speed could be tripled, achieving 2-s time resolution and 350-nm lateral image resolution. The obtained data reveal stereotyped events of approximately 10 s duration: initially, the molecular mark for recruited Pol II increases, then the mark for active Pol II increases, and finally Pol II clusters take on a stretched and unfolded shape. An independent analysis based on fixed sample images reproduces this sequence of events, and suggests that they are related to the transient association of genes with Pol II clusters. Our work-flow consists of procedures that can be implemented on commercial fluorescence microscopes without any hardware or software modification, and should, therefore, be transferable to many other applications.

Keywords: fluorescence microscopy; gene regulation; image processing; reliable deep learning; transcription.

Fig. 1.

Metrics for the reliability and effective resolution in n2v-reconstructed images. (A) Representative micrographs of the DNA distribution in a nucleus in a fixed zebrafish embryo, recorded with a stimulated emission depletion (STED) super-resolution microscope. The same image plane was recorded twice at low quality, once at high quality, and two n2v-reconstructed images were prepared from the low-quality images. (B) SSIM values for pair-wise comparison (image 1 vs. image 2) and comparison against the high-quality image (image 1 vs. high-quality and image 2 vs. high-quality) for the low-quality images and the reconstructed images. (C) FRC curves calculated based on a low-quality image pair and the corresponding reconstructed image pair. (D) FRC-based effective resolution for four pairs of low-quality images and the corresponding pairs of reconstructed images.

Fig. 2.

Metric-based estimation of how far image quality can be compromised while still allowing recovery of effective resolution by denoising. (A) Representative micrographs of nuclei of human cheek cells for different camera exposure times (t_exp, as indicated), all high-quality images were acquired at the same position but with an exposure time of 200 ms. Images are maximum-intensity projections, DNA was labeled by Hoechst 33342. (B) FRC curves calculated from a pair of matched low-quality images, from a pair of reconstructed images, and a pair of high-quality images for the different t_exp. (C) Effective resolution for the indicated t_exp, n = 5 nuclei per t_exp, values are shown with mean.

Fig. 3.

A two-phase acquisition protocol to combine acquisition of quality control images with high-speed time-lapse imaging. (A) Image data were acquired at multiple positions in a sample, thus obtaining multiple viewpoints containing several objects of interest (nuclei, indicated as circles). (B) For each position, a sequence of two acquisition phases is carried out. In phase A, for each z position, a low-quality image, two high-quality reference images, and two low-quality test images are recorded. Low-quality images are recorded at a shortened exposure time (t_exp), high-quality images at a reference exposure time resulting in images of the desired quality (t_ref). Acquisition phase A obtains the images required for n2v model training as well as the assessment of effective image resolution and reconstruction errors. In phase B, only single low-quality images are recorded with the shortened exposure time (t_exp), resulting in an increased rate of acquisition compared to acquisition with full exposure time (t_ref). Acquisition phase B obtains only low-quality images, which are reconstructed after the experiment is completed.

Fig. 4.

n2v-accelerated imaging reveals coordinated changes in shape and phosphorylation levels of Pol II clusters on the scale of seconds. (A) Representative series of time-lapse images showing a single Pol II cluster in the Pol II Ser5P channel (single image plane from the middle z position of the cluster, exposure time , effective time resolution for full 3D volume acquisition of ). The Pol II Ser2P channel is not shown because only average intensity, not shape was quantified from this channel. (B) Example shapes to illustrate how elongation and solidity represent object shape. (C) Time courses of Pol II Ser5P intensity, Pol II Ser2P intensity, elongation, and solidity for the example time-lapse shown in panel A. (D) Cross-correlation analysis of the temporal coordination of Pol II Ser5P intensity, Pol II Ser2P intensity, and solidity with elongation. Gray lines indicate the time-shifted correlation for single cluster time courses, thick lines indicate the mean, and the gray region the 95% bootstrap CI. Analysis based on n = 30 tracked clusters, recorded from one sphere stage embryo. (E) Summary of the coordinated changes in phosphorylation and cluster shape suggested by the cross-correlation analysis. A stereotypical sequence of events can be seen: cluster Pol II Ser5P intensity transiently increases (red) and the cluster becomes rounder, then cluster Pol II Ser2P transiently intensity increases (blue), until finally the cluster transiently unfolds and becomes elongated.

Fig. 5.

Pseudo-time analysis of data from fixed embryos relates transient engagement and activation of a gene to the phosphorylation and shape changes observed in live embryos. (A) Example images of Pol II Ser5P (magenta signal) clusters sorted by a pseudo-time progress coordinate (s, periodic, defined on the interval [0,1)), which is calculated based on interaction with the gene klf2b (green represents oligopaint fluorescence in situ hybridization signal for klf2b). Center positions (weighted centroid) are indicated for the Pol II Ser5P cluster (white circle with black filling) and the gene (black circle with white filling) and connected with a white line for illustration. For details of the reconstruction, see Figure S8 (Supplementary Material). For an overview containing all eight genes that were assessed, see Fig. S9B (Supplementary Material). (B) Pol II Ser5P and Ser2P intensity, elongation, and solidity of Pol II Ser5P clusters sorted by pseudo-time s. A total of n = 186 clusters from N = 4 independent samples, obtained in two independent experiments, were included in the analysis. (C) Cross-correlation analyses for different register shifts in the coordinate s, the register shift is in units of data points by which the coordinate s was shifted. Gray regions indicate 95% bootstrap CI.

Fig. 6.

Work-flow for n2v reconstruction for time-lapse data with quality control.