DNA damage reduces heterogeneity and coherence of chromatin motions.

Chromatin motions depend on and may regulate genome functions, in particular the DNA damage response. In yeast, DNA double-strand breaks (DSBs) globally increase chromatin diffusion, whereas in higher eukaryotes the impact of DSBs on chromatin dynamics is more nuanced. We mapped the motions of chromatin microdomains in mammalian cells using diffractive optics and photoactivatable chromatin probes and found a high level of spatial heterogeneity. DNA damage reduces heterogeneity and imposes spatially defined shifts in motions: Distal to DNA breaks, chromatin motions are globally reduced, whereas chromatin retains higher mobility at break sites. These effects are driven by context-dependent changes in chromatin compaction. Photoactivated lattices of chromatin microdomains are ideal to quantify microscale coupling of chromatin motion. We measured correlation distances up to 2 µm in the cell nucleus, spanning chromosome territories, and speculate that this correlation distance between chromatin microdomains corresponds to the physical separation of A and B compartments identified in chromosome conformation capture experiments. After DNA damage, chromatin motions become less correlated, a phenomenon driven by phase separation at DSBs. Our data indicate tight spatial control of chromatin motions after genomic insults, which may facilitate repair at the break sites and prevent deleterious contacts of DSBs, thereby reducing the risk of genomic rearrangements.

Performance of deep learning restoration methods for the extraction of particle dynamics in noisy microscopy image sequences.

Particle tracking in living systems requires low light exposure and short exposure times to avoid phototoxicity and photobleaching and to fully capture particle motion with high-speed imaging. Low-excitation light comes at the expense of tracking accuracy. Image restoration methods based on deep learning dramatically improve the signal-to-noise ratio in low-exposure data sets, qualitatively improving the images. However, it is not clear whether images generated by these methods yield accurate quantitative measurements such as diffusion parameters in (single) particle tracking experiments. Here, we evaluate the performance of two popular deep learning denoising software packages for particle tracking, using synthetic data sets and movies of diffusing chromatin as biological examples. With synthetic data, both supervised and unsupervised deep learning restored particle motions with high accuracy in two-dimensional data sets, whereas artifacts were introduced by the denoisers in three-dimensional data sets. Experimentally, we found that, while both supervised and unsupervised approaches improved tracking results compared with the original noisy images, supervised learning generally outperformed the unsupervised approach. We find that nicer-looking image sequences are not synonymous with more precise tracking results and highlight that deep learning algorithms can produce deceiving artifacts with extremely noisy images. Finally, we address the challenge of selecting parameters to train convolutional neural networks by implementing a frugal Bayesian optimizer that rapidly explores multidimensional parameter spaces, identifying networks yielding optimal particle tracking accuracy. Our study provides quantitative outcome measures of image restoration using deep learning. We anticipate broad application of this approach to critically evaluate artificial intelligence solutions for quantitative microscopy.