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.     

Validation of an Optimized ELISA for Quantitative Assessment of Epstein-Barr Virus Antibodies from Dried Blood Spots

Our objective was to validate a commercially available ELISA to measure antibody titers against Epstein-Barr virus (EBV) in dried blood spots (DBS) to replace a previously validated assay for DBS that is no longer available. We evaluated the precision, reliability, and stability of the assay for the measurement of EBV antibodies in matched plasma, fingerprick DBS, and venous blood DBS samples from 208 individuals. Effects of hematocrit and DBS sample matrix on EBV antibody determination were also investigated, and the cutoff for seropositivity in DBS was determined. A conversion equation was derived to enable comparison of results generated using this method with the former DBS method. There was a high correlation between plasma and DBS EBV antibody titers (R² = 0.93) with very little bias (?0.07 based on Bland-Altman analysis). The assay showed good linearity and did not appear to be affected by the DBS matrix, and physiological hematocrit levels had no effect on assay performance. There was reasonable agreement between DBS EBV titer estimates obtained using this assay and the previously validated assay (R² = 0.72). The commercially available ELISA assay for EBV antibody titers that we validated for use with DBS will facilitate continued investigation of EBV antibody titers in DBS.     

Prion Protein Paralog Doppel Protein Interacts with Alpha-2-Macroglobulin: A Plausible Mechanism for Doppel-Mediated Neurodegeneration

Doppel protein (Dpl) is a paralog of the cellular form of the prion protein (PrP^C), together sharing common structural and biochemical properties. Unlike PrP^C, which is abundantly expressed throughout the central nervous system (CNS), Dpl protein expression is not detectable in the CNS. Interestingly, its ectopic expression in the brain elicits neurodegeneration in transgenic mice. Here, by combining native isoelectric focusing plus non-denaturing polyacrylamide gel electrophoresis and mass spectrometry analysis, we identified two Dpl binding partners: rat alpha-1-inhibitor-3 (α₁I₃) and, by sequence homology, alpha-2-macroglobulin (α₂M), two known plasma metalloproteinase inhibitors. Biochemical investigations excluded the direct interaction of PrP^C with either α₁I₃ or α₂M. Nevertheless, enzyme-linked immunosorbent assays and surface plasmon resonance experiments revealed a high affinity binding occurring between PrP^C and Dpl. In light of these findings, we suggest a mechanism for Dpl-induced neurodegeneration in mice expressing Dpl ectopically in the brain, linked to a withdrawal of natural inhibitors of metalloproteinase such as α₂M. Interestingly, α₂M has been proven to be a susceptibility factor in Alzheimer''s disease, and as our findings imply, it may also play a relevant role in other neurodegenerative disorders, including prion diseases.     

Combining life extension treatments: A proposal for high-throughput testing in rodents

An experimental design is proposed for high-throughput testing of combined interventions that might increase life expectancy in rodents. There is a growing backlog of promising treatments that have never been tested in mammals, and known treatments have not been tested in combination. The dose-response curve is often nonlinear, as are the interactions among different therapies. Herein are proposed two experimental designs optimized for detecting high-value combinations. In Part I, numerical simulation is used to explore a protocol for testing different dosages of a single intervention. With reasonable and general biological assumptions about the dose-response curve, information is maximized when each animal receives a different dosage. In Part II, numerical simulation is used to explore a protocol for testing interactions among many combinations of treatments, once their individual dosages have been established. Combinations of three are identified as a sweet spot for statistics. To conserve resources, the protocol is designed to identify those outliers that lead to life extension greater than 50%, but not to offer detailed survival curves for any treatments. Every combination of three treatments from a universe of 15 total treatments is represented, with just three mice replicating each combination. Stepwise regression is used to infer information about the effects of individual treatments and all their pairwise interactions. Results are not quite as robust as for the dosage protocol in Part I, but if there is a combination that extends lifespan by more than 50%, it will be detected with 80% certainty. These two screening protocols offer the possibility of expediting the identification of treatment combinations that are most likely to have the largest effect, while controlling costs overall.