Lee, T. J. | bioRxiv Science

bioRxiv2020

SARM1 depletion rescues NMNAT1 dependent photoreceptor cell death and retinal degeneration.

Leber congenital amaurosis type 9 is an autosomal recessive retinopathy caused by mutations of the NAD+ synthesis enzyme NMNAT1. Despite the ubiquitous expression of NMNAT1, patients do not manifest pathologies other than retinal degeneration. Here we demonstrate that widespread NMNAT1 depletion in adult mice mirrors the human pathology, with selective loss of photoreceptors highlighting the exquisite vulnerability of these cells to NMNAT1 loss. Conditional deletion demonstrates that NMNAT1 is required within the photoreceptor. Mechanistically, loss of NMNAT1 activates the NADase SARM1, the central executioner of axon degeneration, to trigger photoreceptor death and vision loss. Hence, the essential function of NMNAT1 in photoreceptors is to inhibit SARM1, highlighting an unexpected shared mechanism between axonal degeneration and photoreceptor neurodegeneration. These results define a novel SARM1-dependent photoreceptor cell death pathway and identifies SARM1 as a therapeutic candidate for retinopathies.

neuroscience↗

bioRxiv2019

ShinyLearner: A containerized benchmarking tool for machine-learning classification of tabular data

Classification algorithms assign observations to groups based on patterns in data. The machine-learning community have developed myriad classification algorithms, which are employed in diverse life-science research domains. When applying such algorithms, researchers face the challenge of deciding which algorithm(s) to apply in a given research domain. Algorithm choice can affect classification accuracy dramatically, so it is crucial that researchers optimize these choices based on empirical evidence rather than hearsay or anecdotal experience. In benchmark studies, multiple algorithms are applied to multiple datasets, and the researcher examines overall trends. In addition, the researcher may evaluate multiple hyperparameter combinations for each algorithm and use feature selection to reduce data dimensionality. Although software implementations of classification algorithms are widely available, robust benchmark comparisons are difficult to perform when researchers wish to compare algorithms that span multiple software packages.\n\nProgramming interfaces, data formats, and evaluation procedures differ across software packages; and dependency conflicts may arise during installation. To address these challenges, we created ShinyLearner, an open-source project for integrating machine-learning packages into software containers. ShinyLearner provides a uniform interface for performing classification, irrespective of the library that implements each algorithm, thus facilitating benchmark comparisons. In addition, ShinyLearner enables researchers to optimize hyperparameters and select features via nested cross validation; it tracks all nested operations and generates output files that make these steps transparent. ShinyLearner includes a Web interface to help users more easily construct the commands necessary to perform benchmark comparisons. ShinyLearner is freely available at https://github.com/srp33/ShinyLearner.

bioinformatics↗