High-throughput microscopy has outpaced analysis; biomarker-optimized CNNs are a generalizable, fast, and interpretable solution.

Huntington’s Disease (HD) is a neurodegenerative disorder caused by an expansion in a CAG-tri-nucleotide repeat that introduces a poly-glutamine stretch into the huntingtin protein (mHTT). Mutant huntingtin (mHTT) has been associated with several phenotypes including mood disorders and depression. Additionally, HD patients are known to be more susceptible to type II diabetes mellitus (T2DM), and HD mice model develops diabetes. However, the mechanism and pathways that link Huntington’s disease and diabetes have not been well established. Understanding the underlying mechanisms can reveal potential targets for drug development in HD. In this study, we investigated the transcriptome of mHTT cell populations alongside intracellular glucose measurements using a functionalized nanopipette. Several genes related to glucose uptake and glucose homeostasis are affected. We observed changes in intracellular glucose concentrations and identified altered transcript levels of certain genes including Sorcs1, Hh-II and Vldlr. Our data suggest that these can be used as markers for HD progression. Sorcs1 may not only have a role in glucose metabolism and trafficking but also in glutamatergic pathways affecting trafficking of synaptic components.

The condition of having a healthy, functional proteome is known as protein homeostasis, or proteostasis. Establishing and maintaining proteostasis is the province of the proteostasis network, approximately 2,700 components that regulate protein synthesis, folding, localization, and degradation. The proteostasis network is a fundamental entity in biology that is essential for cellular health and has direct relevance to many diseases of protein conformation. However, it is not well defined or annotated, which hinders its functional characterization in health and disease. In this series of manuscripts, we aim to operationally define the human proteostasis network by providing a comprehensive, annotated list of its components. We provided in a previous manuscript a list of chaperones and folding enzymes as well as the components that make up the machineries for protein synthesis, protein trafficking into and out of organelles, and organelle-specific degradation pathways. Here, we provide a curated list of 838 unique high-confidence components of the autophagy-lysosome pathway, one of the two major protein degradation systems in human cells.

Cell death is an essential process in biology that must be accounted for in live microscopy experiments. Nevertheless, cell death is difficult to detect without perturbing experiments with stains, dyes or biosensors that can bias experimental outcomes, lead to inconsistent results, and reduce the number of processes that can be simultaneously labelled. These additional steps also make live microscopy difficult to scale for high-throughput screening because of the cost, labor, and analysis they entail. We address this fundamental limitation of live microscopy with biomarker-optimized convolutional neural networks (BO-CNN): computer vision models trained with a ground truth biosensor that detect live cells with superhuman, 96% accuracy more than 100 times faster than previous methods. Our models learn to identify important morphological characteristics associated with cell vitality without human input or additional perturbations, and to generalize to other imaging modalities and cell types for which they have no specialized training. We demonstrate that we can interpret decisions from BO-CNN models to gain biological insight into the patterns they use to achieve superhuman accuracy. The BO-CNN approach is broadly useful for live microscopy, and affords a powerful new paradigm for advancing the state of high-throughput imaging in a variety of contexts.

Changes to neuronal morphology and loss of neurites and synaptic connections can be an important early indicator of neurological diseases, and a pathognomonic sign of neurodevelopmental disorders. These changes are typically detectable by microscopy in cell culture or histological samples, but quantification can be challenging. The neurites extending from cell soma can be quite thin, dim, overlapping and complex, making them laborious to trace manually and difficult to annotate and quantify computationally or automatically. Moreover, the tools available to aid this aim are limited in their capacity to generalize to high throughput image acquisition such as time-lapse or longitudinal imaging, where imaging conditions can change dramatically over the course of the experiment. In order to facilitate neurite quantification, we developed a deep learning (DL) neurite annotation prediction algorithm (NAPA) to predict the structure and length of neurites. NAPA overcomes experimental variation inherent to fluorescence imaging by learning more broader features that are important for neurite recognition. Based on a dataset with partial annotation, NAPA generated predictions on several unannotated datasets, and was able to capture differences between disease and control conditions. We also defined a sequence of steps to generate custom models with a small number of annotation inputs, and extended the predictions to a 3D tissue sample and longitudinal imaging. With this algorithm we developed an approach to quantify neurites with an accuracy that nears and sometimes exceeds human curation, in 1/100th of the time. This approach makes accurate analysis of large or longitudinal datasets feasible across a broad range of datasets.