Proteomics has proved invaluable in generating large-scale quantitative data; however, the development of systems approaches for examining the proteome in vivo has lagged behind. To evaluate protein abundance and localization on a proteome scale, we exploited the yeast GFP-fusion collection in a pipeline combining automated genetics, high-throughput microscopy, and computational feature analysis. We developed an ensemble of binary classifiers to generate localization data from single-cell measurements and constructed maps of ∼3,000 proteins connected to 16 localization classes. To survey proteome dynamics in response to different chemical and genetic stimuli, we measure proteome-wide abundance and localization and identified changes over time. We analyzed >20 million cells to identify dynamic proteins that redistribute among multiple localizations in hydroxyurea, rapamycin, and in an rpd3Δ background. Because our localization and abundance data are quantitative, they provide the opportunity for many types of comparative studies, single cell analyses, modeling, and prediction. VIDEO ABSTRACT.

In the Brassicaceae, compatible pollen-pistil interactions result in pollen adhesion to the stigma, while pollen grains from unrelated plant species are largely ignored. There can also be an additional layer of recognition to prevent self-fertilization, the self-incompatibility response, whereby self pollen grains are distinguished from nonself pollen grains and rejected. This pathway is activated in the stigma and involves the ARM repeat-containing 1 (ARC1) protein, an E3 ubiquitin ligase. In a screen for ARC1-interacting proteins, we have identified Brassica napus Exo70A1, a putative component of the exocyst complex that is known to regulate polarized secretion. We show through transgenic studies that loss of Exo70A1 in Brassica and Arabidopsis thaliana stigmas leads to the rejection of compatible pollen at the same stage as the self-incompatibility response. A red fluorescent protein:Exo70A1 fusion rescues this stigmatic defect in Arabidopsis and is found to be mobilized to the plasma membrane concomitant with flowers opening. By contrast, increased expression of Exo70A1 in self-incompatible Brassica partially overcomes the self pollen rejection response. Thus, our data show that the Exo70A1 protein functions at the intersection of two cellular pathways, where it is required in the stigma for the acceptance of compatible pollen in both Brassica and Arabidopsis and is negatively regulated by Brassica self-incompatibility.

Existing computational pipelines for quantitative analysis of high‐content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone‐arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open‐source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high‐content microscopy data.

In both academia and the pharmaceutical industry, large-scale assays for drug discovery are expensive and often impractical, particularly for the increasingly important physiologically relevant model systems that require primary cells, organoids, whole organisms, or expensive or rare reagents. We hypothesized that data from a single high-throughput imaging assay can be repurposed to predict the biological activity of compounds in other assays, even those targeting alternate pathways or biological processes. Indeed, quantitative information extracted from a three-channel microscopy-based screen for glucocorticoid receptor translocation was able to predict assay-specific biological activity in two ongoing drug discovery projects. In these projects, repurposing increased hit rates by 50- to 250-fold over that of the initial project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from high-content screens are a rich source of information that can be used to predict and replace customized biological assays.

Two-dimensional (2D) cell cultures growing on plastic do not recapitulate the three dimensional (3D) architecture and complexity of human tumors. More representative models are required for drug discovery and validation. Here, 2D culture and 3D mono- and stromal co-culture models of increasing complexity have been established and cross-comparisons made using three standard cell carcinoma lines: MCF7, LNCaP, NCI-H1437. Fluorescence-based growth curves, 3D image analysis, immunohistochemistry and treatment responses showed that end points differed according to cell type, stromal co-culture and culture format. The adaptable methodologies described here should guide the choice of appropriate simple and complex in vitro models.