SVEP1 plays a crucial role in epidermal differentiation.

SVEP1 is a recently identified multidomain cell adhesion protein, homologous to the mouse polydom protein, which has been shown to mediate cell-cell adhesion in an integrin-dependent manner in osteogenic cells. In this study, we characterized SVEP1 function in the epidermis. SVEP1 was found by qRT-PCR to be ubiquitously expressed in human tissues, including the skin. Confocal microscopy revealed that SVEP1 is normally mostly expressed in the cytoplasm of basal and suprabasal epidermal cells. Downregulation of SVEP1 expression in primary keratinocytes resulted in decreased expression of major epidermal differentiation markers. Similarly, SVEP1 downregulation was associated with disturbed differentiation and marked epidermal acanthosis in three-dimensional skin equivalents. In contrast, the dispase assay failed to demonstrate significant differences in adhesion between keratinocytes expressing normal vs low levels of SVEP1. Homozygous Svep1 knockout mice were embryonic lethal. Thus, to assess the importance of SVEP1 for normal skin homoeostasis in vivo, we downregulated SVEP1 in zebrafish embryos with a Svep1-specific splice morpholino. Scanning electron microscopy revealed a rugged epidermis with perturbed microridge formation in the centre of the keratinocytes of morphant larvae. Transmission electron microscopy analysis demonstrated abnormal epidermal cell-cell adhesion with disadhesion between cells in Svep1-deficient morphant larvae compared to controls. In summary, our results indicate that SVEP1 plays a critical role during epidermal differentiation.

Robust mouse tracking in complex environments using neural networks.

The ability to track animals accurately is critical for behavioral experiments. For video-based assays, this is often accomplished by manipulating environmental conditions to increase contrast between the animal and the background in order to achieve proper foreground/background detection (segmentation). Modifying environmental conditions for experimental scalability opposes ethological relevance. The biobehavioral research community needs methods to monitor behaviors over long periods of time, under dynamic environmental conditions, and in animals that are genetically and behaviorally heterogeneous. To address this need, we applied a state-of-the-art neural network-based tracker for single mice. We compare three different neural network architectures across visually diverse mice and different environmental conditions. We find that an encoder-decoder segmentation neural network achieves high accuracy and speed with minimal training data. Furthermore, we provide a labeling interface, labeled training data, tuned hyperparameters, and a pretrained network for the behavior and neuroscience communities.