Scratching is a main behavioral response accompanied by acute and chronic itch conditions, and has been quantified as an objective correlate to assess itch in studies using laboratory animals. Scratching has been counted mostly by human annotators, which is a time-consuming and laborious process. It has been attempted to develop automated scoring methods using various strategies, but they often require specialized equipment, costly software, or implantation of device which may disturb animal behaviors. To complement limitations of those methods, we have adapted machine learning-based strategy to develop a novel automated and real-time method detecting mouse scratching from experimental movies captured using monochrome cameras such as a webcam. Scratching is identified by characteristic changes in pixels, body position, and body size by frame as well as the size of body. To build a training model, a novel two-step J48 decision tree-inducing algorithm along with a C4.5 post-pruning algorithm was applied to three 30-min video recordings in which a mouse exhibits scratching following an intradermal injection of a pruritogen, and the resultant frames were then used for the next round of training. The trained method exhibited, on average, a sensitivity and specificity of 95.19% and 92.96%, respectively, in a performance test with five new recordings. This result suggests that it can be used as a non-invasive, automated and objective tool to measure mouse scratching from video recordings captured in general experimental settings, permitting rapid and accurate analysis of scratching for preclinical studies and high throughput drug screening.
Animals ; Animals, Laboratory ; Behavior, Animal ; Body Size ; Complement System Proteins ; Decision Trees ; Drug Evaluation, Preclinical ; Humans ; Injections, Intradermal ; Machine Learning ; Methods ; Mice ; Motion Pictures as Topic ; Pruritus ; Research Design ; Sensitivity and Specificity ; Video Recording

Interferons (IFNs) have been known as antiviral genes and they are classified by type 1, type 2, and type 3 IFN. The type 1 IFN consists of IFNα, IFNβ, IFNτ, and IFNω whereas the type 2 IFN consists of only IFNγ, which is a key cytokine driving T helper cell type 1 immunity. IFNλ belongs to the type 3 IFN, which is also known as IL-28 and IL-29 possessing antiviral activities. Type 1 IFN is produced by viral infection whereas type 2 IFN is induced by mitogenic or antigenic T-cell stimuli. The IFNτ of bovine was first discovered in an ungulate ruminant recognition hormone. IFNτ belongs to the type 1 IFN with the common feature of type 1 IFN such as antiviral activity. IFNs have been mostly studied for basic research and clinical usages therefore there was no effort to investigate IFNs in industrial animals. Here we cloned porcine IFNα8 from peripheral blood mononuclear cells of Korean domestic pig (Sus scrofa domestica). The newly cloned IFNα8 amino acid sequence from Korean domestic pig shares 98.4% identity with the known porcine IFNα8 in databank. The recombinant porcine IFNα8 showed potent antiviral activity and protected bovine Madin-Darby bovine kidney epithelial (MDBK) cells from the cytopathic effect of vesicular stomatitis virus, but it failed to protect human Wistar Institute Susan Hayflick (WISH) cells and canine Madin-Darby canine kidney epithelial-like (MDCK) cells. The present study demonstrates species specific antiviral activity of porcine IFNα8.
Amino Acid Sequence ; Animals ; Clone Cells ; Humans ; Interferons ; Kidney ; Ruminants ; Sus scrofa ; T-Lymphocytes ; T-Lymphocytes, Helper-Inducer ; Vesicular Stomatitis