Studying naturalistic animal behavior remains a difficult objective. Recent machine learning advances have enabled limb localization; however, extracting behaviors requires ascertaining the spatiotemporal patterns of these positions. To provide a link from poses to actions and their kinematics, we developed B-SOiD - an open-source, unsupervised algorithm that identifies behavior without user bias. By training a machine classifier on pose pattern statistics clustered using new methods, our approach achieves greatly improved processing speed and the ability to generalize across subjects or labs. Using a frameshift alignment paradigm, B-SOiD overcomes previous temporal resolution barriers. Using only a single, off-the-shelf camera, B-SOiD provides categories of sub-action for trained behaviors and kinematic measures of individual limb trajectories in any animal model. These behavioral and kinematic measures are difficult but critical to obtain, particularly in the study of rodent and other models of pain, OCD, and movement disorders.

The excitatory glutamatergic synapse is the principal site of communication between cortical pyramidal neurons and their targets, a key locus of action of many drugs, and highly vulnerable to dysfunction and loss in neurodegenerative disease. A detailed knowledge of the structure of these synapses in distinct cortical areas and across species is a prerequisite for understanding the anatomical underpinnings of cortical specialization and, potentially, selective vulnerability in neurological disorders. We used serial electron microscopy to assess the ultrastructural features of excitatory (asymmetric) synapses in the layers 2-3 (L2-3) neuropil of visual (V1) and frontal (FC) cortices of the adult mouse and compared findings to those in the rhesus monkey (V1 and lateral prefrontal cortex [LPFC]). Analyses of multiple ultrastructural variables revealed four organizational features. First, the density of asymmetric synapses does not differ between frontal and visual cortices in either species, but is significantly higher in mouse than in monkey. Second, the structural properties of asymmetric synapses in mouse V1 and FC are nearly identical, by stark contrast to the significant differences seen between monkey V1 and LPFC. Third, while the structural features of postsynaptic entities in mouse and monkey V1 do not differ, the size of presynaptic boutons are significantly larger in monkey V1. Fourth, both presynaptic and postsynaptic entities are significantly smaller in the mouse FC than in the monkey LPFC. The diversity of synaptic ultrastructural features demonstrated here have broad implications for the nature and efficacy of glutamatergic signaling in distinct cortical areas within and across species.

The motivation, control, and selection of actions comprising naturalistic behaviors remains a tantalizing but difficult field of study. Detailed and unbiased quantification is critical. Interpreting the positions of animals and their limbs can be useful in studying behavior, and significant recent advances have made this step straightforward (1, 2). However, body position alone does not provide a grasp of the dynamic range of naturalistic behaviors. Behavioral Segmentation of Open-field In DeepLabCut, or B-SOiD ("B-side"), is an unsupervised learning algorithm that serves to discover and classify behaviors that are not pre-defined by users. Our algorithm segregates statistically different, sub-second rodent behaviors with a single bottom-up perspective video camera. Upon DeepLabCut estimating the positions of 6 body parts (snout, the 4 paws, and the base of the tail), our software performs novel expectation maximization fitting of Gaussian mixture models on t-Distributed Stochastic Neighbor Embedding (t-SNE). The original features taken from dimensionally-reduced classes are then used build a multi-class support vector machine classifier that can decode millions of actions within seconds. We demonstrate that the highly reproducible, independently-classified behaviors can be used to extract kinematic parameters of individual actions as well as broader action sequences. This open-source platform enables the efficient study of the neural mechanisms of spontaneous behavior as well as the performance of disease-related behaviors that have been difficult to quantify, such as grooming and stride-length in Obsessive-Compulsive Disorder (OCD) and stroke research. Behavioral Analysis | Open-field | DeepLabCut | Unsupervised LearningCorrespondence: eyttri@andrew.cmu.edu

Behavior identification and quantification techniques have undergone rapid development. To this end, supervised or unsupervised methods are chosen based pon their intrinsic strengths and weaknesses (e.g. user bias, training cost, complexity, action discovery). Here, a new active learning platform, A-SOiD, blends these strengths and in doing so, overcomes several of their inherent drawbacks. A-SOiD iteratively learns user-defined groups with a fraction of the usual training data while attaining expansive classification through directed unsupervised classification. In socially-interacting mice, A-SOiD outperformed standard methods despite requiring 85% less training data. Additionally, it isolated two additional ethologically-distinct mouse interactions via unsupervised classification. Similar performance and efficiency was observed using non-human primate 3D pose data. In both cases, the transparency in A-SOiD's cluster definitions revealed the defining features of the supervised classification through a game-theoretic approach. To facilitate use, A-SOiD comes as an intuitive, open-source interface for efficient segmentation of user-defined behaviors and discovered subactions.

Behavior identification and quantification techniques have undergone rapid development. To this end, supervised or unsupervised methods are chosen based upon their intrinsic strengths and weaknesses (e.g. user bias, training cost, complexity, action discovery). Here, a new active learning platform, A-SOiD, blends these strengths and in doing so, overcomes several of their inherent drawbacks. A-SOiD iteratively learns user-defined groups with a fraction of the usual training data while attaining expansive classification through directed unsupervised classification. In socially-interacting mice, A-SOiD outperformed standard methods despite requiring 85$\%$ less training data. Additionally, it isolated two additional ethologically-distinct mouse interactions via unsupervised classification. Similar performance and efficiency was observed using non-human primate 3D pose data. In both cases, the transparency in A-SOiD’s cluster definitions revealed the defining features of the supervised classification through a game-theoretic approach. To facilitate use, A-SOiD comes as an intuitive, open-source interface for efficient segmentation of user-defined behaviors and discovered subactions.