Systematic exploration of unsupervised methods for mapping behavior

Abstract

To fully understand the mechanisms giving rise to behavior, we need to be able to precisely measure it. When coupled with large behavioral data sets, unsupervised clustering methods offer the potential of unbiased mapping of behavioral spaces. However, unsupervised techniques to map behavioral spaces are in their infancy, and there have been few systematic considerations of all the methodological options. We compared the performance of seven distinct mapping methods in clustering a wavelettransformed data set consisting of the x-and y-positions of the six legs of individual flies. Legs were automatically tracked by small pieces of fluorescent dye, while the fly was tethered and walking on an air-suspended ball. We find that there is considerable variation in the performance of these mapping methods, and that better performance is attained when clustering is done in higher dimensional spaces (which are otherwise less preferable because they are hard to visualize). High dimensionality means that some algorithms, including the non-parametric watershed cluster assignment algorithm, cannot be used. We developed an alternative watershed algorithm which can be used in high-dimensional spaces when a probability density estimate can be computed directly. With these tools in hand, we examined the behavioral space of fly leg postural dynamics and locomotion. We find a striking division of behavior into modes involving the fore legs and modes involving the hind legs, with few direct transitions between them. By computing behavioral clusters using the data from all flies simultaneously, we show that this division appears to be common to all flies. We also identify individual-to-individual differences in behavior and behavioral transitions. Lastly, we suggest a computational pipeline that can achieve satisfactory levels of performance without the taxing computational demands of a systematic combinatorial approach.

Mouse Academy: high-throughput automated training and trial-by-trial behavioral analysis during learning

“…We also projected the trajectories into 2 dimensions using a non-linear embedding method, t-distributed stochastic neighbor embedding 29,30 (t-SNE). Unlike PCA, this graph prioritizes the preservation of local structures within the data instead of the global structure 30 . In the t-SNE space the trajectories formed clear clusters ( Fig.…”

“…The behavioral trajectories can reveal intricate aspects of the animal’s decision process that are hidden from a mere record of the binary choices. The large data volume again calls for automated analysis, and both supervised machine learning methods 28,38,39 and unsupervised classification 28–30,40 have been employed for this purpose. Unsupervised analysis is not constrained by class labels, and can identify hidden structure in the data in an unbiased manner.…”

“…We performed a non-linear embedding method, t-distributed stochastic neighbor embedding (t-SNE) analysis as previously described 29,30 . Briefly, the trajectory data of each trial were projected into a 2D t-SNE space.…”

MAPLE: a Modular Automated Platform for Large-scale Experiments, a low-cost robot for integrated animal-handling and phenotyping

“…Even the venerable forward genetic screen could be automated. Unsupervised learning algorithms have been used to automatically phenotype flies (Berman et al 2014;Todd et al, 2017), and with the capacity to store and access large numbers of flies individually, MAPLE could identify and isolate outliers within a population without human intervention. We believe MAPLE is compatible with all such modern, automated approaches to fly experimentation, and brings automated animalhandling one step closer to the revolutionary potential achieved by liquid-handling robots.…”

anTraX: high throughput video tracking of color-tagged insects

“…Consequently, the behavioral and neural sciences have moved to study more complex forms of behavior at ever-increasing resolution. This has created a growing demand for methods to measure and quantify behavior, which has been met with a wide range of tools to measure, track and analyze behavior across a variety of species, conditions, and spatiotemporal scales [1][2][3][4][5][6][7][8]. One of the exciting frontiers of the field is the study of collective behavior in group-living organisms, and particularly the behavior of groups of insects.…”