Analysis of operant self-administration behaviors with supervised machine learning: Protocol for video acquisition and pose estimation analysis using DeepLabCut and Simple Behavioral Analysis (SimBA).

Abstract

The use of supervised machine learning to approximate poses in video recordings allows for rapid and efficient analysis of complex behavioral profiles. Currently, there are limited protocols for automated analysis of operant self-administration behavior. We provide methodology to 1) obtain videos of training sessions via Raspberry Pi microcomputers or GoPros 2) obtain pose estimation data using the supervised machine learning software packages DeepLabCut (DLC) and Simple Behavioral Analysis (SimBA) with local high performance computer cluster, 3) comparison of standard MedPC lever response vs quadrant time data generated from pose estimation regions of interest and 4) generation of predictive behavioral classifiers. Overall, we demonstrate proof-of-concept to use pose estimation outputs from DLC to both generate quadrant time results and obtain behavioral classifiers from SimBA during operant training phases.Significance Statement Substance use disorders are comprised of complex behaviors that promote chronic relapse to drug-seeking and -taking. Rodent operant self-administration is commonly used as a preclinical tool to examine drug-taking, -seeking and craving behavior. We provide protocols to acquire videos of self-administration behavior and obtain pose estimation outputs and unique behavioral classifiers using the supervised learning softwares DeepLabCut and Simple Behavioral Analysis (SimBA).