SaLSa: a combinatory approach of semi-automatic labeling and long short-term memory to classify behavioral syllables

Accurately and quantitatively describing mouse behavior is an important area. Although advances in machine learning have made it possible to track their behaviors accurately, reliable classification of behavioral sequences or syllables remains a challenge. In this study, we present a novel machine learning approach, called SaLSa (a combination of semi-automatic labeling and long short-term memory-based classification), to classify behavioral syllables of mice exploring an open field. This approach consists of two major steps: first, after tracking multiple body parts, spatial and temporal features of their egocentric coordinates are extracted. A fully automated unsupervised process identifies candidates for behavioral syllables, followed by manual labeling of behavioral syllables using a graphical user interface. Second, a long short-term memory (LSTM) classifier is trained with the labeled data. We found that the classification performance was marked over 97%. It provides a performance equivalent to a state-of-the-art model while classifying some of the syllables. We applied this approach to examine how hyperactivity in a mouse model of Alzheimers disease (AD) develops with age. When the proportion of each behavioral syllable was compared between genotypes and sexes, we found that the characteristic hyper-locomotion of female AD mice emerges between 4 and 8 months. In contrast, age-related reduction in rearing is common regardless of genotype and sex. Overall, SaLSa enables detailed characterization of mouse behavior. Significance StatementDescribing complex animal behavior is a challenge. Here, we developed an open-source, combinatory approach to behavioral syllable classification, called SaLSa (a combination of semi- automatic labeling and long short-term memory-based classification). In order to classify behavioral syllables, this approach combines multiple machine learning methods to label video frames semi- automatically and train a deep learning model. To demonstrate SaLSas versatility, we monitored the exploratory behavior of an Alzheimers disease mouse model and delineated their complex behaviors. We found that female Alzheimers mice become hyperactive in the sense that their locomotion behavior, but not other active behaviors, appear more frequently than controls and even male Alzheimers mice as they age. SaLSa offers a toolkit to analyze complex behaviors.