TY - JOUR
T1 - A layered, hybrid machine learning analytic workflow for mouse risk assessment behavior
AU - Wang, Jinxin
AU - Karbasi, Paniz
AU - Wang, Liqiang
AU - Meeks, Julian P.
N1 - Funding Information:
This work was supported by the National Institute of Deafness and Other Communication Disorders of the National Institutes of Health (Grants R01DC017985 and R01DC015784, JPM) and the BioHPC Fellows Program (JW).
Publisher Copyright:
© 2022 Wang et al.
PY - 2023/1
Y1 - 2023/1
N2 - Accurate and efficient quantification of animal behavior facilitates the understanding of the brain. An emerging approach within machine learning (ML) field is to combine multiple ML-based algorithms to quantify animal behavior. These so-called hybrid models have emerged because of limitations associated with supervised (e.g., random forest, RF) and unsupervised (e.g., hidden Markov model, HMM) ML models. Forexample, RF models lack temporal information across video frames, and HMM latent states are often difficult to interpret. We sought to develop a hybrid model, and did so in the context of a study of mouse risk assessment behavior. We utilized DeepLabCut to estimate the positions of mouse body parts. Positional features were calculated using DeepLabCut outputs and were used to train RF and HMM models with equal number of states, separately. The per-frame predictions from RF and HMM models were then passed to a second HMM model layer (“reHMM”). The outputs of the reHMM layer showed improved interpretability over the initial HMM output. Finally, we combined predictions from RF and HMM models with selected positional features to train a third HMM model (“reHMM+"). This reHMM+ layered hybrid model unveiled distinctive temporal and human-interpretable behavioral patterns. We applied this workflow to investigate risk assessment to trimethylthiazoline and snake feces odor, finding unique behavioral patterns to each that were separable from attractive and neutral stimuli. We conclude that this layered, hybrid ML workflow represents a balanced approach for improving the depth and reliability of ML classifiers in chemosensory and other behavioral contexts.
AB - Accurate and efficient quantification of animal behavior facilitates the understanding of the brain. An emerging approach within machine learning (ML) field is to combine multiple ML-based algorithms to quantify animal behavior. These so-called hybrid models have emerged because of limitations associated with supervised (e.g., random forest, RF) and unsupervised (e.g., hidden Markov model, HMM) ML models. Forexample, RF models lack temporal information across video frames, and HMM latent states are often difficult to interpret. We sought to develop a hybrid model, and did so in the context of a study of mouse risk assessment behavior. We utilized DeepLabCut to estimate the positions of mouse body parts. Positional features were calculated using DeepLabCut outputs and were used to train RF and HMM models with equal number of states, separately. The per-frame predictions from RF and HMM models were then passed to a second HMM model layer (“reHMM”). The outputs of the reHMM layer showed improved interpretability over the initial HMM output. Finally, we combined predictions from RF and HMM models with selected positional features to train a third HMM model (“reHMM+"). This reHMM+ layered hybrid model unveiled distinctive temporal and human-interpretable behavioral patterns. We applied this workflow to investigate risk assessment to trimethylthiazoline and snake feces odor, finding unique behavioral patterns to each that were separable from attractive and neutral stimuli. We conclude that this layered, hybrid ML workflow represents a balanced approach for improving the depth and reliability of ML classifiers in chemosensory and other behavioral contexts.
KW - hidden Markov model
KW - machine learning
KW - quantification of behavior
KW - random forest
KW - risk assessment behavior
UR - http://www.scopus.com/inward/record.url?scp=85145974884&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145974884&partnerID=8YFLogxK
U2 - 10.1523/ENEURO.0335-22.2022
DO - 10.1523/ENEURO.0335-22.2022
M3 - Article
C2 - 36564214
AN - SCOPUS:85145974884
SN - 2373-2822
VL - 10
JO - eNeuro
JF - eNeuro
IS - 1
ER -