@article {Hebert2020.07.09.193755, author = {Laetitia Hebert and Tosif Ahamed and Antonio C. Costa and Liam O{\textquoteright}Shaugnessy and Greg J. Stephens}, title = {WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans}, elocation-id = {2020.07.09.193755}, year = {2020}, doi = {10.1101/2020.07.09.193755}, publisher = {Cold Spring Harbor Laboratory}, abstract = {An important model system for understanding genes, neurons and behavior, the nematode worm C. elegans naturally moves through a variety of complex postures, for which estimation from video data is challenging. We introduce an open-source Python package, WormPose, for 2D pose estimation in C. elegans, including self-occluded, coiled shapes. We leverage advances in machine vision afforded from convolutional neural networks and introduce a synthetic yet realistic generative model for images of worm posture, thus avoiding the need for human-labeled training. WormPose is effective and adaptable for imaging conditions across worm tracking efforts. We quantify pose estimation using synthetic data as well as N2 and mutant worms in on-food conditions. We further demonstrate WormPose by analyzing long (\~{} 10 hour), fast-sampled (\~{} 30 Hz) recordings of on-food N2 worms to provide a posture-scale analysis of roaming/dwelling behaviors.Competing Interest StatementThe authors have declared no competing interest.}, URL = {https://www.biorxiv.org/content/early/2020/08/15/2020.07.09.193755}, eprint = {https://www.biorxiv.org/content/early/2020/08/15/2020.07.09.193755.full.pdf}, journal = {bioRxiv} }