DiverScan: attention-guided exploratory analysis of animal behaviour across diverse comparative experiments
Year: 2026
Type: preprint
Abstract: High-throughput tracking yields rich time-series data of animal behaviour, yet extracting biological insight remains a bottleneck, even for simple control--treatment comparisons. Existing analyses struggle to pinpoint the multiple, nonlinearly intertwined differences hidden in the data and fail to generalise across diverse recording set-ups. Here we present DiverScan, a deep-learning framework for attention-guided exploratory analysis of behavioural time series. DiverScan disentangles condition-dependent behavioural differences by pairing a loss function tailored to data exploration with an attention-branch architecture, and highlights condition-specific behavioural features visually and with explanatory text generated by a large language model. DiverScan is validated on a synthetic benchmark and on datasets from seven laboratories spanning multiple species and both single- and multi-animal behaviour. Beyond recovering known phenotypes, we demonstrate that DiverScan helps researchers generate new hypotheses across these diverse datasets. Available as Jupyter notebooks with a graphical user interface and flexible input formats, DiverScan can integrate into existing behavioural-analysis pipelines.
Authors: Momoe Sukegawa, Hirotsugu Azechi, Tatsumi Butsugan, Nadja Freund, Shiomi Hakataya, Tomohiro Iwata, Noriko Katsu, Koutarou D. Kimura, Hiroki Koda, Akiko Koto, Yuya Makiguchi, Hiroshi Matsui, Koji Miyoshi, Annakarina Mundorf, Hiraku Nishimori, Kazuo Okanoya, Masashi Shiraishi, Susumu Takahashi, Ryoya Tanaka, Genta Toya, Chitose Yamazaki, Shuhei J. Yamazaki, Takuya Maekawa
Institutions: The University of Osaka, Doshisha University, Nagoya City University, University Hospitals of the Ruhr-University of Bochum, LWL-Universitätsklinikum Bochum, University of the Ryukyus, National Institute of Advanced Industrial Science and Technology, The University of Tokyo, Nihon University, Hokkaido Research Organization, MSH Medical School Hamburg – University of Applied Sciences and Medical University, Meiji University, Meiji (Japan), Teikyo University, Hiroshima City University, Nagoya University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Japan Agency for Medical Research and Development, Ministry of Education, Culture, Sports, Science and Technology, Daiichi-Sankyo, Nagoya City University, Nakatani Foundation for Advancement of Measuring Technologies in Biomedical Engineering, Japan Society for the Promotion of Science, Core Research for Evolutional Science and Technology
OpenAlex ID: W7221019112