CV

Download CV (PDF)

Overview

Assistant Professor at the Life Science Center for Survival Dynamics, Tsukuba Advanced Research Alliance (TARA), University of Tsukuba. My research aims to treat life phenomena as a hierarchical system of morphology, psychology, and behavior and to quantify them as information. Specifically, I work on quantification of morphology using deep generative models, quantification of psychological state (e.g., social stress) using mathematical models, and quantitative analysis of behavior based on inter-individual interactions, with the goal of understanding universal principles that describe the state and dynamics of life.

Contact

  • Email: mtsutsumi[at]tara.tsukuba.ac.jp
  • Address: Life Science Center for Survival Dynamics, Tsukuba Advanced Research Alliance (TARA), University of Tsukuba, Tsukuba, Japan

Education

  • Ph.D. in Science, Graduate School of Science, The University of Tokyo (Apr 2020 - Sep 2023)
  • M.S. in Science, Graduate School of Science, The University of Tokyo (Apr 2018 - Mar 2020)
  • B.S. in Science, Department of Physics, Faculty of Science, The University of Tokyo (Apr 2014 - Mar 2018)

Professional Appointments

  • Assistant Professor, Life Science Center for Survival Dynamics (TARA), University of Tsukuba (Dec 2025 - Present)
  • Visiting Researcher, Graduate School of Medicine, Nagoya University (Dec 2025 - Present)
  • Designated Assistant Professor, Graduate School of Medicine, Nagoya University (Oct 2024 - Nov 2025)
  • Designated Researcher, Graduate School of Integrated Sciences for Life, Hiroshima University (Oct 2023 - Sep 2024)
  • Graduate Student Research Associate, RIKEN (Apr 2020 - Mar 2023)

Teaching

  • Medical Data Science I, Nagoya University School of Medicine (Jun 2025 - Jul 2025)
  • Basic Medical Seminar, Nagoya University School of Medicine (Oct 2024 - Mar 2025)
  • Computational Experiments I (Teaching Assistant), Department of Physics, The University of Tokyo (Apr 2019 - Aug 2019)

Grants & Awards

  • Takeda Science Foundation Medical Research Grant (Basic Research) (2025)

Publications

  • Sakaguchi, S.#, Tsutsumi, M.# (co-first), Nishi, K., Honda, N. Disentanglement of batch effects and biological signals across conditions in the single-cell transcriptome. Patterns (in press; expected October 2026) DOI
  • Yamaguchi, Tsutsumi et al. Artificial-Intelligence-Based Cephalometric Landmark Detection in Lateral Cephalograms. Journal of Clinical Medicine (2026)
  • Uchida, Tsutsumi et al. Deciphering the origin of developmental stability: The role of intracellular expression variability in evolutionary conservation. Evolution & Development (2024)
  • Tsutsumi, Saito, Koyabu, Furusawa. A deep learning approach for morphological feature extraction based on variational auto-encoder: an application to mandible shape. npj Systems Biology and Applications (2023)

Preprints

  • Tsutsumi et al. Mind the gap: quantifying population–individual gap in depressive symptom dynamics through energy landscapes. bioRxiv (2026)
  • Matsuda-Watanabe, Tsutsumi et al. Chemosensory input suppresses cannibalism by stabilizing social feeding boundaries in Drosophila larvae. In submission (2026)
  • Tsutsumi et al. Decoding Anadara shell morphology with deep learning. bioRxiv (2026)

Invited Talks

  • 2026/07/30 — AI for measuring morphological differences among living organisms. FY2026 University of Tsukuba Open Lecture
  • 2026/07/27 — Towards quantification of form using information science. Workshop on Quantification of Form 2026
  • 2026/07/15 — Development of methods for quantifying biological morphology with an information-science approach. Japan Society for Cell Biology
  • 2026/06/09 — Variational energy landscape analysis reveals population trends and individual heterogeneity during and after COVID-19 emergency declarations. JSAI 2026
  • 2026/03/05 — Towards quantification of diverse life phenomena: morphology, behavior, and psychology as information. SSTB2026
  • 2024/09/16 — Development of quantitative analysis methods for biological morphology using deep learning. JSIAM Annual Meeting 2024
  • 2024/03/09 — Development of quantitative analysis methods for biological morphology using deep learning. Online Seminar Series “Future of Evolutionary Biology with AI”
  • 2024/02/14 — Development of quantitative analysis methods for biological morphology using deep learning. 8th Theoretical Immunology Workshop
  • 2022/11/10 — Quantification of various biological morphologies using machine learning. Hiroshima University Mathematical Life Sciences Program Seminar
  • 2021/10 — Quantification and application of biological morphology using machine learning: Focusing on primate mandibles. NIBB Departmental Seminar

Conference Presentations

  • 2026/07/12 — Mind the gap: quantifying population–individual differences in depressive symptom dynamics using energy landscapes. 2nd Systems Behavioral Science Workshop
  • 2026/06/27 — Morphological character selection using machine learning for phylogenetic analysis: revisiting the phylogenetic position of lepidosaurs. Palaeontological Society of Japan 2026
  • 2026/02/20 — Quantitative Analysis of Biological Morphology and Behavior Based on Deep Learning: Development of Morpho-VAE and DOLO. Frontiers of coevolutionary phenotypic emergence research
  • 2026/01/13 — Analysis of morphology and behavior using deep learning methods. Principles for Creating Life Functions through Evolutionary Information Assembly
  • 2025/12/05 — Development of a markerless multi-individual tracking system for controlling cannibalistic behavior in crickets. Japanese Society for Comparative Physiology and Biochemistry
  • 2025/11/30 — Morphological quantification using deep learning: Morpho-VAE. 99th Symposium on Science of Form
  • 2025 — Visualization of morphological variation using 3D Variational Autoencoder. Japanese Society for Bioimaging
  • 2025/05/30 — Behavioral analysis of double mutant Drosophila larvae using DOLO. 1st Systems Behavioral Science Workshop
  • 2025/02/20 — Estimation of psychological state transitions during/after emergency declarations using energy landscape analysis. SSTB2025
  • 2024/09/12 — Proposal of morphological quantitative analysis methods using deep learning. Japanese Society for Mathematical Biology 2024
  • 2024/03/28 — Quantification of mouse behavior under social defeat stress using mathematical models. CPSY TOKYO 2024
  • 2024/02/20 — Mathematical model of rumination in the brain using Bayesian inference. Spring School for Theoretical Biology 2024
  • 2024/01/06 — Mathematical model of rumination in the brain using free energy principle. Quantitative Biology Society
  • 2023/12/16 — Unveiling the enigmatic Middle Devonian vertebrate, Palaeospondylus. Asia Evo Conference Symposium
  • 2023/08/08 — Development of a quantitative analysis method for biological morphology using deep learning. Statphys28 Satellite meeting
  • 2022/12/15 — Morphological feature extraction of primate mandibles using variational autoencoders. Quantitative Biology Society
  • 2022/09/30 — A method for morphological feature extraction based on variational auto-encoder. Biophysical Society of Japan
  • 2022/06/01 — A deep learning approach for the shape analysis of the primates mandible. Euro Evo Devo 2022
  • 2020/01/31 — Verification of classification methods for 2D OCT images using two-stage networks. Japanese Society for Medical AI

For links and additional details, see the Publications page and researchmap.