吉留崇,
"シミュレーション不要の水和自由エネルギー分布予測AI" (invited),
現代化学(2026年7月号)
S. Arai, Y. Takayama (Corresponding author), and T. Yoshidome (Corresponding author, ポスドク指導),
"Structure-based Prediction of Gas Diffusion Property of Catalytic Layer of Proton Exchange Membrane Fuel Cells via Manifold Learning and X-ray Ptychographic Nano-computed Tomography "
Journal of Power Sources, Vol. 676, 239916 (2026). [Open access]
プレスリリース(東北大学、JST):ナノテラスのナノCT画像からガス拡散を10秒で予測 - 燃料電池の高出力・長寿命化に向けた材料設計最適化へ -
Y. Fukushima and T. Yoshidome (Corresponding author, 学生指導),
“Deep GIST: Deep-Learning Models for Predicting the Distribution of Hydration Thermodynamics around Proteins”
Journal of Chemical Information and Modeling, Vol. 66, 1429 (2026). [Open access]
プログラム"Deep GIST":https://github.com/YoshidomeGroup-Hydration/Deep-GIST
プレスリリース(東北大学):深層学習によりタンパク質周辺の水和解析を実用速度に ―創薬への応用を目指し、従来法の計算時間を大幅に短縮―
K. Kawama, Y. Fukushima, M. Ikeguchi, M. Ohta, and T. Yoshidome (Corresponding author, 学生指導)
"gr Predictor: A Deep-Learning Model For Predicting the Hydration Structure of Proteins",
Journal of Chemical Information and Modeling, Vol. 62, 4460 (2022).
プログラム"gr Predictor":https://github.com/YoshidomeGroup-Hydration/gr-predictor
小田垣 孝、吉留 崇、大久保 毅、
「現代の物性物理学」(M. L. Cohen and S. G. Louie: Fundamentals of Condensed Matter Physics)
吉岡書店、2021年9月出版 Amazonのページ
Yusaku Fukushima and Takashi Yoshidome(発表者)
“Deep Learning Model for Hydration Free Energy Distributions around Proteins”(Poster)
Shota Arai, Yuki Takayama, and Takashi Yoshidome,
“Prediction of Gas Diffusion Coefficients from X-ray Ptychography Images via Manifold Learning”(Poster)
Kei Sano and Takashi Yoshidome,
“Machine learning-based method for calculating hydration free energy of protein–small molecule complexes”(Poster)
吉留 崇、
“マニフォールド学習を用いた多孔質構造ナノCTデータからのガス拡散予測”(依頼講演)
Shota Arai, Yuki Takayama, and Takashi Yoshidome,
“Prediction of Gas Diffusion Coefficients in Proton Exchange Membrane Fuel Cells Using X-ray Ptychography and Manifold Learning”(Poster)
Shota Arai, Yuki Takayama, and Takashi Yoshidome,
“Prediction of the Gas Diffusion Coefficients in Porous Materials using Nano-CT images of NanoTerasu and Manifold Learning”(Poster)
Yusaku Fukushima and Takashi Yoshidome(発表者)
“Prediction of Hydration Thermodynamics Distributions around Proteins using Deep Learning”(Poster)
Shota Arai , Yuki Takayama, and Takashi Yoshidome,
“A Data-Driven Framework for Predicting Transport Properties Using Manifold-Learning-Based Feature Extraction of Porous Structures” (Poster)
Kaito Fukushima, Masateru Ohta, Mitsunori Ikeguchi, and Takashi Yoshidome,
“Deep-Learning-Based Identification of Halogen Substitution Positions Using Water Molecules in Ligand-Binding Pockets” (Poster)
Kei Sano and Takashi Yoshidome,
“Acceleration of Protein Hydration Free Energy Calculation Using Machine Learning” (Poster)
Yuta Hattori and Takashi Yoshidome,
“Pathway Analysis of Protein Structural Changes using Machine Learning and Molecular Dynamics Simulations” (Poster)
水和に主眼を置いたタンパク質折り畳み・変性・機能発現機構の統一的理解、及び創薬への応用
マニフォールドラーニングを用いた低温電子顕微鏡実験データ分類・解析法の開発と応用
自由エネルギーランドスケープ理論を用いたガラス転移の理解