Ryosuke Kojima 研究室

主宰者：Ryosuke Kojima

京都大学

AI 要約（直近 5 年の研究成果）

Kojima研究室は、機械学習と計算科学の手法を用いて医療・医薬品開発における様々な課題に取り組んでいます。研究の問いは多岐にわたり、新規医薬品候補の発見を加速させる手法の開発、患者の疾患進行状態を正確に予測・可視化する方法の構築、医薬品の安全性や薬物動態に関わる性質の評価など、創薬プロセスの複数の段階で活用できる技術を目指しています。また、疾患診断補助や患者個別の健康状態の分析といった臨床応用も視野に入れています。手法としては、グラフニューラルネットワークや変圧器モデル、勾配ブースティング決定木などの深層学習技術を中心に用いています。分子構造や遺伝子ネットワーク、臨床データなど異なるタイプの情報をこれらの方法で処理し、予測精度を高めています。さらに、プライバシーを保護しながら複数機関のデータを活用するフェデレーション学習や、限定されたデータセットでも高精度を実現するための転移学習といった実践的な課題への対応も進めています。主要な成果として、化学反応予測や化合物タンパク質相互作用の予測における高精度モデルの構築、医薬品毒性スクリーニングに向けた構造警告の自動抽出、患者の疾患発症リスクを個人単位で可視化する手法の開発などが報告されています。これらの研究を通じて、理論的な精度向上だけでなく、実際の創薬現場や医療現場で実装可能な技術の開発を志向しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（35 件）

[2026] A deep state-space analysis framework for cancer patient latent state estimation and classification from EHR time-series data
DOI: https://doi.org/10.1371/journal.pone.0341003
[2026] Acute β-cell failure induced by selpercatinib in RET fusion–positive non-small cell lung cancer: A case report
DOI: https://doi.org/10.1016/j.rmcr.2026.102372
[2025] ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data
DOI: https://doi.org/10.1186/s13321-025-01075-4
[2025] Improving ADME Prediction with Multitask Graph Neural Networks and Assessing Explainability in Lead Optimization
DOI: https://doi.org/10.1021/acs.jcim.5c00758
[2025] Detection of Polyphonic Alarm Sounds From Medical Devices Using Frequency-Enhanced Deep Learning: Simulation Study
DOI: https://doi.org/10.2196/35987
[2025] Transfer learning from custom-tailored virtual molecular databases to real-world organic photosensitizers for catalytic activity prediction
DOI: https://doi.org/10.1038/s42004-025-01678-w
[2025] Improving ADME Prediction with Multitask Graph Neural Networks and Assessing Explainability in Lead Optimization
DOI: https://doi.org/10.26434/chemrxiv-2025-ls77r-v2
[2025] Empowering Federated Learning for Robust Compound-Protein Interaction Prediction across Heterogeneous Cross-Pharma Domains
DOI: https://doi.org/10.26434/chemrxiv-2025-nj6jd
[2025] Transfer learning across different photocatalytic organic reactions
DOI: https://doi.org/10.1038/s41467-025-58687-5
[2025] Precision spatiotemporal analysis of large-scale compound–protein interactions through molecular dynamics simulation
DOI: https://doi.org/10.1093/pnasnexus/pgaf094

続きを表示（残り 25 件）

[2025] Out-of-distribution reject option method for dataset shift problem in early disease onset prediction
DOI: https://doi.org/10.1038/s41598-025-01811-8
[2025] kMoL: an open-source machine and federated learning library for drug discovery
DOI: https://doi.org/10.1186/s13321-025-00967-9
[2025] Sustained remission after discontinuation of immunosuppressive therapy in patients with anti-MDA5 antibody–positive dermatomyositis–associated interstitial lung disease: Two case reports
DOI: https://doi.org/10.1016/j.resinv.2025.10.014
[2024] Constructing a graph neural network-based artificial intelligence model to predict drug-induced phospholipidosis potential
DOI: https://doi.org/10.2131/fts.11.279
[2024] Interpretable machine learning-based individual analysis of acute kidney injury in immune checkpoint inhibitor therapy
DOI: https://doi.org/10.1371/journal.pone.0298673
[2024] Developing a GNN-based AI model to predict mitochondrial toxicity using the bagging method
DOI: https://doi.org/10.2131/jts.49.117
[2024] Selective recognition between aromatics and aliphatics by cage-shaped borates supported by a machine learning approach
DOI: https://doi.org/10.1039/d4ob00408f
[2024] Floor-Field-Guided Neural Model for Crowd Counting
DOI: https://doi.org/10.1109/access.2024.3483252
[2023] VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search
DOI: https://doi.org/10.1021/acs.jcim.3c01220
[2023] Interpretable Machine Learning-Based Individual Analysis of AKI in Immune Checkpoint Inhibitor Therapy
DOI: https://doi.org/10.1681/asn.20233411s1411d
[2023] Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network
DOI: https://doi.org/10.1186/s12859-023-05507-6
[2023] Toward AI-supported evaluation for safety control measures against near-miss events in pharmaceutical products
DOI: https://doi.org/10.1016/j.ssci.2023.106314
[2023] Individual health-disease phase diagrams for disease prevention based on machine learning
DOI: https://doi.org/10.1016/j.jbi.2023.104448
[2023] Improving Compound–Protein Interaction Prediction by Self-Training with Augmenting Negative Samples
DOI: https://doi.org/10.1021/acs.jcim.3c00269
[2023] Development of a GCN-based model to predict <i>in vitro</i> phototoxicity from the chemical structure and HOMO-LUMO gap
DOI: https://doi.org/10.2131/jts.48.243
[2023] Toward Ai-Supported Evaluation for Safety Control Measures Against Near-Miss Events in Pharmaceutical Products
DOI: https://doi.org/10.2139/ssrn.4333919
[2022] GCN-Based Structure-Activity Relationship and DFT Studies of Staphylococcus aureus FabI Inhibitors
DOI: https://doi.org/10.4018/ijqspr.313627
[2022] Characterizing eye-gaze positions of people with severe motor dysfunction: Novel scoring metrics using eye-tracking and video analysis
DOI: https://doi.org/10.1371/journal.pone.0265623
[2022] AI-Driven Synthetic Route Design Incorporated with Retrosynthesis Knowledge
DOI: https://doi.org/10.1021/acs.jcim.1c01074
[2022] Predictive Diagnostic Approach to Dementia and Dementia Subtypes Using Wireless and Mobile Electroencephalography: A Pilot Study
DOI: https://doi.org/10.1089/bioe.2021.0030
[2022] Differential Privacy under Incalculable Sensitivity
DOI: https://doi.org/10.1109/csp55486.2022.00013
[2021] Evaluation of Kidney Histological Images Using Unsupervised Deep Learning
DOI: https://doi.org/10.1016/j.ekir.2021.06.008
[2021] Health improvement framework for actionable treatment planning using a surrogate Bayesian model
DOI: https://doi.org/10.1038/s41467-021-23319-1
[2021] Prediction and visualization of acute kidney injury in intensive care unit using one-dimensional convolutional neural networks based on routinely collected data
DOI: https://doi.org/10.1016/j.cmpb.2021.106129
[2021] An unsupervised auditory scene analysis system using incremental low-dimensional embedding
DOI: https://doi.org/10.1109/ieeeconf49454.2021.9382632

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（35 件）

科研費（0 件）

所属学会・役職（0 件）