About
Shogo Nakamura / 中村 彰悟
Researcher at Xeureka, Inc.
Research Interest
- Organic Chemistry
- Cheminformatics
- Computer Aided Drug Discovery
Education
- 2018 B.Sci. (Chemistry), Osaka University (Advisor: Prof. Satoshi, Minakata)
- 2020 M.Sci. (Chemistry), Osaka University (Advisor: Prof. Satoshi, Minakata)
- 2025 Ph.D. (Cheminformatics), Institute of Science Tokyo (Advisor: Prof. Masakazu, Sekijima)
Experience
- 2020/04 - 2022/3, Daikin Industries, Ltd.
- Structure Development of Small Molecules for Materials:
- Investigated the synthesis of small molecules to obtain polymers with desired properties through communication with customer polymer manufacturers and internal teams responsible for polymer synthesis and evaluation.
- Process Investigation:
- Investigated processes for synthesizing building blocks using the company’s fluorination technology.
- Structure Development of Small Molecules for Materials:
- 2022/04 - 2025/03, Institute of Science Tokyo (formerly Tokyo Institute of Technology):
- Optimization of Compound Structures with Synthesis Route Generation
- Leveraged expertise in organic chemistry to explicitly handle reactions applied to raw materials, generating synthesis routes while optimizing compound structures against evaluation functions.
- Developed a framework integrating product prediction of chemical reactions using Transformer, the core structure of large language models, with Monte Carlo tree search, an optimization algorithm.
- Structure Generation of Compounds with Specific Interactions for Target Proteins
- Developed a compound generation model that takes interaction vectors as input, obtained by calculating the strength of interactions with amino acid residues in the pocket of target proteins.
- Large Language Model Drug Discovery Competition (LLM Drug Discovery)
- Participated and won the competition for proposing compounds predicted to have high binding affinity for target proteins using large language models.
- Collaborative Research with Companies and Universities
- Investigated the generation of compounds with high docking scores for target proteins using existing compound generation models.
- Collaborated with a laboratory specializing in organic synthetic chemistry to investigate the generation of compounds with high docking scores for target proteins.
- Optimization of Compound Structures with Synthesis Route Generation
- 2025/04 - present, Xeureka, Inc.
Publications
- ‘Molecular Optimization Using Conditional Transformer for Reaction-Aware Compound Exploration with Reinforcement Learning’ Shogo Nakamura, Nobuaki Yasuo and Masakazu Sekijima* Commun. Chem. 2025, 8, 40. Link
- ‘IEV2Mol: Molecular Generative Model Considering Protein–Ligand Interaction Energy Vectors’ Mami Ozawa, Shogo Nakamura, Nobuaki Yasuo, Masakazu Sekijima* J. Chem. Inf. Model. 2024, 64, 6969. Link
- ‘LLM Drug Discovery Challenge: A Contest as a Feasibility Study on the Utilization of Large Language Models in Medicinal Chemistry’ Kusuri Murakumo, Naruki Yoshikawa, Kentaro Rikimaru, Shogo Nakamura, Kairi Furui, Takamasa Suzuki, Hiroyuki Yamasaki, Yuki Nishigaya, Yuzo Takagi, Masahito Ohue NeurIPS 2023 AI for Accelerated Materials Design (AI4Mat) Workshop 2023. Link
- ‘Gargoyles: An Open Source Graph-Based Molecular Optimization Method Based on Deep Reinforcement Learning’ Daiki Erikawa, Nobuaki Yasuo, Takamasa Suzuki, Shogo Nakamura, and Masakazu Sekijima* ACS Omega 2023, 8, 37431–37441. Link
- ‘Transition-Metal-Free Aziridination of Alkenes with Sulfamate Esters Using tert-Butyl Hypoiodite’ Kensuke Kiyokawa*, Shogo Nakamura, and Satoshi Minakata* Heterocycles 2021, 103, 190–197. Link
- ‘Transition-Metal-Free Intramolecular C−H Amination of Sulfamate Esters and N-Alkylsulfamides’ Kensuke Kiyokawa*, Shogo Nakamura, Keisuke Jou, Kohji Iwaida, and Satoshi Minakata* Chem. Commun. 2019, 55, 11782–11785. Link
Conferences
- 〇Shogo Nakamura, Nobuaki Yasuo, Masakazu Sekijima. Chemical-reaction-aware molecular optimization using conditional transformer and reinforcement learning. ACS Spring 2025 COMP Poster Session, #1172, United States, California, San Diego, 2025/03, Poster
- 〇Shogo Nakamura, Nobuaki Yasuo, Masakazu Sekijima. Chemical-reaction-aware molecular optimization using conditional transformer and reinforcement learning. ACS Spring 2025 COMP Sci-Mix, #667, United States, California, San Diego, 2025/03, Poster
- 〇中村彰悟, 安尾信明, 関嶋政和. 合成経路の生成を伴う化合物生成モデルの開発, 学術変革領域研究(A)「潜在空間分子設計」第1回 リトリート, P-32, 福岡県北九州市, 2024年11月, ポスター発表.
- 〇中村彰悟, 安尾信明, 関嶋政和. Reaction-Aware Molecular Optimization Using Conditional Transformer and Reinforcement Learning, CBI学会2024年大会, P03-04, 東京都江戸川区, 2024年10月, ポスター発表.
- 〇中村彰悟, 安尾信明, 関嶋政和. Transformerとモンテカルロ木探索を活用した合成経路の生成を伴う化合物最適化モデルの開発, 学術変革領域研究(A)「潜在空間分子設計」第2回公開シンポジウム, P-28, 宮城県仙台市, 2024年6月, ポスター発表.
- 〇中村彰悟, #LLM創薬チャレンジ 開催報告 ～創薬における大規模言語モデル活用のフィージビリティスタディとして～, 構造活性フォーラム2023, 2023年8月, 口頭発表 (招待講演).
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルの分子内C–Hアミノ化, 第22回ヨウ素学会シンポジウム, V-4, 千葉県千葉市, 2019年8月, 口頭発表.
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルの分子内C–Hアミノ化, 第39回有機合成若手セミナー, P-002, 大阪府堺市, 2019年8月, ポスター発表.
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルのメタルフリー分子内C–Hアミノ化, 第8回 JACI/GSCシンポジウム, C-53, 東京都千代田区, 2019年6月, ポスター発表.
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルの分子内C–Hアミノ化, 日本化学会第99春季年会, 1I4-18, 兵庫県神戸市, 2019年3月, 口頭発表.
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルの遷移金属フリー分子内C–Hアミノ化, 第8回CSJ化学フェスタ, P3-035, 東京都江戸川区, 2018年10月, ポスター発表.
- 〇中村彰悟, 清川謙介, 南方聖司. ヨウ素酸化剤を活用したスルファマートエステルの遷移金属フリー分子内C–Hアミノ化, 第38回有機合成若手セミナー, P-041, 兵庫県西宮市, 2018年8月, ポスター発表.
- 〇中村彰悟, 清川謙介, 南方聖司. 次亜ヨウ素酸 tert-ブチルを活用したスルファマートエステルの分子内C–Hアミノ化, 第53回有機反応若手の会, 埼玉県熊谷市, 2018年7月, ポスター発表.
- 〇中村彰悟, 清川謙介, 南方聖司. 次亜ヨウ素酸 tert-ブチルを活用したスルファマートエステルを窒素源とするオレフィン類のアジリジン化, 日本化学会第98春季年会, 4H4-13, 千葉県船橋市, 2018年3月, 口頭発表.