Download all files (3.48MB)

コレクション

引用

説明:

Language models have been increasingly popular in therapeutic peptide generation, but molecular diversity remains limited due to reliance on the 20 canonical amino acids. We propose a language model that generates peptidomimetics incorporating noncanonical elements like noncanonical amino acids and terminal modifications. To accomplish this, we created a vocabulary of over 17,000 noncanonical elements by extracting them from chemical formulas stored in the ChEMBL database. Our pretrained language model, GPepT, showed improved diversity in molecular structures and chemical properties. To demonstrate its real-world application, we fine-tuned the model for antimicrobial peptides. Experimental validation revealed that one of the generated peptidomimetics exhibited effective antimicrobial activity, marking a successful case of AI-driven peptide development. GPepT is fully accessible on HuggingFace: https://huggingface.co/Playingyoyo/GPepT.

権利情報:

• Creative Commons BY-NC-ND Attribution-NonCommercial-NoDerivs 4.0 International
  

キーワード: Language model, amino acid

刊行年月日: 2025-07-22

出版者: American Chemical Society (ACS)

掲載誌:

• ACS Medicinal Chemistry Letters (ISSN: 19485875) vol. 16 issue. 8 acsmedchemlett.5c00375

研究助成金:

• Core Research for Evolutional Science and Technology JPMJCR21O2
• Exploratory Research for Advanced Technology JPMJER1903
• Agency for Cultural Affairs, Government of Japan JPMXP1122712807

原稿種別: 出版者版 (Version of record)

MDR DOI:

公開URL: https://doi.org/10.1021/acsmedchemlett.5c00375

関連資料:

その他の識別子:

連絡先:

更新時刻: 2025-08-25 12:30:37 +0900

MDRでの公開時刻: 2025-08-25 12:19:24 +0900