AI-guided few-shot inverse design of HDP-mimicking polymers against 
drug-resistant bacteria

Wu, Tianyu; Zhou, Min; Zou, Jingcheng; Chen, Qi; Qian, Feng; Kurths, Jürgen; Liu, Runhui; Tang, Yang

doi:10.1038/s41467-024-50533-4

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

学術論文

AI-guided few-shot inverse design of HDP-mimicking polymers against drug-resistant bacteria

Authors

Wu, Tianyu
External Organizations;

Zhou, Min
External Organizations;

Zou, Jingcheng
External Organizations;

Chen, Qi
External Organizations;

Qian, Feng
External Organizations;

/persons/resource/Juergen.Kurths

Kurths, Jürgen
Potsdam Institute for Climate Impact Research;

Liu, Runhui
External Organizations;

Tang, Yang
External Organizations;

URL

https://github.com/TianyuWu813/polymer_generation
(付録資料)

https://github.com/TianyuWu813/polymer_prediction
(付録資料)

フルテキスト (公開)

wu_2024_s41467-024-50533-4.pdf
(出版社版), 65MB

付随資料 (公開)

There is no public supplementary material available

引用

Wu, T., Zhou, M., Zou, J., Chen, Q., Qian, F., Kurths, J., Liu, R., & Tang, Y. (2024). AI-guided few-shot inverse design of HDP-mimicking polymers against drug-resistant bacteria. Nature Communications, 15:. doi:10.1038/s41467-024-50533-4.

引用: https://publications.pik-potsdam.de/pubman/item/item_30669

要旨

Host defense peptide (HDP)-mimicking polymers are promising therapeutic alternatives to antibiotics and have large-scale untapped potential. Artificial intelligence (AI) exhibits promising performance on large-scale chemical-content design, however, existing AI methods face difficulties on scarcity data in each family of HDP-mimicking polymers (<102), much smaller than public polymer datasets (>105), and multi-constraints on properties and structures when exploring high-dimensional polymer space. Herein, we develop a universal AI-guided few-shot inverse design framework by designing multi-modal representations to enrich polymer information for predictions and creating a graph grammar distillation for chemical space restriction to improve the efficiency of multi-constrained polymer generation with reinforcement learning. Exampled with HDP-mimicking β-amino acid polymers, we successfully simulate predictions of over 105 polymers and identify 83 optimal polymers. Furthermore, we synthesize an optimal polymer DM0.8iPen0.2 and find that this polymer exhibits broad-spectrum and potent antibacterial activity against multiple clinically isolated antibiotic-resistant pathogens, validating the effectiveness of AI-guided design strategy.