Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning

Antimicrobial peptides (AMPs) are attractive candidates to combat antibiotic resistance for their capability to target biomembranes and restrict a wide range of pathogens. It is a daunting challenge to discover novel AMPs due to their sparse distributions in a vast peptide universe, especially for p...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruihan Dong, Rongrong Liu, Ziyu Liu, Yangang Liu, Gaomei Zhao, Honglei Li, Shiyuan Hou, Xiaohan Ma, Huarui Kang, Jing Liu, Fei Guo, Ping Zhao, Junping Wang, Cheng Wang, Xingan Wu, Sheng Ye, Cheng Zhu
Format: Article
Language:English
Published: eLife Sciences Publications Ltd 2025-03-01
Series:eLife
Subjects:
Online Access:https://elifesciences.org/articles/97330
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850029873084497920
author Ruihan Dong
Rongrong Liu
Ziyu Liu
Yangang Liu
Gaomei Zhao
Honglei Li
Shiyuan Hou
Xiaohan Ma
Huarui Kang
Jing Liu
Fei Guo
Ping Zhao
Junping Wang
Cheng Wang
Xingan Wu
Sheng Ye
Cheng Zhu
author_facet Ruihan Dong
Rongrong Liu
Ziyu Liu
Yangang Liu
Gaomei Zhao
Honglei Li
Shiyuan Hou
Xiaohan Ma
Huarui Kang
Jing Liu
Fei Guo
Ping Zhao
Junping Wang
Cheng Wang
Xingan Wu
Sheng Ye
Cheng Zhu
author_sort Ruihan Dong
collection DOAJ
description Antimicrobial peptides (AMPs) are attractive candidates to combat antibiotic resistance for their capability to target biomembranes and restrict a wide range of pathogens. It is a daunting challenge to discover novel AMPs due to their sparse distributions in a vast peptide universe, especially for peptides that demonstrate potencies for both bacterial membranes and viral envelopes. Here, we establish a de novo AMP design framework by bridging a deep generative module and a graph-encoding activity regressor. The generative module learns hidden ‘grammars’ of AMP features and produces candidates sequentially pass antimicrobial predictor and antiviral classifiers. We discovered 16 bifunctional AMPs and experimentally validated their abilities to inhibit a spectrum of pathogens in vitro and in animal models. Notably, P076 is a highly potent bactericide with the minimal inhibitory concentration of 0.21 μM against multidrug-resistant Acinetobacter baumannii, while P002 broadly inhibits five enveloped viruses. Our study provides feasible means to uncover the sequences that simultaneously encode antimicrobial and antiviral activities, thus bolstering the function spectra of AMPs to combat a wide range of drug-resistant infections.
format Article
id doaj-art-a3cc7efaeefe498d8f6703762a5ec74b
institution DOAJ
issn 2050-084X
language English
publishDate 2025-03-01
publisher eLife Sciences Publications Ltd
record_format Article
series eLife
spelling doaj-art-a3cc7efaeefe498d8f6703762a5ec74b2025-08-20T02:59:23ZengeLife Sciences Publications LtdeLife2050-084X2025-03-011310.7554/eLife.97330Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learningRuihan Dong0https://orcid.org/0009-0001-5862-8410Rongrong Liu1https://orcid.org/0000-0002-9725-3463Ziyu Liu2Yangang Liu3Gaomei Zhao4Honglei Li5Shiyuan Hou6Xiaohan Ma7Huarui Kang8Jing Liu9Fei Guo10Ping Zhao11Junping Wang12Cheng Wang13https://orcid.org/0000-0002-6690-6433Xingan Wu14Sheng Ye15Cheng Zhu16https://orcid.org/0000-0003-0260-6287Frontiers Science Center for Synthetic Biology (Ministry of Education), Tianjin Key Laboratory of Function and Application of Biological Macromolecular Structures, School of Life Sciences, Faculty of Medicine, Tianjin University, Tianjin, China; Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaDepartment of Microbiology, Second Military Medical University, Shanghai, ChinaState Key Laboratory of Trauma and Chemical Poisoning, Institute of Combined Injury of PLA, College of Preventive Medicine, Third Military Medical University (Army Medical University), Chongqing, ChinaTianjin Cancer Hospital Airport Hospital, Tianjin, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, ChinaDepartment of Microbiology, Second Military Medical University, Shanghai, ChinaState Key Laboratory of Trauma and Chemical Poisoning, Institute of Combined Injury of PLA, College of Preventive Medicine, Third Military Medical University (Army Medical University), Chongqing, ChinaState Key Laboratory of Trauma and Chemical Poisoning, Institute of Combined Injury of PLA, College of Preventive Medicine, Third Military Medical University (Army Medical University), Chongqing, ChinaDepartment of Microbiology, School of Basic Medicine, Fourth Military Medical University, Shaanxi, ChinaFrontiers Science Center for Synthetic Biology (Ministry of Education), Tianjin Key Laboratory of Function and Application of Biological Macromolecular Structures, School of Life Sciences, Faculty of Medicine, Tianjin University, Tianjin, ChinaFrontiers Science Center for Synthetic Biology (Ministry of Education), Tianjin Key Laboratory of Function and Application of Biological Macromolecular Structures, School of Life Sciences, Faculty of Medicine, Tianjin University, Tianjin, ChinaAntimicrobial peptides (AMPs) are attractive candidates to combat antibiotic resistance for their capability to target biomembranes and restrict a wide range of pathogens. It is a daunting challenge to discover novel AMPs due to their sparse distributions in a vast peptide universe, especially for peptides that demonstrate potencies for both bacterial membranes and viral envelopes. Here, we establish a de novo AMP design framework by bridging a deep generative module and a graph-encoding activity regressor. The generative module learns hidden ‘grammars’ of AMP features and produces candidates sequentially pass antimicrobial predictor and antiviral classifiers. We discovered 16 bifunctional AMPs and experimentally validated their abilities to inhibit a spectrum of pathogens in vitro and in animal models. Notably, P076 is a highly potent bactericide with the minimal inhibitory concentration of 0.21 μM against multidrug-resistant Acinetobacter baumannii, while P002 broadly inhibits five enveloped viruses. Our study provides feasible means to uncover the sequences that simultaneously encode antimicrobial and antiviral activities, thus bolstering the function spectra of AMPs to combat a wide range of drug-resistant infections.https://elifesciences.org/articles/97330antimicrobial peptidesantiviral peptidesdeep learningdual-functiongenerative modelsequence design
spellingShingle Ruihan Dong
Rongrong Liu
Ziyu Liu
Yangang Liu
Gaomei Zhao
Honglei Li
Shiyuan Hou
Xiaohan Ma
Huarui Kang
Jing Liu
Fei Guo
Ping Zhao
Junping Wang
Cheng Wang
Xingan Wu
Sheng Ye
Cheng Zhu
Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
eLife
antimicrobial peptides
antiviral peptides
deep learning
dual-function
generative model
sequence design
title Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
title_full Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
title_fullStr Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
title_full_unstemmed Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
title_short Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning
title_sort exploring the repository of de novo designed bifunctional antimicrobial peptides through deep learning
topic antimicrobial peptides
antiviral peptides
deep learning
dual-function
generative model
sequence design
url https://elifesciences.org/articles/97330
work_keys_str_mv AT ruihandong exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT rongrongliu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT ziyuliu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT yangangliu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT gaomeizhao exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT hongleili exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT shiyuanhou exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT xiaohanma exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT huaruikang exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT jingliu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT feiguo exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT pingzhao exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT junpingwang exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT chengwang exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT xinganwu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT shengye exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning
AT chengzhu exploringtherepositoryofdenovodesignedbifunctionalantimicrobialpeptidesthroughdeeplearning