| 134 | 0 | 80 |
| 下载次数 | 被引频次 | 阅读次数 |
随着抗生素耐药性危机在全球范围内持续蔓延,研发新型抗菌药物已成为亟待解决的问题。抗菌肽(antimicrobial peptides, AMPs)具有独特的抗菌作用机制,不易诱导细菌产生耐药性,已经成为替代传统抗生素的重要候选药物。然而,传统实验筛选抗菌肽存在周期长、成本高等问题,不利于天然抗菌肽的挖掘。近年来,宏基因组学与人工智能的深度融合,为从海量环境及微生物组数据中高效挖掘抗菌肽提供了全新的思路。本文梳理了抗菌肽特征、相关资源数据库及实验验证方法,总结了人工智能判别抗菌肽的方法,包括传统机器学习、深度学习、蛋白质语言模型和迁移学习等技术方法,并且系统叙述了多模型混合策略在宏基因组数据中的应用进展。目前,该领域仍存在高质量标注数据不足、高通量验证困难等问题。但随着人工智能和多组学技术的进步,抗菌肽的智能化、精准化挖掘将实现突破性进展,有效加速更高效候选分子的发现和临床转化进程,为应对抗生素耐药性危机提供有效解决方案。
Abstract：As the antimicrobial resistance crisis continues to spread globally, the development of novel antimicrobial agents has become an urgent issue to be addressed. Antimicrobial peptides( AMPs), which possess unique mechanisms of action and are less prone to inducing bacterial resistance, have emerged as important candidates for replacing traditional antibiotics. Traditional experimental screening methods are time-consuming and costly, severely hindering the discovery of natural AMPs. In recent years, the integration of metagenomics and artificial intelligence has opened new avenues for efficiently mining AMPs from large-scale environmental and microbiome datasets. This review summarizes the characteristics of AMPs, relevant databases, and experimental validation approaches, and reviews computational identification strategies, including traditional machine learning, deep learning, protein language models, and transfer learning. We also discuss the application of multi-model hybrid strategies in metagenomics data analysis. Current challenges include insufficient high-quality annotated data and difficulties in high-throughput validation. However, continued advances in artificial intelligence and multi-omics technologies are expected to enable intelligent and precise identification of AMPs, thereby accelerating the discovery and clinical translation of highly effective candidate molecules and offering effective solutions to the resistance crisis.
Alanzi A R,2024.Exploring microbial dark matter for the discovery of novel natural products:characteristics,abundance challenges and methods[J].J.Microbiol.Biotechnol.,35:e2407064.
Anwer F,Navid A,Faiz F,et al.,2024.Ab AMPdb:a database of Acinetobacter baumannii specific antimicrobial peptides[J].Database,2024:baae096.
Bartels E J H,Dekker D,Amiche M,2019.Dermaseptins,multifunctional antimicrobial peptides:a review of their pharmacology,effectivity,mechanism of action,and possible future directions[J].Front.Pharmacol.,10:1421.
Benfield A H,Henriques S T,2020.Mode-of-action of antimicrobial peptides:membrane disruption vs.intracellular mechanisms[J].Front.Med.Technol.,2:610997.
Benítez-Chao D F,León-Buitimea A,Lerma-Escalera J A,et al.,2021.Bacteriocins:an overview of antimicrobial,toxicity,and biosafety assessment by in vivo models[J].Front.Microbiol.,12:630695.
Bin Hafeez A,Jiang X K,Bergen P J,et al.,2021.Antimicrobial peptides:an update on classifications and databases[J].Int.J.Mol.Sci.,22(21):11691.
Boudza R,Bounou S,Segura-Garcia J,et al.,2026.Artificial intelligence as a catalyst for antimicrobial discovery:from predictive models to de novo design[J].Microorganisms,14(2):394.
Brandes N,Ofer D,Peleg Y,et al.,2022.Protein BERT:a universal deep-learning model of protein sequence and function[J].Bioinformatics,38(8):2102-2110.
Brizuela C A,Liu G,Stokes J M,et al.,2025.AI methods for antimicrobial peptides:progress and challenges[J].Microb.Biotechnol.,18(1):e70072.
Burdukiewicz M,Sidorczuk K,Rafacz D,et al.,2020.Proteomic screening for prediction and design of antimicrobial peptides with Amp Gram[J].Int.J.Mol.Sci.,21(12):4310.
Cai J X,Yan J L,Un C,et al.,2025.BERT-Am PEP60:a BERT-based transfer learning approach to predict the minimum inhibitory concentrations of antimicrobial peptides for Escherichia coli and Staphylococcus aureus[J].J.Chem.Inf.Model.,65(7):3186-3202.
Cascella M,Semeraro F,Montomoli J,et al.,2024.The breakthrough of large language models release for medical applications:1-year timeline and perspectives[J].J.Med.Syst.,48(1):22.
Chen B,Cheng X Y,Li P,et al.,2025.x Trimo PGLM:unified100-billion-parameter pretrained transformer for deciphering the language of proteins[J].Nat.Methods,22(5):1028-1039.
Chen I A,Chu K,Palaniappan K,et al.,2023.The IMG/M data management and analysis system v.7:content updates and new features[J].Nucleic Acids Res.,51 (D1):D723-D732.
Chen J W,Jia Y Y,Sun Y,et al.,2024.Global marine microbial diversity and its potential in bioprospecting[J].Nature,633(8029):371-379.
Chen Q W,Li S M,Huang L,et al.,2026.i AMP-Se E:an antimicrobial peptide recognition model based on ESM2 feature extraction and hybrid attention mechanisms[J].Peer J,14:e20978.
Coelho L P,Alves R,Del RíoÁR,et al.,2022.Towards the biogeography of prokaryotic genes[J].Nature,601(7892):252-256.
Dho M,Candian V,Tedeschi R,2023.Insect antimicrobial peptides:advancements,enhancements and new challenges[J].Antibiotics (Basel),12(6):952.
Di Luca M,Maccari G,Maisetta G,et al.,2015.Ba AMPs:the database of biofilm-active antimicrobial peptides[J].Biofouling,31(2):193-199.
Dong R H,Cao Q S,Song C,2025.Painting peptides with antimicrobial potency through deep reinforcement learning[J].Adv.Sci.,12(43):e06332.
Du R B,Li X,Xu Y,et al.,2026.Metagenomics reveals potential antimicrobial peptides in Chinese Baijiu fermentation[J].Food Microbiol.,134:104918.
Du Z J,Caragea D,Guo X L,et al.,2025.Pep BERT:lightweight language models for bioactive peptide representation[PP/OL].bio Rxiv (2025-07-04)[2026-06-30].https://doi.org/10.1101/2025.04.08.647838.
Elnaggar A,Heinzinger M,Dallago C,et al.,2022.Prot Trans:toward understanding the language of life through selfsupervised learning[J].IEEE Trans.Pattern Anal.Mach.Intell.,44(10):7112-7127.
Fan S,Lu J,Cui H,et al.,2026.Unlocking the unexplored AMPSphere in marine rare species[J].Microbiome,14(1):100.
Fingerhut L C H W,Miller D J,Strugnell J M,et al.,2021.Ampir:an R package for fast genome-wide prediction of antimicrobial peptides[J].Bioinformatics,36 (21):5262-5263.
Georgoulis E,Zervou M A,Pantazis Y,2025.Transfer learning on protein language models improves antimicrobial peptide classification[J].Sci.Rep.,15:37456.
Grafskaia E,Pavlova E,Babenko V V,et al.,2020.The Hirudo medicinalis microbiome is a source of new antimicrobial peptides[J].Int.J.Mol.Sci.,21(19):7141.
Hayes T,Rao R,Akin H,et al.,2025.Simulating 500 million years of evolution with a language model[J].Science,387(6736):850-858.
Heinzinger M,Weissenow K,Sanchez J G,et al.,2024.Bilingual language model for protein sequence and structure[J].NAR Genom.Bioinform.,6(4):lqae150.
Ibisanmi T A,Jiang X T,Willcox M,et al.,2026.Recent advances in computational antimicrobial peptide discovery through big data,modeling,and artificial intelligence and their interplay in ushering the next golden era of drug development[J].Front.Bioinform.,6:1749404.
Jiang P Z,Liang Z J,Kovacevic V,et al.,2026.The Extreme Environment Microbiome Catalog (EEMC):a global resource for microbial diversity and antimicrobial discovery[J].Nat.Commun.,17(1):4791.
Jiang Q Y,Han Y C,Ye C Y,et al.,2025.A global deep-sea small protein atlas reveals a reservoir of noncanonical antimicrobial peptides[PP/OL].bio Rxiv (2025-12-16)[2026-06-30].https://doi.org/10.64898/2025.12.15.694180.
Kang Z X,Zhang H H,Zhou Q Z,et al.,2025.AI-driven discovery and optimization of antimicrobial peptides from extreme environments on global scale[PP/OL].bio Rxiv(2025-11-26)[2026-06-30].https://doi.org/10.1101/2025.11.13.688364.
Kłodzińska S N,Esposito T V F,Agnoletti M,et al.,2025.Nanogel encapsulation improves pharmacokinetics and biodistribution of antimicrobial peptide LL37 upon lung deposition:In vivo evaluation by SPECT/CT[J].J.Control.Release,383:113817.
Kumar P,Kizhakkedathu J N,Straus S K,2018.Antimicrobial peptides:diversity,mechanism of action and strategies to improve the activity and biocompatibility in vivo[J].Biomolecules,8(1):4.
Kumar R,2025.Expanding horizon of antimicrobial peptides:mechanistic complexity and biomedical potential[J].Explor.Drug Sci.,3:1008135.
Kundu R,2020.Cationic amphiphilic peptides:synthetic antimicrobial agents inspired by nature[J].Chem Med Chem,15(20):1887-1896.
Lawrence T J,Carper D L,Spangler M K,et al.,2021.am PEP-py 1.0:a portable and accurate antimicrobial peptide prediction tool[J].Bioinformatics,37(14):2058-2060.
Lee H,Lee S,Lee I,et al.,2023.AMP-BERT:prediction of antimicrobial peptide function based on a BERT model[J].Protein Sci.,32(1):e4529.
Li C K,Warren R L,Birol I,2023a.Models and data of AMPlify:a deep learning tool for antimicrobial peptide prediction[J].BMC Res.Notes,16(1):11.
Li H X,Niu J H,Wang X L,et al.,2023b.The contribution of antimicrobial peptides to immune cell function:a review of recent advances[J].Pharmaceutics,15(9):2278.
Li J P,Hu S P,Jian W,et al.,2021.Plant antimicrobial peptides:structures,functions,and applications[J].Bot.Stud.,62(1):5.
Li T T,Ren X B,Luo X L,et al.,2024.A foundation model identifies broad-spectrum antimicrobial peptides against drugresistant bacterial infection[J].Nat.Commun.,15 (1):7538.
Li W H,Zhu G Y,Zubair M,et al.,2025.Deep learning-driven discovery of novel antimicrobial peptides from large-scale protist genomes and experimental characterization[J].J.Chem.Inf.Model.,65(19):9962-9973.
Lin Z M,Akin H,Rao R,et al.,2023.Evolutionary-scale prediction of atomic-level protein structure with a language model[J].Science,379(6637):1123-1130.
Liu C,Wang X H,Zhang Z L,et al.,2026.GMrepo v3:a curated human gut microbiome database with expanded disease coverage and enhanced cross-dataset biomarker analysis[J].Nucleic Acids Res.,54(D1):D734-D742.
Lv J,Liu G X,Zhou X R,et al.,2026.Artificial intelligencedriven antimicrobial peptide discovery:prediction,generation,mining and optimization[PP/OL].Probiotics Antimicrob.Prot.(2026-04-22)[2026-06-30].https://doi.org/10.1007/s12602-026-11013-x.
Ma T Y,Liu Y C,Yu B X,et al.,2025.DRAMP 4.0:an openaccess data repository dedicated to the clinical translation of antimicrobial peptides[J].Nucleic Acids Res.,53(D1):D403-D410.
Ma Y,Guo Z Y,Xia B B,et al.,2022.Identification of antimicrobial peptides from the human gut microbiome using deep learning[J].Nat.Biotechnol.,40(6):921-931.
Medina-Ortiz D,Contreras S,Fernández D,et al.,2024.Protein language models and machine learning facilitate the identification of antimicrobial peptides[J].Int.J.Mol.Sci.,25(16):8851.
Meher P K,Sahu T K,Saini V,et al.,2017.Predicting antimicrobial peptides with improved accuracy by incorporating the compositional,physico-chemical and structural features into Chou′s general Pse AAC[J].Sci.Rep.,7:42362.
Mejía-Pitta A,Broset E,de la Fuente-Nunez C,2021.Probiotic engineering strategies for the heterologous production of antimicrobial peptides[J].Adv.Drug Deliv.Rev.,176:113863.
Meng H L,2026.AI-driven discovery and design of antimicrobial peptides:progress,challenges,and opportunities[J].Probiotics Antimicrob.Proteins,18:5122-5144.
Musin K,Asyanova E,2025.How machine learning helps in combating antimicrobial resistance:a review of AMP analysis and generation methods[J].Int.J.Pept.Res.Ther.,31(4):59.
Mwangi J,Hao X,Lai R,et al.,2019.Antimicrobial peptides:new hope in the war against multidrug resistance[J].Zool.Res.,40(6):488-505.
Nayar G,Tartici A,Altman R B,2025.Paying attention to attention:high attention sites as indicators of protein family and function in language models[J].PLo S Comput.Biol.,21(9):e1013424.
Niu T L,Zhu Y M,Mou M J,et al.,2025.Identification of natural product-based drug combination (NPDC) using artificial intelligence[J].Chin.J.Nat.Med.,23(11):1377-1390.
Parks D H,Chaumeil P A,Mussig A J,et al.,2026.GTDB release 10:a complete and systematic taxonomy for 715 230bacterial and 17 245 archaeal genomes[J].Nucleic Acids Res.,54(D1):D743-D754.
Pimentel J P F,Quigua Orozco R M,de Rezende S B,et al.,2026.Harnessing AI for antimicrobial peptide innovation against multidrug resistance[J].JACS Au,6(2):678-690.
Pirtskhalava M,Amstrong A A,Grigolava M,et al.,2021.DBAASP v3:database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics[J].Nucleic Acids Res.,49 (D1):D288-D297.
Richardson L,Allen B,Baldi G,et al.,2023.MGnify:the microbiome sequence data analysis resource in 2023[J].Nucleic Acids Res.,51(D1):D753-D759.
Santos-Júnior C D,Pan S J,Zhao X M,et al.,2020.Macrel:antimicrobial peptide screening in genomes and metagenomes[J].Peer J,8:e10555.
Santos-Júnior C D,Torres M D T,Duan Y Q,et al.,2024.Discovery of antimicrobial peptides in the global microbiome with machine learning[J].Cell,187 (14):3761-3778.e16.
Seiad Ahmadnezhad R,Shams-Ghahfarokhi M,Jamzivar F,et al.,2025.Next-generation antifungal peptide discovery:the synergy of artificial intelligence and omics technologies[J].World J.Microbiol.Biotechnol.,41(12):456.
Shen H,Li Y R,Pi Q J,et al.,2025a.Unveiling novel antimicrobial peptides from the ruminant gastrointestinal microbiomes:a deep learning-driven approach yields an anti-MRSAcandidate[J].J.Adv.Res.,77:821-835.
Shen X T,Wang Y X,Zhang P,et al.,2025b.AI-driven discovery and design of antimicrobial peptides[J].Sci.China Technol.Sci.,68(12):2200205.
Sidorczuk K,Gagat P,Pietluch F,et al.,2022.Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data[J].Brief.Bioinform.,23 (5):bbac343.
Soltani S,Hammami R,Cotter P D,et al.,2021.Bacteriocins as a new generation of antimicrobials:toxicity aspects and regulations[J].FEMS Microbiol.Rev.,45(1):fuaa039.
Strandberg E,Wadhwani P,Ulrich A S,2021.Antibiotic potential and biophysical characterization of amphipathicβ-stranded[XZ]n peptides with alternating cationic and hydrophobic residues[J].Front.Med.Technol.,3:622096.
Sumpradit N,Wongkongkathep S,Malathum K,et al.,2021.Thailand′s national strategic plan on antimicrobial resistance:progress and challenges[J].Bull.World Health Organ.,99(9):661-673.
Sun S W,2025.Progress in the identification and design of novel antimicrobial peptides against pathogenic microorganisms[J].Probiotics Antimicrob.Proteins,17(2):918-936.
Sun Y,Chen Q,Fan G M,et al.,2026.gc Meta 2025:a global repository of metagenome-assembled genomes enabling crossecosystem microbial discovery and function research[J].Nucleic Acids Res.,54(D1):D724-D733.
Sun Z H,Xu J,Zhang Y M,et al.,2025.Multimodal geometric learning for antimicrobial peptide identification by leveraging alphafold2-predicted structures and surface features[J].Brief.Bioinform.,26(3):bbaf261.
Velásquez-Mejía L,Vidal-Limon A,Flores-Vargas G,et al.,2026.Reviewing the role of artificial intelligence in accelerating the development of novel antimicrobial peptides[J].J.Appl.Microbiol.,137(3):lxag036.
Veltri D,Kamath U,Shehu A,2018.Deep learning improves antimicrobial peptide recognition[J].Bioinformatics,34(16):2740-2747.
Verma D P,Tripathi A K,Thakur A K,2024.Innovative strategies and methodologies in antimicrobial peptide design[J].J.Funct.Biomater.,15(11):320.
Vernette C,Lecubin J,Sánchez P,et al.,2022.The Ocean Gene Atlas v2.0:online exploration of the biogeography and phylogeny of plankton genes[J].Nucleic Acids Res.,50(W1):W516-W526.
Wang B L,Lin P J,Zhong Y W,et al.,2025a.Explainable deep learning and virtual evolution identifies antimicrobial peptides with activity against multidrug-resistant human pathogens[J].Nat.Microbiol.,10(2):332-347.
Wang C K,Kaas Q,Chiche L,et al.,2008.Cy Base:a database of cyclic protein sequences and structures,with applications in protein discovery and engineering[J].Nucleic Acids Res.,36(Database issue):D206-D210.
Wang G S,Schmidt C,Li X,et al.,2026.APD6:the antimicrobial peptide database is expanded to promote research and development by deploying an unprecedented information pipeline[J].Nucleic Acids Res.,54(D1):D363-D374.
Wang X,Wu Z,Wang R,et al.,2024.Unipro Lcad:accurate identification of antimicrobial peptide by fusing multiple pretrained protein language models[J].Symmetry,16 (4):464.
Wang Y Y,Zhang Z Y,Gu M,et al.,2025b.Carboxymethyl chitosan hydrogel loaded with the antimicrobial peptide FK-13promotes healing of diabetic skin wounds by inhibiting infection and biofilm formation[J].ACS Appl.Polym.Mater.,7(17):11514-11526.
Wiegand I,Hilpert K,Hancock R E,2008.Agar and broth dilution methods to determine the minimal inhibitory concentration (MIC) of antimicrobial substances[J].Nat.Protoc.,3(2):163-175.
Wu K Y,Xu G X,Tian Y,et al.,2025.Synthesis and evaluation of aquatic antimicrobial peptides derived from marine metagenomes using a high-throughput screening approach[J].Mar.Drugs,23(4):178.
Xie C Z,Hong F T,Wei Y J,et al.,2026.Plant AMP:a finetuned protein large language model for plant antimicrobial peptide prediction[J].Plant Commun.,7(3):101625.
Xu C M,Han A P,Tian Y,et al.,2025.Based on computer simulation and experimental verification:mining and characterizing novel antimicrobial peptides from soil microbiome[J].Food Chem.,467:142275.
Xu D,Lu W Y,2020.Defensins:a double-edged sword in host immunity[J].Front.Immunol.,11:764.
Xu J Q,Xu X,Jiang Y H,et al.,2024.Waste to resource:mining antimicrobial peptides in sludge from metagenomes using machine learning[J].Environ.Int.,186:108574.
Xu L L,Xie H R,Qin S J,et al.,2026.Parameter-efficient finetuning methods for pretrained language models:a critical review and assessment[J].IEEE Trans.Pattern Anal.Mach.Intell.,48(6):6107-6126.
Yan K,Lv H W,Guo Y C,et al.,2023.s AMPpred-GAT:prediction of antimicrobial peptide by graph attention network and predicted peptide structure[J].Bioinformatics,39(1):btac715.
Yao L T,Guan J H,Xie P L,et al.,2025.db AMP 3.0:updated resource of antimicrobial activity and structural annotation of peptides in the post-pandemic era[J].Nucleic Acids Res.,53(D1):D364-D376.
Yu Q Z,Liu H B,Shi H M,et al.,2026.Uncovering evolutionarily remote and highly potent antimicrobial peptides with protein language models[J/OL].Nat.Biomed.Eng.,https://pubmed.ncbi.nlm.nih.gov/41776033/.
Zahid H,Maryam,Chong K T,et al.,2026.Peptide Net:an integrative deep learning framework for predicting diverse bioactive peptides using protein language model embeddings[J].J.Chem.Inf.Model.,66(5):2616-2626.
Zhang L,You J Q,Lv H X,et al.,2023.Black phosphorusrising star in the antibacterial materials[J].Int.J.Nanomed.,18:6563-6584.
Zhang Q Y,Chen X,Li B W,et al.,2022.A database of anticoronavirus peptides[J].Sci.Data,9(1):294.
基本信息:
DOI：10.13417/j.gab.045.000873
中图分类号:Q811.4;TP18
引用信息:
[1]牛培源,李丝,林冠宏,等.人工智能在宏基因组抗菌肽挖掘中的应用[J].基因组学与应用生物学,2026,45(04):873-886.DOI:10.13417/j.gab.045.000873.
基金信息:
湖北省自然科学基金项目(2026AFB006)资助
2026-07-14
2026-07-14
2026-07-14