陆军军医大学(第三军医大学)药学与检验医学系国家免疫生物制品工程技术研究中心,重庆
Received:09 December 2025,
Revised:2026-01-14,
Accepted:20 January 2026,
Published:28 February 2026
移动端阅览
顾江,李宇航.人工智能重塑疫苗研发新范式:效率革命与精准设计[J].陆军军医大学学报,2026,48(04):387-393.DOI:10.16016/j.2097-0927.202512040.
GU J,LI Y H.Artificial intelligence reshaping vaccine development: a new paradigm of efficiency revolution and precision design[J].J Army Med Univ,2026,48(04):387-393.DOI:10.16016/j.2097-0927.202512040.
顾江,李宇航.人工智能重塑疫苗研发新范式:效率革命与精准设计[J].陆军军医大学学报,2026,48(04):387-393.DOI:10.16016/j.2097-0927.202512040. DOI:
GU J,LI Y H.Artificial intelligence reshaping vaccine development: a new paradigm of efficiency revolution and precision design[J].J Army Med Univ,2026,48(04):387-393.DOI:10.16016/j.2097-0927.202512040. DOI:
人工智能(artificial intelligence, AI)通过整合深度学习架构与多组学数据,正在系统性地重塑疫苗研发全链条,推动其从传统依赖试错的“经验驱动”模式,向以“数据驱动”和“算法生成”为核心的理性设计新范式转型。尽管面临数据异质性、模型“黑箱”、算法偏见以及监管框架滞后等多重挑战,AI技术通过与免疫机理的深度结合,推动疫苗设计从“结构模拟”向“功能创造”跨越,为疫苗研发提供了全新范式。本综述系统梳理了AI在疫苗研发多个关键环节的创新应用与典型进展,包括疫苗靶标挖掘、抗原设计、疫苗佐剂、工艺开发、临床试验、疫苗犹豫等,尤其汇总了近年来用于疫苗理性设计的相关工具、核心架构、主要特点和典型案例,为后续疫苗开发中AI技术的应用提供借鉴。
Artificial intelligence (AI) is systematically reshaping the entire vaccine research and development pipeline through integrating deep learning architectures with multi-omics data. This facilitates a paradigm shift from traditional trial-and-error empirical approaches to a novel rational design framework centered on
data
-
driven
and
algorithm
-
generated
methodologies. Despite challenges including data heterogeneity
model opacity
algorithmic bias
and lagging regulatory frameworks
AI enables a transformative leap from
structural mimicry
to
functional innovation
in vaccine design
via
deep integration with immunological mechanisms. This review comprehensively analyzes AI applications across key vaccine development stages: target identification
antigen design
adjuvant screening
process optimization
clinical trial design
and vaccine hesitancy mitigation. We particularly summarize recent tools
core architectures
functional features
and representative cases for AI-powered rational vaccine design
providing actionable references for future AI implementation in vaccinology.
PRONKER E S , WEENEN T C , COMMANDEUR H , et al . Risk in vaccine research and development quantified [J]. PLoS One , 2013 , 8 ( 3 ): e57755 . DOI: 10.1371/journal.pone.0057755 http://dx.doi.org/10.1371/journal.pone.0057755 .
PARK J , BARTZOKA F , VON BECK T , et al . Molecular features of the serological IgG repertoire elicited by egg-based, cell-based, or recombinant haemagglutinin-based seasonal influenza vaccines: a comparative, prospective, observational cohort study [J]. Lancet Microbe , 2025 , 6 ( 2 ): 100935 . DOI: 10.1016/j.lanmic.2024.06.002 http://dx.doi.org/10.1016/j.lanmic.2024.06.002 .
KWONG P D , MASCOLA J R . HIV-1 vaccines based on antibody identification, B cell ontogeny, and epitope structure [J]. Immunity , 2018 , 48 ( 5 ): 855 - 871 . DOI: 10.1016/j.immuni.2018.04.029 http://dx.doi.org/10.1016/j.immuni.2018.04.029 .
VILLANUEVA-FLORES F , SANCHEZ-VILLAMIL J I , GARCIA-ATUTXA I . AI-driven epitope prediction: a system review, comparative analysis, and practical guide for vaccine development [J]. NPJ Vaccines , 2025 , 10 ( 1 ): 207 . DOI: 10.1038/s41541-025-01258-y http://dx.doi.org/10.1038/s41541-025-01258-y .
ZHANG L , SONG W K , ZHU T H , et al . ConvNeXt-MHC: improving MHC-peptide affinity prediction by structure-derived degenerate coding and the ConvNeXt model [J]. Brief Bioinform , 2024 , 25 ( 3 ): bbae133 . DOI: 10.1093/bib/bbae133 http://dx.doi.org/10.1093/bib/bbae133 .
SHUJAAT M , KIM H , TAYARA H , et al . iProm-Sigma54: a CNN base prediction tool for σ(54) promoters [J]. Cells , 2023 , 12 ( 6 ): 829 . DOI: 10.3390/cells12060829 http://dx.doi.org/10.3390/cells12060829 .
HAO Q , WEI P , SHU Y , et al . Improvement of neoantigen identification through convolution neural network [J]. Front Immunol , 2021 , 12 : 682103 . DOI: 10.3389/fimmu. 2021. 682103 http://dx.doi.org/10.3389/fimmu.2021.682103 .
QUE J H , XUE G F , WANG T , et al . Identifying T cell antigen at the atomic level with graph convolutional network [J]. Nat Commun , 2025 , 16 ( 1 ): 5171 . DOI: 10.1038/s41467-025-60461-6 http://dx.doi.org/10.1038/s41467-025-60461-6 .
LI G Y , IYER B , SURYA PRASATH V B , et al . DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity [J]. Brief Bioinform , 2021 , 22 ( 6 ): bbab160 . DOI: 10.1093/bib/bbab160 http://dx.doi.org/10.1093/bib/bbab160 .
SHAO X M , BHATTACHARYA R , HUANG J , et al . High-throughput prediction of MHC class I and II neoantigens with MHCnuggets [J]. Cancer Immunol Res , 2020 , 8 ( 3 ): 396 - 408 . DOI: 10.1158/2326-6066.CIR-19-0464 http://dx.doi.org/10.1158/2326-6066.CIR-19-0464 .
CHENG J , BENDJAMA K , RITTNER K , et al . BERTMHC: improved MHC-peptide class II interaction prediction with transformer and multiple instance learning [J]. Bioinformatics , 2021 , 37 ( 22 ): 4172 - 4179 . DOI: 10.1093/bioinformatics/btab422 http://dx.doi.org/10.1093/bioinformatics/btab422 .
ZENG Y S , WEI Z Y , YUAN Q M , et al . Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model [J]. Bioinformatics , 2023 , 39 ( 4 ): btad187 . DOI: 10.1093/bioinformatics/btad187 http://dx.doi.org/10.1093/bioinformatics/btad187 .
HU R S , GU K , EHSAN M , et al . Transformer-based deep learning enables improved B-cell epitope prediction in parasitic pathogens: a proof-of-concept study on Fasciola hepatica [J]. PLoS Negl Trop Dis , 2025 , 19 ( 4 ): e0012985 . DOI: 10.1371/journal.pntd.0012985 http://dx.doi.org/10.1371/journal.pntd.0012985 .
ALBERT B A , YANG Y X , SHAO X M , et al . Deep neural networks predict class I major histocompatibility complex epitope presentation and transfer learn neoepitope immunogenicity [J]. Nat Mach Intell , 2023 , 5 ( 8 ): 861 - 872 . DOI: 10.1038/s42256-023-00694-6 http://dx.doi.org/10.1038/s42256-023-00694-6 .
SHANTHAPPA P M , VERMA N , GEORGE A , et al . Computational prediction of potential vaccine candidates from tRNA encoded peptides (tREP) using a bioinformatic workflow and molecular dynamics validations [J]. IEEE/ACM Trans Comput Biol Bioinform , 2024 , 21 ( 3 ): 439 - 449 . DOI: 10.1109/TCBB.2024.3371984 http://dx.doi.org/10.1109/TCBB.2024.3371984 .
SCHAUPERL M , DENNY R A . AI-based protein structure prediction in drug discovery: impacts and challenges [J]. J Chem Inf Model , 2022 , 62 ( 13 ): 3142 - 3156 . DOI: 10.1021/acs.jcim.2c00026 http://dx.doi.org/10.1021/acs.jcim.2c00026 .
NAVARRO S , VENTURA S . Computational methods to predict protein aggregation [J]. Curr Opin Struct Biol , 2022 , 73 : 102343 . DOI: 10.1016/j.sbi.2022.102343 http://dx.doi.org/10.1016/j.sbi.2022.102343 .
JISNA V A , JAYARAJ P B . Protein structure prediction: conventional and deep learning perspectives [J]. Protein J , 2021 , 40 ( 4 ): 522 - 544 . DOI: 10.1007/s10930-021-10003-y http://dx.doi.org/10.1007/s10930-021-10003-y .
VALANCIUTE A , NYGAARD L , ZSCHACH H , et al . Accurate protein stability predictions from homology models [J]. Comput Struct Biotechnol J , 2022 , 21 : 66 - 73 . DOI: 10.1016/j.csbj.2022.11.048 http://dx.doi.org/10.1016/j.csbj.2022.11.048 .
ALQURAISHI M . Protein-structure prediction revolutionized [J]. Nature , 2021 , 596 ( 7873 ): 487 - 488 . DOI: 10.1038/d41586-021-02265-4 http://dx.doi.org/10.1038/d41586-021-02265-4 .
JUMPER J , EVANS R , PRITZEL A , et al . Highly accurate protein structure prediction with AlphaFold [J]. Nature , 2021 , 596 ( 7873 ): 583 - 589 . DOI: 10.1038/s41586-021-03819-2 http://dx.doi.org/10.1038/s41586-021-03819-2 .
DOBSON L , SZEKERES L I , GERDÁN C , et al . TmAlphaFold database: membrane localization and evaluation of AlphaFold2 predicted alpha-helical transmembrane protein structures [J]. Nucleic Acids Res , 2023 , 51 ( D1 ): D517 - D522 . DOI: 10.1093/nar/gkac928 DOI:10.1093/nar/gkac928 http://dx.doi.org/10.1093/nar/gkac928DOI:10.1093/nar/gkac928 .
LIU Z , PAN W H , LI W H , et al . Evaluation of the effectiveness of derived features of AlphaFold2 on single-sequence protein binding site prediction [J]. Biology , 2022 , 11 ( 10 ): 1454 . DOI: 10.3390/biology11101454 http://dx.doi.org/10.3390/biology11101454 .
VARADI M , ANYANGO S , DESHPANDE M , et al . AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models [J]. Nucleic Acids Res , 2022 , 50 ( D1 ): D439 - D444 . DOI: 10.1093/nar/gkab1061 http://dx.doi.org/10.1093/nar/gkab1061 .
CARBALLO G M , VÁZQUEZ K G , GARCÍA-GONZÁLEZ L A , et al . Embedded-AMP: a multi-thread computational method for the systematic identification of antimicrobial peptides embedded in proteome sequences [J]. Antibiotics , 2023 , 12 ( 1 ): 139 . DOI: 10.3390/antibiotics12010139 http://dx.doi.org/10.3390/antibiotics12010139 .
ZHANG H C , SHEN Y F . Template-based prediction of protein structure with deep learning [J]. BMC Genomics , 2020 , 21 ( Suppl 11 ): 878 . DOI: 10.1186/s12864-020-07249-8 http://dx.doi.org/10.1186/s12864-020-07249-8 .
CARUGO O , DJINOVIĆ-CARUGO K . Structural biology: a golden era [J]. PLoS Biol , 2023 , 21 ( 6 ): e3002187 . DOI: 10.1371/journal.pbio.3002187 http://dx.doi.org/10.1371/journal.pbio.3002187 .
SCALZITTI N , JEANNIN-GIRARDON A , COLLET P , et al . A benchmark study of ab initio gene prediction methods in diverse eukaryotic organisms [J]. BMC Genomics , 2020 , 21 ( 1 ): 293 . DOI: 10.1186/s12864-020-6707-9 http://dx.doi.org/10.1186/s12864-020-6707-9 .
MA X Y , LYU H Y , HAO K R , et al . High-efficient ab initio Bayesian active learning method and applications in prediction of two-dimensional functional materials [J]. Nanoscale , 2021 , 13 ( 35 ): 14694 - 14704 .
GREENER J G , KANDATHIL S M , JONES D T . Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints [J]. Nat Commun , 2019 , 10 ( 1 ): 3977 . DOI: 10.1038/s41467-019-11994-0 http://dx.doi.org/10.1038/s41467-019-11994-0 .
BAEK M , DIMAIO F , ANISHCHENKO I , et al . Accurate prediction of protein structures and interactions using a three-track neural network [J]. Science , 2021 , 373 ( 6557 ): 871 - 876 . DOI: 10.1126/science.abj8754 http://dx.doi.org/10.1126/science.abj8754 .
WANG W K , PENG Z L , YANG J Y . Single-sequence protein structure prediction using supervised transformer protein language models [J]. Nat Comput Sci , 2022 , 2 ( 12 ): 804 - 814 . DOI: 10.1038/s43588-022-00373-3 http://dx.doi.org/10.1038/s43588-022-00373-3 .
DEY S , GATES H , SALEHI R , et al . AstraMEV (AI-guided structural assembly of multi-epitope vaccines) against infectious bronchitis virus [J]. J Chem Inf Model , 2025 , 65 ( 21 ): 12068 - 12087 . DOI: 10.1021/acs.jcim.5c01809 http://dx.doi.org/10.1021/acs.jcim.5c01809 .
KUMAR A , DIXIT S , SRINIVASAN K , et al . Personalized cancer vaccine design using AI-powered technologies [J]. Front Immunol , 2024 , 15 : 1357217 . DOI: 10.3389/fimmu.2024.1357217 http://dx.doi.org/10.3389/fimmu.2024.1357217 .
LEE S , KIBLER R D , AHN G , et al . Four-component protein nanocages designed by programmed symmetry breaking [J]. Nature , 2025 , 638 ( 8050 ): 546 - 552 . DOI: 10.1038/s41586-024-07814-1 http://dx.doi.org/10.1038/s41586-024-07814-1 .
DOWLING Q M , PARK Y J , FRIES C N , et al . Hierarchical design of pseudosymmetric protein nanocages [J]. Nature , 2025 , 638 ( 8050 ): 553 - 561 . DOI: 10.1038/s41586-024-08360-6 http://dx.doi.org/10.1038/s41586-024-08360-6 .
HAAS C M , JASTI N , DOSEY A , et al . From sequence to scaffold: Computational design of protein nanoparticle vaccines from AlphaFold2-predicted building blocks [J]. Proc Natl Acad Sci USA , 2025 , 122 ( 45 ): e2409566122 . DOI: 10.1073/pnas.2409566122 http://dx.doi.org/10.1073/pnas.2409566122 .
IKHSANURAHMAN R Y , IKHSAN N , KURNIAWAN I . Classification of CDK2 inhibitor as anti-cancer agent by using simulated annealing-support vector machine methods [C]// 2022 International Conference on Data Science and Its Applications (ICoDSA) , Bandung : IEEE , 2022 : 82 - 86 . DOI: 10.1109/ICoDSA55874. 2022.9862929 http://dx.doi.org/10.1109/ICoDSA55874.2022.9862929 .
TIWARI P , ALI S A , PURI B , et al . Tinospora cordifolia Miers enhances the immune response in mice immunized with JEV-vaccine: a network pharmacology and experiment al approach [J]. Phytomedicine , 2023 , 119 : 154976 . DOI: 10.1016/j.phymed.2023.154976 http://dx.doi.org/10.1016/j.phymed.2023.154976 .
MA J , WANG S Q , ZHAO C F , et al . Computer-aided discovery of potent broad-spectrum vaccine adjuvants [J]. Angew Chem Int Ed , 2023 , 62 ( 18 ): e202301059 . DOI: 10.1002/anie.202301059 http://dx.doi.org/10.1002/anie.202301059 .
CUI Z , SHI C Y , AN R , et al . In silico-guided discovery of polysaccharide derivatives as adjuvants in nanoparticle vaccines for cancer immunotherapy [J]. ACS Nano , 2025 , 19 ( 2 ): 2099 - 2116 . DOI: 10.1021/acsnano.4c08898 http://dx.doi.org/10.1021/acsnano.4c08898 .
KHUAT T T , GABRYS B . Random hyperboxes [J]. IEEE Trans Neural Netw Learning Syst , 2023 , 34 ( 2 ): 1008 - 1022 . DOI: 10.1109/tnnls.2021.3104896 http://dx.doi.org/10.1109/tnnls.2021.3104896 .
PURI M , MIRANDA-HERNANDEZ S , SUBBIAN S , et al . Repurposing mucosal delivery devices for live attenuated tuberculosis vaccines [J]. Front Immunol , 2023 , 14 : 1159084 . DOI: 10.3389/fimmu.2023.1159084 http://dx.doi.org/10.3389/fimmu.2023.1159084 .
OLAWADE D B , WADA O J , DAVID-OLAWADE A C , et al . Using artificial intelligence to improve public health: a narrative review [J]. Front Public Health , 2023 , 11 : 1196397 . DOI: 10.3389/fpubh.2023.1196397 http://dx.doi.org/10.3389/fpubh.2023.1196397 .
ESMAEILZADEH P . Challenges and strategies for wide-scale artificial intelligence (AI) deployment in healthcare practices: a perspective for healthcare organizations [J]. Artif Intell Med , 2024 , 151 : 102861 . DOI: 10.1016/j.artmed.2024.102861 http://dx.doi.org/10.1016/j.artmed.2024.102861 .
WANG G P , ZHENG C J , LU M X , et al . Assessment of knowledge, attitudes, practices, and risk perceptions regarding COVID-19: a cross-sectional study from China [J]. J Public Health , 2024 , 32 ( 6 ): 943 - 953 . DOI: 10.1007/s10389-023-01877-6 http://dx.doi.org/10.1007/s10389-023-01877-6 .
FU L X , JIA G S , LIU Z M , et al . The applications and advances of artificial intelligence in drug regulation: a global perspective [J]. Acta Pharm Sin B , 2025 , 15 ( 1 ): 1 - 14 . DOI: 10.1016/j.apsb.2024.11.006 http://dx.doi.org/10.1016/j.apsb.2024.11.006 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621
