Development, study, and comparison of models of cross-immunity to the influenza virus using statistical methods and machine learning
- 作者: Asatryan M.N.1, Shmyr I.S.1, Timofeev B.I.1, Shcherbinin D.N.1, Agasaryan V.G.1, Timofeeva T.A.1, Ershov I.F.1, Gerasimuk E.R.1,2, Nozdracheva A.V.1, Semenenko T.A.1, Logunov D.Y.1, Gintsburg A.L.1
-
隶属关系:
- National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
- State University «Dubna»
- 期: 卷 69, 编号 4 (2024)
- 页面: 349-362
- 栏目: ORIGINAL RESEARCH
- URL: https://journal-vniispk.ru/0507-4088/article/view/265972
- DOI: https://doi.org/10.36233/0507-4088-250
- EDN: https://elibrary.ru/phejeu
- ID: 265972
如何引用文章
详细
Introduction. The World Health Organization considers the values of antibody titers in the hemagglutination inhibition assay as one of the most important criteria for assessing successful vaccination. Mathematical modeling of cross-immunity allows for identification on a real-time basis of new antigenic variants, which is of paramount importance for human health.
Materials and methods. This study uses statistical methods and machine learning techniques from simple to complex: logistic regression model, random forest method, and gradient boosting. The calculations used the AAindex matrices in parallel to the Hamming distance. The calculations were carried out with different types and values of antigenic escape thresholds, on four data sets. The results were compared using common binary classification metrics.
Results. Significant differentiation is shown depending on the data sets used. The best results were demonstrated by all three models for the forecast autumn season of 2022, which were preliminary trained on the February season of the same year (Auroc 0.934; 0.958; 0.956, respectively). The lowest results were obtained for the entire forecast year 2023, they were set up on data from two seasons of 2022 (Aucroc 0.614; 0.658; 0.775). The dependence of the results on the types of thresholds used and their values turned out to be insignificant. The additional use of AAindex matrices did not significantly improve the results of the models without introducing significant deterioration.
Conclusion. More complex models show better results. When developing cross-immunity models, testing on a variety of data sets is important to make strong claims about their prognostic robustness.
作者简介
Marina Asatryan
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
编辑信件的主要联系方式.
Email: masatryan@gamaleya.org
ORCID iD: 0000-0001-6273-8615
PhD (Med.), senior researcher epidemiological cybernetics group of the Epidemiology Department
俄罗斯联邦, 123098, MoscowIlya Shmyr
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: shmyris@gamaleya.org
ORCID iD: 0000-0002-8514-5174
researcher epidemiological cybernetics group of the Epidemiology Department
俄罗斯联邦, 123098, MoscowBoris Timofeev
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: timofeevbi@gamaleya.org
ORCID iD: 0000-0001-7425-0457
PhD (Phys.-Mat.), senior researcher D.I. Ivanovsky Institute of Virology Division
俄罗斯联邦, 123098, MoscowDmitrii Shcherbinin
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: shcherbinindn@gamaleya.org
ORCID iD: 0000-0002-8518-1669
PhD (Biol.), senior researcher, Department of Genetics and Molecular Biology of Bacteria
俄罗斯联邦, 123098, MoscowVaagn Agasaryan
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: agasaryanvg@gamaleya.org
ORCID iD: 0009-0009-3824-7061
researcher epidemiological cybernetics group of the Epidemiology Department
俄罗斯联邦, 123098, MoscowTatiana Timofeeva
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: timofeeva.tatyana@gamaleya.org
ORCID iD: 0000-0002-8991-8525
PhD (Biol.), head of laboratory D.I. Ivanovsky Institute of Virology Division
俄罗斯联邦, 123098, MoscowIvan Ershov
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: ershovif@gamaleya.org
ORCID iD: 0000-0002-3333-5347
researcher epidemiological cybernetics group of the Epidemiology Department
俄罗斯联邦, 123098, MoscowElita Gerasimuk
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya; State University «Dubna»
Email: ealita@mail.ru
ORCID iD: 0000-0002-7364-163X
PhD (Med.), Assoc. Prof.
俄罗斯联邦, 123098, Moscow; 141982, DubnaAnna Nozdracheva
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: nozdrachevaav@gamaleya.org
ORCID iD: 0000-0002-8521-1741
PhD (Med.), head of laboratory for non-specific prevention of infectious diseases, Department of Epidemiology
俄罗斯联邦, 123098, MoscowTatyana Semenenko
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: semenenko@gamaleya.org
ORCID iD: 0000-0002-6686-9011
D. Sci. (Med.), Prof., Full Member of RANS, chief researcher Department of Epidemiology
俄罗斯联邦, 123098, MoscowDenis Logunov
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: logunov@gamaleya.org
ORCID iD: 0000-0003-4035-6581
D. Sci. (Biol.), Full Member of RAS, Deputy Director for research
俄罗斯联邦, 123098, MoscowAleksander Gintsburg
National Research Center for Epidemiology and Microbiology named after Honorary Academician N.F. Gamaleya
Email: gintsburg@gamaleya.org
ORCID iD: 0000-0003-1769-5059
D. Sci. (Biol.), Prof., Full Member of RAS, Director
俄罗斯联邦, 123098, Moscow参考
- Walker P.J., Siddell S.G., Lefkowitz E.J., Mushegian A.R., Adriaenssens E.M., Alfenas-Zerbini P., et al. Recent changes to viruses taxonomy ratified by the International Committee on Taxonomy of Viruses. Arch. Virol. 2022; 167(11): 2429–40. https://doi.org/10.1007/s00705-022-05516-5
- Chen J., Li K., Rong H., Bilal K., Yang N., Li K. A disease diagnosis and treatment recommendation system based on big data mining and cloud computing. Inf. Sci. 2018; 435: 124–49. https://doi.org/10.1016/j.ins.2018.01.001
- Qiu J., Qiu T., Yang Y., Wu D., Cao Z. Incorporating structure context of HA protein to improve antigenicity calculation for influenza virus A/H3N2. Sci. Rep. 2016; 6: 31156. https://doi.org/10.1038/srep31156
- Asatryan M.N., Agasaryan V.G, Shcherbinin D.N., Timofeev B.I., Ershov I.F., Shmyr I.S., et al. Influenza IDE. Patent RF № 2020617965; 2020. (in Russian)
- Asatryan M.N., Timofeev B.I., Shmyr I.S., Khachatryan K.R., Shcherbinin D.N., Timofeeva T.A., et al. Mathematical model for assessing the level of cross-immunity between strains of influenza virus subtype H3N2. Voprosy virusologii. 2023; 68(3): 252–64. https://doi.org/10.36233/0507-4088-179 https://elibrary.ru/rexvea (in Russian)
- Nakai K., Kidera A., Kanehisa M. Cluster analysis of amino acid indices for prediction of protein structure and function. Protein Eng. 1988; 2(2): 93–100. https://doi.org/10.1093/protein/2.2.93
- Virology Research Services. The Hemagglutination Inhibition Assay; 2023. Available at: https://virologyresearchservices.com/2023/04/07/understanding-the-hai-assay/
- Spackman E., Sitaras I. Hemagglutination Inhibition Assay. In: Animal Influenza Virus. 2020; 11–28. Available at: https://link.springer.com/protocol/10.1007/978-1-0716-0346-8_2
- Kaufmann L., Syedbasha M., Vogt D., Hollenstein Y., Hartmann J., Linnik J.E., et al. An optimized Hemagglutination Inhibition (HI) assay to quantify influenza-specific antibody titers. J. Vis Exp. 2017; (130): 55833. https://doi.org/10.3791/55833
- Burnet F.M., Lush D. The action of certain surface active agents on viruses. Aust. J. Exp. Biol. Med. Sci. 1940; 18(2): 141–50.
- Bedford T., Suchard M.A., Lemey P., Dudas G., Gregory V., Hay A.J., et al. Integrating influenza antigenic dynamics with molecular evolution. Elife. 2014; 3: e01914. https://doi.org/10.7554/eLife.01914
- Anderson C.S., McCall P.R., Stern H.A., Yang H., Topham D.J. Antigenic cartography of H1N1 influenza viruses using sequence-based antigenic distance calculation. BMC Bioinformatics. 2018; 19(1): 51. https://doi.org/10.1186/s12859-018-2042-4
- Lee M.S., Chen J.S. Predicting antigenic variants of influenza A/H3N2 viruses. Emerg. Infect. Dis. 2004; 10(8): 1385–90. https://doi.org/10.3201/eid1008.040107
- MU 3.1.3490–17. The study of population immunity to influenza in the population of the Russian Federation: Methodological guidelines; 2017. (in Russian)
- Lin X., Lin F., Liang T., Ducatez M.F., Zanin M., Wong S.S. Antibody responsiveness to influenza: what drives it? Viruses. 2021; 13(7): 1400. https://doi.org/10.3390/v13071400
- Lees W.D., Moss D.S., Shepherd A.J. A computational analysis of the antigenic properties of haemagglutinin in influenza A H3N2. Bioinformatics. 2010; 26(11): 1403–8. https://doi.org/10.1093/bioinformatics/btq160
- Zhou X., Yin R., Kwoh C.K., Zheng J. A context-free encoding scheme of protein sequences for predicting antigenicity of diverse influenza A viruses. BMC Genomics. 2018; 19(Suppl. 10): 936. https://doi.org/10.1186/s12864-018-5282-9
- Peng Y., Wang D., Wang J., Li K., Tan Z., Shu Y., et al. A universal computational model for predicting antigenic variants of influenza A virus based on conserved antigenic structures. Sci. Rep. 2017; 7: 42051. https://doi.org/10.1038/srep42051
- Huang J.W., Yang J.M. Changed epitopes drive the antigenic drift for influenza A (H3N2) viruses. BMC Bioinformatics. 2011; 12(Suppl. 1): S31. https://doi.org/10.1186/1471-2105-12-S1-S31
- Tolles J., Meurer W.J. Logistic regression: relating patient characteristics to outcomes. JAMA. 2016; 316(5): 533–4. https://doi.org/10.1001/jama.2016.7653
- Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer; 2009.
- Zacour М., Ward В.J., Brewer A., Tang P., Boivin G., Li Y. Standardization of hemagglutination inhibition assay for influenza serology allows for high reproducibility between laboratories. Clin. Vaccine Immunol. 2016; 23(3): 236–42. https://doi.org/10.1128/CVI.00613-15
- Kilbourne E.D., ed. The Influenza Viruses and Influenza. New York, London: Academic Press; 1975.
- Yao Y., Li X., Liao B., Huang L., He P., Wang F., et al. Predicting influenza antigenicity from Hemagglutintin sequence data based on a joint random forest method. Sci. Rep. 2017; 7(1): 1545. https://doi.org/10.1038/s41598-017-01699-z
- Lee E.K., Tian H., Nakaya H.I. Antigenicity prediction and vaccine recommendation of human influenza virus A (H3N2) using convolutional neural networks. Hum. Vaccin. Immunother. 2020; 16(11): 2690–708. https://doi.org/10.1080/21645515.2020.1734397
- Shah S.A.W., Palomar D.P., Barr I., Poon L.L.M., Quadeer A.A., McKay M.R. Seasonal antigenic prediction of influenza A H3N2 using machine learning. Nat. Commun. 2024; 15(1): 3833. https://doi.org/10.21203/rs.3.rs-2924528/v1
- Wang P., Zhu W., Liao B., Cai L., Peng L., Yang J. Predicting influenza antigenicity by matrix completion with antigen and antiserum similarity. Front. Microbiol. 2018; 9: 2500. https://doi.org/10.3389/fmicb.2018.02500
- Huang L., Li X., Guo P., Yao Y., Liao B., Zhang W., et al. Matrix completion with side information and its applications in predicting the antigenicity of influenza viruses. Bioinformatics. 2017; 33(20): 3195–201. https://doi.org/ 10.1093/bioinformatics/btx390
- Liao Y.C., Lee M.S., Ko C.Y., Chao A.H. Bioinformatics models for predicting antigenic variants of influenza A/H3N2 virus. Bioinformatics. 2008; 24(4): 505–12. https://doi.org/10.1093/bioinformatics/btm638
- Yang J., Zhang T., Wan X.F. Sequence-based antigenic change prediction by a sparse learning method incorporating co-evolutionary information. PLoS One. 2014; 9(9): e106660. https://doi.org/10.1371/journal.pone.0106660
- Adabor E.S. A statistical analysis of antigenic similarity among influenza A (H3N2) viruses. Heliyon. 2021; 7(11): e08384. https://doi.org/10.1016/j.heliyon.2021.e08384
补充文件
