Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 22;25(2):bbae033.
doi: 10.1093/bib/bbae033.

PREDAC-CNN: predicting antigenic clusters of seasonal influenza A viruses with convolutional neural network

Jing Meng  1 , Jingze Liu  1 , Wenkai Song  2 , Honglei Li  3 , Jiangyuan Wang  4 , Le Zhang  2 , Yousong Peng  5 , Aiping Wu  1 , Taijiao Jiang  1   4   6
Affiliations

PREDAC-CNN: predicting antigenic clusters of seasonal influenza A viruses with convolutional neural network

Jing Meng et al. Brief Bioinform. .

Abstract

Vaccination stands as the most effective and economical strategy for prevention and control of influenza. The primary target of neutralizing antibodies is the surface antigen hemagglutinin (HA). However, ongoing mutations in the HA sequence result in antigenic drift. The success of a vaccine is contingent on its antigenic congruence with circulating strains. Thus, predicting antigenic variants and deducing antigenic clusters of influenza viruses are pivotal for recommendation of vaccine strains. The antigenicity of influenza A viruses is determined by the interplay of amino acids in the HA1 sequence. In this study, we exploit the ability of convolutional neural networks (CNNs) to extract spatial feature representations in the convolutional layers, which can discern interactions between amino acid sites. We introduce PREDAC-CNN, a model designed to track antigenic evolution of seasonal influenza A viruses. Accessible at http://predac-cnn.cloudna.cn, PREDAC-CNN formulates a spatially oriented representation of the HA1 sequence, optimized for the convolutional framework. It effectively probes interactions among amino acid sites in the HA1 sequence. Also, PREDAC-CNN focuses exclusively on physicochemical attributes crucial for the antigenicity of influenza viruses, thereby eliminating unnecessary amino acid embeddings. Together, PREDAC-CNN is adept at capturing interactions of amino acid sites within the HA1 sequence and examining the collective impact of point mutations on antigenic variation. Through 5-fold cross-validation and retrospective testing, PREDAC-CNN has shown superior performance in predicting antigenic variants compared to its counterparts. Additionally, PREDAC-CNN has been instrumental in identifying predominant antigenic clusters for A/H3N2 (1968-2023) and A/H1N1 (1977-2023) viruses, significantly aiding in vaccine strain recommendation.

Keywords: HA sequence; antigenic cluster; antigenic variant; convolutional neural network; seasonal influenza A viruses.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Overview of PREDAC-CNN. In the first step, PREDAC-CNN takes paired HA1 sequences from influenza A/H3N2 or A/H1N1 viruses as input. It generates an input matrix that corresponds to the paired HA1 sequences (sequence 1 and sequence 2) by encoding selected physicochemical features of amino acids using the feature dictionary. Subsequently, PREDAC-CNN utilizes the CNN model to assess the input matrix and infer the antigenic relationship between the paired strains of influenza A/H3N2 or A/H1N1 viruses. In the second step, PREDAC-CNN connects strains exhibiting similar antigenicity to construct an antigenic correlation network and performs antigenic clustering using the MCL method.
Figure 2
Figure 2
ROC curves for 5-fold cross-validations of PREDAC-CNN and four machine learning models with four feature encodings. ROC curves for feature encoding of 7-features (A), AAindex-PCA (B), ESM-2 (C) and iFeatureOmega (D) on influenza A/H3N2 viruses. ROC curves for feature encoding of 7-features (E), AAindex-PCA (F), ESM-2 (G) and iFeatureOmega (H) on influenza A/H1N1 viruses.
Figure 3
Figure 3
PRROC curves for retrospective testing of PREDAC-CNN and four machine learning models with four feature encodings. PRROC curves for feature encoding of 7-features (A), AAindex-PCA (B), ESM-2 (C) and iFeatureOmega (D) on influenza A/H3N2 viruses. PRROC curves for feature encoding of 7-features (E), AAindex-PCA (F), ESM-2 (G) and iFeatureOmega (H) on influenza A/H1N1 viruses.
Figure 4
Figure 4
ROC curves for 5-fold cross-validations of PREDAC-CNN and its five competitors. ROC curves on influenza A/H3N2 viruses (A) and influenza A/H1N1 viruses (B).
Figure 5
Figure 5
PRROC curves for retrospective testing of PREDAC-CNN and its five competitors. PRROC curves on influenza A/H3N2 viruses (A) and influenza A/H1N1 viruses (B).
Figure 6
Figure 6
Genetic and antigenic evolution of influenza A/H3N2 viruses. The left panel illustrates genetic evolution, with WHO-recommended vaccine strains denoted by five-pointed stars. The right panel shows antigenic evolution, with antigenic clusters named after abbreviations of the WHO-recommended earliest vaccine strains included in the clusters.
Figure 7
Figure 7
Genetic and antigenic evolution of influenza A/H1N1 viruses. The left panel illustrates genetic evolution, with WHO-recommended vaccine strains denoted by five-pointed stars. The right panel shows antigenic evolution, with antigenic clusters named after abbreviations of the WHO-recommended earliest vaccine strains included in the clusters.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Influenza Fact Sheet WHO. https://www.who.int/en/news-room/fact-sheets/detail/influenza-(seasonal).
    1. Virelizier J-L. Host defenses against influenza virus: the role of anti-hemagglutinin antibody. J Immunol 1975;115:434–9. - PubMed
    1. Cox NJ, Lynnette Brammer T, Regnery HL. Influenza: global surveillance for epidemic and pandemic variants. Eur J Epidemiol 1994;10:467–70. - PubMed
    1. Rolfes MA, Flannery B, Chung JR, et al. Effects of influenza vaccination in the United States during the 2017–2018 influenza season. Clin Infect Dis 2019;69:1845–53. - PMC - PubMed
    1. Chung JR, Rolfes MA, Flannery B, et al. Effects of influenza vaccination in the United States during the 2018–2019 influenza season. Clin Infect Dis 2020;71:e368–76. - PMC - PubMed

MeSH terms