Machine Learning Prediction and Experimental Validation of Antigenic Drift in H3 Influenza A Viruses in Swine

Abstract

The antigenic diversity of influenza A viruses (IAV) circulating in swine challenges the development of effective vaccines, increasing zoonotic threat and pandemic potential. High-throughput sequencing technologies can quantify IAV genetic diversity, but there are no accurate approaches to adequately describe antigenic phenotypes. This study evaluated an ensemble of nonlinear regression models to estimate virus phenotype from genotype. Regression models were trained with a phenotypic data set of pairwise hemagglutination inhibition (HI) assays, using genetic sequence identity and pairwise amino acid mutations as predictor features. The model identified amino acid identity, ranked the relative importance of mutations in the hemagglutinin (HA) protein, and demonstrated good prediction accuracy. Four previously untested IAV strains were selected to experimentally validate model predictions by HI assays. Errors between predicted and measured distances of uncharacterized strains were 0.35, 0.61, 1.69, and 0.13 antigenic units. These empirically trained regression models can be used to estimate antigenic distances between different strains of IAV in swine by using sequence data. By ranking the importance of mutations in the HA, we provide criteria for identifying antigenically advanced IAV strains that may not be controlled by existing vaccines and can inform strain updates to vaccines to better control this pathogen. IMPORTANCE Influenza A viruses (IAV) in swine constitute a major economic burden to an important global agricultural sector, impact food security, and are a public health threat. Despite significant improvement in surveillance for IAV in swine over the past 10 years, sequence data have not been integrated into a systematic vaccine strain selection process for predicting antigenic phenotype and identifying determinants of antigenic drift. To overcome this, we developed nonlinear regression models that predict antigenic phenotype from genetic sequence data by training the model on hemagglutination inhibition assay results. We used these models to predict antigenic phenotype for previously uncharacterized IAV, ranked the importance of genetic features for antigenic phenotype, and experimentally validated our predictions. Our model predicted virus antigenic characteristics from genetic sequence data and provides a rapid and accurate method linking genetic sequence data to antigenic characteristics. This approach also provides support for public health by identifying viruses that are antigenically advanced from strains used as pandemic preparedness candidate vaccine viruses.

Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning

“…This effect on antigenic distance could be associated with the physical or chemical properties of the amino acid affecting protein folding or the effect of such differences on N -glycosylation. As for other viruses, mutations/substitutions in certain amino acid sites (also referred to as immunodominant sites) may result in changes in epitope structure or complete hiding of an epitope, hence limiting or impairing host immune response and translating to a change in immunogenic phenotype ( 46 , 64 – 68 ). For PRRSV, although the ectodomains have been documented to present epitope binding sites, characterization of the role of amino acid substitutions in specific sites in immune response, especially for PRRSV1, has not been exhaustive.…”

“…As such, genetic differences within the HA gene are generally considered responsible for the differences in antigenic phenotypes between viral strains (simply described as antigenic distances between viruses) ( 45 ). Outputs from such HI/cross-reactivity assays have been used to develop in silico predictive models combining sequence data and machine learning algorithms to predict antigenic differences among viruses ( 46 , 47 ). Genomic differences between PRRSV and influenzas notwithstanding, similar cross-reactivity data from SN assays can be combined with machine learning algorithms and sequence data for already characterized genes of PRRSV to estimate the antigenic distance between viruses.…”

Evidence of influenza A infection and risk of transmission between pigs and farmworkers

“…Clade classification for each segment was done using the automated classification tool OctoFLU (Chang et al, 2019) (Zeller et al, 2021).…”

Machine learning in handling disease outbreaks: a comprehensive review

“…Over the past two decades, 2020 was the most prolific publication year on this topic, with 33 articles from a total of 96 articles. Most of the articles discussed machine learning and deep learning approach to predict and forecast virus spread [95], the likelihood of vaccinated patients [96], and the vaccine effectiveness [97]. The rest articles discussed the classification of tropism protein signature for influenza virus identification [98], classification of symptoms for diagnosis of suspected people [99], and early warning detection of infected patients [100].…”