Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning
ABSTRACT The control of porcine reproductive and respiratory syndrome (PRRS) remains a significant challenge due to the genetic and antigenic variability of the causative virus (PRRSV). Predominantly, PRRSV management includes using vaccines and live virus inoculations to confer immunity against PRR...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Society for Microbiology
2023-02-01
|
| Series: | Microbiology Spectrum |
| Subjects: | |
| Online Access: | https://journals.asm.org/doi/10.1128/spectrum.04085-22 |
| _version_ | 1811164409395937280 |
|---|---|
| author | Dennis N. Makau Cinta Prieto Francisco J. Martínez-Lobo I. A. D. Paploski Kimberly VanderWaal |
| author_facet | Dennis N. Makau Cinta Prieto Francisco J. Martínez-Lobo I. A. D. Paploski Kimberly VanderWaal |
| author_sort | Dennis N. Makau |
| collection | DOAJ |
| description | ABSTRACT The control of porcine reproductive and respiratory syndrome (PRRS) remains a significant challenge due to the genetic and antigenic variability of the causative virus (PRRSV). Predominantly, PRRSV management includes using vaccines and live virus inoculations to confer immunity against PRRSV on farms. While understanding cross-protection among strains is crucial for the continued success of these interventions, understanding how genetic diversity translates to antigenic diversity remains elusive. We developed machine learning algorithms to estimate antigenic distance in silico, based on genetic sequence data, and identify differences in specific amino acid sites associated with antigenic differences between viruses. First, we obtained antigenic distance estimates derived from serum neutralization assays cross-reacting PRRSV monospecific antisera with virus isolates from 27 PRRSV1 viruses circulating in Europe. Antigenic distances were weakly to moderately associated with ectodomain amino acid distance for open reading frames (ORFs) 2 to 4 (ρ < 0.2) and ORF5 (ρ = 0.3), respectively. Dividing the antigenic distance values at the median, we then categorized the sera-virus pairs into two levels: low and high antigenic distance (dissimilarity). In the machine learning models, we used amino acid distances in the ectodomains of ORFs 2 to 5 and site-wise amino acid differences between the viruses as potential predictors of antigenic dissimilarity. Using mixed-effect gradient boosting models, we estimated the antigenic distance (high versus low) between serum-virus pairs with an accuracy of 81% (95% confidence interval, 76 to 85%); sensitivity and specificity were 86% and 75%, respectively. We demonstrate that using sequence data we can estimate antigenic distance and potential cross-protection between PRRSV1 strains. IMPORTANCE Understanding cross-protection between cocirculating PRRSV1 strains is crucial to reducing losses associated with PRRS outbreaks on farms. While experimental studies to determine cross-protection are instrumental, these in vivo studies are not always practical or timely for the many cocirculating and emerging PRRSV strains. In this study, we demonstrate the ability to rapidly estimate potential immunologic cross-reaction between different PRRSV1 strains in silico using sequence data routinely collected by production systems. These models can provide fast turn-around information crucial for improving PRRS management decisions such as selecting vaccines/live virus inoculation to be used on farms and assessing the risk of outbreaks by emerging strains on farms previously exposed to certain PRRSV strains and vaccine development among others. |
| first_indexed | 2024-04-10T15:21:04Z |
| format | Article |
| id | doaj.art-f5d4fd2e89ad4075a6803b457b36b57c |
| institution | Directory Open Access Journal |
| issn | 2165-0497 |
| language | English |
| last_indexed | 2024-04-10T15:21:04Z |
| publishDate | 2023-02-01 |
| publisher | American Society for Microbiology |
| record_format | Article |
| series | Microbiology Spectrum |
| spelling | doaj.art-f5d4fd2e89ad4075a6803b457b36b57c2023-02-14T14:15:50ZengAmerican Society for MicrobiologyMicrobiology Spectrum2165-04972023-02-0111110.1128/spectrum.04085-22Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine LearningDennis N. Makau0Cinta Prieto1Francisco J. Martínez-Lobo2I. A. D. Paploski3Kimberly VanderWaal4Department of Veterinary Population Medicine, College of Veterinary Medicine, University of Minnesota, Minneapolis, USADepartamento de Sanidad Animal, Facultad de Veterinaria, Universidad Complutense de Madrid, Madrid, SpainDepartament de Ciència Animal, ETSEA-Universitat de Lleida, Lleida, SpainDepartment of Veterinary Population Medicine, College of Veterinary Medicine, University of Minnesota, Minneapolis, USADepartment of Veterinary Population Medicine, College of Veterinary Medicine, University of Minnesota, Minneapolis, USAABSTRACT The control of porcine reproductive and respiratory syndrome (PRRS) remains a significant challenge due to the genetic and antigenic variability of the causative virus (PRRSV). Predominantly, PRRSV management includes using vaccines and live virus inoculations to confer immunity against PRRSV on farms. While understanding cross-protection among strains is crucial for the continued success of these interventions, understanding how genetic diversity translates to antigenic diversity remains elusive. We developed machine learning algorithms to estimate antigenic distance in silico, based on genetic sequence data, and identify differences in specific amino acid sites associated with antigenic differences between viruses. First, we obtained antigenic distance estimates derived from serum neutralization assays cross-reacting PRRSV monospecific antisera with virus isolates from 27 PRRSV1 viruses circulating in Europe. Antigenic distances were weakly to moderately associated with ectodomain amino acid distance for open reading frames (ORFs) 2 to 4 (ρ < 0.2) and ORF5 (ρ = 0.3), respectively. Dividing the antigenic distance values at the median, we then categorized the sera-virus pairs into two levels: low and high antigenic distance (dissimilarity). In the machine learning models, we used amino acid distances in the ectodomains of ORFs 2 to 5 and site-wise amino acid differences between the viruses as potential predictors of antigenic dissimilarity. Using mixed-effect gradient boosting models, we estimated the antigenic distance (high versus low) between serum-virus pairs with an accuracy of 81% (95% confidence interval, 76 to 85%); sensitivity and specificity were 86% and 75%, respectively. We demonstrate that using sequence data we can estimate antigenic distance and potential cross-protection between PRRSV1 strains. IMPORTANCE Understanding cross-protection between cocirculating PRRSV1 strains is crucial to reducing losses associated with PRRS outbreaks on farms. While experimental studies to determine cross-protection are instrumental, these in vivo studies are not always practical or timely for the many cocirculating and emerging PRRSV strains. In this study, we demonstrate the ability to rapidly estimate potential immunologic cross-reaction between different PRRSV1 strains in silico using sequence data routinely collected by production systems. These models can provide fast turn-around information crucial for improving PRRS management decisions such as selecting vaccines/live virus inoculation to be used on farms and assessing the risk of outbreaks by emerging strains on farms previously exposed to certain PRRSV strains and vaccine development among others.https://journals.asm.org/doi/10.1128/spectrum.04085-22cross-protectionseroneutralizationimmunodominant sitesimmunogenicityimmune responsemachine learning |
| spellingShingle | Dennis N. Makau Cinta Prieto Francisco J. Martínez-Lobo I. A. D. Paploski Kimberly VanderWaal Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning Microbiology Spectrum cross-protection seroneutralization immunodominant sites immunogenicity immune response machine learning |
| title | Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning |
| title_full | Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning |
| title_fullStr | Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning |
| title_full_unstemmed | Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning |
| title_short | Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning |
| title_sort | predicting antigenic distance from genetic data for prrsv type 1 applications of machine learning |
| topic | cross-protection seroneutralization immunodominant sites immunogenicity immune response machine learning |
| url | https://journals.asm.org/doi/10.1128/spectrum.04085-22 |
| work_keys_str_mv | AT dennisnmakau predictingantigenicdistancefromgeneticdataforprrsvtype1applicationsofmachinelearning AT cintaprieto predictingantigenicdistancefromgeneticdataforprrsvtype1applicationsofmachinelearning AT franciscojmartinezlobo predictingantigenicdistancefromgeneticdataforprrsvtype1applicationsofmachinelearning AT iadpaploski predictingantigenicdistancefromgeneticdataforprrsvtype1applicationsofmachinelearning AT kimberlyvanderwaal predictingantigenicdistancefromgeneticdataforprrsvtype1applicationsofmachinelearning |