Scholarlink

In developing countries, transboundary animal diseases pose serious threats to animal health, international trade, and food security, where animal agriculture is a major source of livelihood. Foot-and-Mouth Disease (FMD) is the foremost transboundary and highly contagious viral disease affecting all the cloven-hoofed animals, such as cattle, pigs, goats, sheep, wildlife, etc. The causative agent of FMD is a single-stranded positive-sense RNA virus (genus: Aphthovirus and family: Picornaviridae), which is highly prone to mutation. To date, more than 65 topotypes and numerous genetic lineages within the seven serotypes of the FMD virus have been reported. The dynamic nature of the FMD virus necessitates epidemiology at the molecular level, which is indispensable for understanding virus evolution and selection of an appropriate vaccine strain. Alternatively, FMD molecular epidemiology is crucial to implement its control strategy, which primarily deals with knowing the serotype, topotype, and lineage of the virus causing the outbreak. Traditional serological techniques and epidemiological tools, though effective, often have supply chain issues, are costly, time-consuming, and labor-intensive, require a biocontainment facility, and have limited applicability in large-scale surveillance. Thus, the use of Artificial Intelligence (AI) and Machine Learning (ML) in molecular epidemiology of the transboundary animal viruses has huge potential and has shown promising results in some viruses like FMD virus. In this chapter, the application and utility of AI/ML in molecular epidemiology of the FMD virus are shown with great detail. Such a computational platform utilizes sequence-based feature-trained learning algorithms for accurate and rapid prediction of FMD virus serotype/topotype/lineage, demonstrating how data-driven approaches can complement and enhance conventional methods. However, these approaches are highly dependent on the availability of high-quality, diverse, and representative genomic data. With the adoption of a sequence-based surveillance system, continued refinement, broader data integration, and increased accessibility, AI-driven molecular epidemiology holds the potential to transform disease control strategies, shifting from reactive responses to proactive, predictive, and precision-based disease management.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI/ML in Molecular Epidemiology of Transboundary Infectious Animal Virus with Special Reference to Foot-and-Mouth Disease

  • 章节

  • 发表日期：

    2026年

查看全文
  • Samarendra Das,
  • Bighneswar Barik,
  • Rajeev Ranjan,
  • Soumen Pal

摘要

In developing countries, transboundary animal diseases pose serious threats to animal health, international trade, and food security, where animal agriculture is a major source of livelihood. Foot-and-Mouth Disease (FMD) is the foremost transboundary and highly contagious viral disease affecting all the cloven-hoofed animals, such as cattle, pigs, goats, sheep, wildlife, etc. The causative agent of FMD is a single-stranded positive-sense RNA virus (genus: Aphthovirus and family: Picornaviridae), which is highly prone to mutation. To date, more than 65 topotypes and numerous genetic lineages within the seven serotypes of the FMD virus have been reported. The dynamic nature of the FMD virus necessitates epidemiology at the molecular level, which is indispensable for understanding virus evolution and selection of an appropriate vaccine strain. Alternatively, FMD molecular epidemiology is crucial to implement its control strategy, which primarily deals with knowing the serotype, topotype, and lineage of the virus causing the outbreak. Traditional serological techniques and epidemiological tools, though effective, often have supply chain issues, are costly, time-consuming, and labor-intensive, require a biocontainment facility, and have limited applicability in large-scale surveillance. Thus, the use of Artificial Intelligence (AI) and Machine Learning (ML) in molecular epidemiology of the transboundary animal viruses has huge potential and has shown promising results in some viruses like FMD virus. In this chapter, the application and utility of AI/ML in molecular epidemiology of the FMD virus are shown with great detail. Such a computational platform utilizes sequence-based feature-trained learning algorithms for accurate and rapid prediction of FMD virus serotype/topotype/lineage, demonstrating how data-driven approaches can complement and enhance conventional methods. However, these approaches are highly dependent on the availability of high-quality, diverse, and representative genomic data. With the adoption of a sequence-based surveillance system, continued refinement, broader data integration, and increased accessibility, AI-driven molecular epidemiology holds the potential to transform disease control strategies, shifting from reactive responses to proactive, predictive, and precision-based disease management.