波克斯病毒科是一个大家庭,复杂,信封,和双链DNA病毒。这个家族的成员无处不在,众所周知,在人类和其他类型的动物中也会引起传染病。分类上,痘病毒科分为两个亚科,即毛虫科(影响脊椎动物)和昆虫科(影响昆虫)。根据基因组结构和进化关系,将Chordopoxvirinae亚科的成员进一步分为18个属。在这18个属中,四属,即软体动物痘病毒,正痘病毒,副痘病毒,和Yatapoxvirus,以感染人类而闻名。痘病毒科的一些流行成员是天花病毒,疫苗病毒,水痘(以前称为猴痘),牛痘,等。对于开发针对痘病毒的有效疫苗仍然存在迫切的需求。基于综合免疫信息学和人工智能(AI)的方法已成为设计针对传染性新兴传染病的多表位疫苗的重要方法。尽管免疫信息学和基于人工智能的技术取得了重大进展,有限的方法可用于预测表位。在这项研究中,我们提出了一种独特的方法来预测多种痘病毒的潜在抗原和T细胞表位。有了PoxiPred,我们开发了一种基于AI的工具,该工具经过了痘病毒抗原和表位的训练和测试。我们的工具能够从25种不同的痘病毒中找到3191种抗原蛋白。从这些抗原蛋白中,PoxiPred冗余定位每个蛋白质多达五个表位,产生16,817个潜在的T细胞表位,这些表位主要是(即,92%)预测为对CD8+T细胞有反应性。PoxiPred能够,在一次奔跑中,用一个单一输入鉴定痘病毒的抗原和T细胞表位,即,任何痘病毒的蛋白质组文件.
Poxviridae is a family of large, complex, enveloped, and double-stranded DNA viruses. The members of this family are ubiquitous and well known to cause contagious diseases in humans and other types of animals as well. Taxonomically, the
poxviridae family is classified into two subfamilies, namely Chordopoxvirinae (affecting vertebrates) and Entomopoxvirinae (affecting insects). The members of the Chordopoxvirinae subfamily are further divided into 18 genera based on the genome architecture and evolutionary relationship. Of these 18 genera, four genera, namely Molluscipoxvirus, Orthopoxvirus, Parapoxvirus, and Yatapoxvirus, are known for infecting humans. Some of the popular members of
poxviridae are variola virus, vaccine virus, Mpox (formerly known as monkeypox), cowpox, etc. There is still a pressing demand for the development of effective vaccines against poxviruses. Integrated immunoinformatics and artificial-intelligence (AI)-based methods have emerged as important approaches to design multi-epitope vaccines against contagious emerging infectious diseases. Despite significant progress in immunoinformatics and AI-based techniques, limited methods are available to predict the epitopes. In this study, we have proposed a unique method to predict the potential antigens and T-cell epitopes for multiple poxviruses. With PoxiPred, we developed an AI-based tool that was trained and tested with the antigens and epitopes of poxviruses. Our tool was able to locate 3191 antigen proteins from 25 distinct poxviruses. From these antigenic proteins, PoxiPred redundantly located up to five epitopes per protein, resulting in 16,817 potential T-cell epitopes which were mostly (i.e., 92%) predicted as being reactive to CD8+ T-cells. PoxiPred is able to, on a single run, identify antigens and T-cell epitopes for poxviruses with one single input, i.e., the proteome file of any poxvirus.