Kou Z, Li J, Fan X, Kosari S, Qiang X. Predicting Cross-Species Infection of Swine Influenza Virus with Representation Learning of Amino Acid Features. Comput Math Methods Med. 2021 Oct 11;2021:6985008
Swine influenza viruses (SIVs) can unforeseeably cross the species barriers and directly infect humans, which pose huge challenges for public health and trigger pandemic risk at irregular intervals. Computational tools are needed to predict infection phenotype and early pandemic risk of SIVs. For this purpose, we propose a feature representation algorithm to predict cross-species infection of SIVs. We built a high-quality dataset of 1902 viruses. A feature representation learning scheme was applied to learn feature representations from 64 well-trained random forest models with multiple feature descriptors of mutant amino acid in the viral proteins, including compositional information, position-specific information, and physicochemical properties. Class and probabilistic information were integrated into the feature representations, and redundant features were removed by feature space optimization. High performance was achieved using 20 informative features and 22 probabilistic information. The proposed method will facilitate SIV characterization of transmission phenotype.
See Also:
Latest articles in those days:
- The evolution, complexity, and diversity of swine influenza viruses in China: A hidden public health threat 22 hours ago
- MHC class II proteins mediate sialic acid independent entry of human and avian H2N2 influenza A viruses 23 hours ago
- Histopathologic Features and Viral Antigen Distribution of H5N1 Highly Pathogenic Avian Influenza Virus Clade 2.3.4.4b from the 2022–2023 Outbreak in Iowa Wild Birds 23 hours ago
- Detection and characterization of H5N1 HPAIV in environmental samples from a dairy farm 1 days ago
- Genomic Characterization of Highly Pathogenic Avian Influenza A H5N1 Virus Newly Emerged in Dairy Cattle 1 days ago
[Go Top] [Close Window]