The new coronavirus disease (COVID-19) broke out earlier in Wuhan, and the plague spread rapidly from multiple resources of different countries. COVID-19 has caused millions of diagnosed people worldwide, causing many deaths and posing a severe threat to public health in countries around the world. Facing this urgent situation, in-depth research on the emerging SARS-CoV-2 to understand the related pathogenic mechanism and epidemiological characteristics is urgent. This type of activity would be useful to determine its origin to formulate effective prevention and treatment strategies for affected patients.
This paper adopts t-SNE based on machine learning to draw a phylogenetic tree from collected genomic sequences to analyze G20 countries’ samples. The phylogenetic tree of the generating mechanism was described, and intermediate results were illustrated. The results of this research showed that viruses in many countries have similar or similar relationships among the gene sequences.