Staphylococcus Genomics Sequence Identification with Gradient Boosting Machine
摘要
The biological function of Staphylococcus on the human body is mainly reflected in its pathogenicity as a pathogen and its non-pathogenic coexistence in some cases. Staphylococcus can invade the body in a variety of ways, leading to a variety of skin or organ infections. In this work, we focused on the classification of coding and non-coding genes in the species of Staphylococcus. We employed three sequential features, including ENAC, NAC, and MMI. Meanwhile, we employed several classification algorithms, including several typical Gradient Boosting Machine (GBM) models, to deal with the three features in this classification issue.