Table 2.
List of top 15 genes deemed important or discriminative by machine learning algorithms in classifying multipartite and unipartite genomes based on differentially-present-gene-level analysis.
| Most Important Features for Differentially Present Gene-Level Analysis | |
|---|---|
| 1 | transcriptional regulator |
| 2 | chemotaxis protein |
| 3 | sugar ABC transporter permease |
| 4 | flagellar M-ring protein FliF |
| 5 | acetolactate synthase |
| 6 | PAS domain-containing protein |
| 7 | sugar ABC transporter substrate-binding protein |
| 8 | Porin |
| 9 | cell envelope biogenesis protein TolA |
| 10 | hybrid sensor histidine kinase/response regulator |
| 11 | GntR family transcriptional regulator |
| 12 | chemotaxis protein CheD |
| 13 | 2-C-methyl-D-erythritol 4-phosphate cytidylyltransferase |
| 14 | short-chain dehydrogenase |
| 15 | 2-C-methyl-D-erythritol 2,4-cyclodiphosphate synthase |