Table 1 Summary of the most important features in the random forest model based on the mean decrease accuracy (mean value > 1%)

HS-copy_log

10

1.37%

0.42%

0.13%

1.06%

1.67%

16 S rRNA copies

10

1.34%

0.45%

0.14%

1.01%

1.66%

HS-copies

10

1.29%

0.34%

0.11%

1.05%

1.53%

HSMH

10

1.20%

0.35%

0.11%

0.95%

1.46%

HSMH_log

10

1.14%

0.36%

0.12%

0.88%

1.40%

MBMH

10

1.12%

0.33%

0.10%

0.88%

1.35%

MBMH_log

10

1.07%

0.18%

0.06%

0.94%

1.19%

HSMB_log

10

1.03%

0.30%

0.10%

0.82%

1.25%

MB-copies

10

1.00%

0.26%

0.08%

0.82%

1.19%