Skip to main content

Table 1 Results of Random Forest classification and k-mer association

From: Genome-wide association studies of Shigella spp. and Enteroinvasive Escherichia coli isolates demonstrate an absence of genetic markers for prediction of disease severity

Characteristic

Random Forest

K-mer association with Pyseer

OOB error rate

No. of k-mers

Lowest LRT p-value

MVS severity scale

70.1%

0

NA

De Wit severity scale

65.1%

17

0.015

Abdominal cramps

52.7%

0

NA

Abdominal pain

40.8%

0

NA

Blood in stool

41.2%

0

NA

Diarrhea

51.6%

156

0.313

Fever

47.7%

0

NA

Headache

46.6%

0

NA

Mucus in stool

43.3%

0

NA

Nausea

53.1%

0

NA

Vomiting

51.6%

0

NA

Genus

15.9%

3,036,507

1.94E-153