BMC Bioinformatics

Table 1 Accuracy of RF, SVM and GLM across three datasets from DIABIMMUNE research group

From: MegaR: an interactive R package for rapid sample classification and phenotype prediction using metagenome profiles and machine learning

Dataset	Data type	Accuracy
Dataset	Data type	RF	SVM	GLM
Three country cohort	16S	0.8832	0.8063	0.7844
Three country cohort	WGS	0.8846	0.7014	0.5165
T1D cohort	16S	0.9017	0.9245	0.5897
T1D cohort	WGS	0.9385	0.7719	0.6316
Antibiotic cohort	16S	0.8666	0.7544	0.7397
Antibiotic cohort	WGS	0.7149	0.6328	0.5362

Bold values represent the highest accuracy for each type of tested data in any given dataset

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com