BMC Bioinformatics

Table 8 Performance of machine learning models on E. coli sequencing dataset (threshold: total aligned bases = 60 bp)

From: MAC-ErrorReads: machine learning-assisted classifier for filtering erroneous NGS reads

Metrics	Accuracy					Precision					Recall					F1-score
k-mer size	7	9	11	13	15	7	9	11	13	15	7	9	11	13	15	7	9	11	13	15
SVM	0.81	0.67	0.88	1	1	0.81	0.67	0.88	1	1	1	1	1	1	1	0.89	0.80	0.94	1	1
RF	0.89	0.83	0.48	0.25	0.17	0.89	0.84	0.48	0.25	0.17	1	1	1	1	1	0.94	0.91	0.65	0.4	0.29
LR	0.74	0.66	0.77	×	×	0.74	0.66	0.77	×	×	1	1	1	×	×	0.85	0.79	0.87	×	×
NB	0.88	0.90	0.99	1	1	0.88	0.90	1	1	1	1	1	1	1	1	0.94	0.95	1	1	1
XGBoost	0.36	0.20	0.14	×	×	0.36	0.20	0.14	×	×	1	1	1	×	×	0.52	0.34	0.25	×	×

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com