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

BMC Bioinformatics

Table 5 Performance of machine learning models on E. coli sequencing dataset (threshold: total aligned bases = 90 bp)

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	0.76	0.65	0.83	0.91	0.91	0.81	0.68	0.89	1	1	0.91	0.92	0.92	0.91	0.91	0.86	0.78	0.91	0.95	0.95
RF	0.82	0.78	0.49	0.3	0.24	0.9	0.84	0.49	0.25	0.17	0.91	0.91	0.91	0.92	0.93	0.90	0.87	0.63	0.39	0.29
LR	0.70	0.64	0.74	×	×	0.75	0.66	0.78	×	×	0.91	0.92	0.92	×	×	0.82	0.77	0.85	×	×
NB	0.82	0.84	0.91	0.91	0.91	0.89	0.91	1	1	1	0.91	0.91	0.91	0.91	0.91	0.9	0.91	0.95	0.95	0.95
XGBoost	0.38	0.25	0.21	×	×	0.35	0.20	0.14	×	×	0.91	0.90	0.91	×	×	0.51	0.33	0.25	×	×

ISSN: 1471-2105