Skip to main content

Table 5 Performance of the 8 AMR prediction models on their respective test sets and MGS2AMR output

From: MGS2AMR: a gene-centric mining of metagenomic sequencing data for pathogens and their antimicrobial resistance profile

Antibiotic

Precision

Recall

Accuracy

MCC

Ampicillin

1.00/0.98

1.00/0.99

1.00/0.97

0.94/0.74

Cefepime

0.91/0.85

0.80/0.78

0.78/0.74

0.46/0.37

Gentamicin

0.93/0.73

0.95/0.89

0.92/0.81

0.83/0.63

Meropenem

0.86/0.74

0.74/0.78

0.78/0.74

0.57/0.48

Tetracycline

0.79/0.61

0.99/0.94

0.86/0.75

0.75/0.57

Tobramycin

0.95/0.76

0.99/0.97

0.96/0.84

0.91/0.70

Trimethoprim-sulfamethoxazole

0.97/0.86

0.95/0.93

0.93/0.86

0.81/0.70

Vancomycin

1.00/0.97

1.00/1.00

1.00/0.98

1.00/0.95

  1. The first value is the performance on the XGBoost model test set (isolates only), and the second value is the performance on the MGS2AMR processed output (ARG recovered from the metagenomics data)