Skip to main content

Table 1 The ARG/non-ARG classification results between different methods

From: HMD-ARG: hierarchical multi-task deep learning for annotating antibiotic resistance genes

  Accuracy Precisiona Recall F1-score
HMD-ARG 0.948 0.939 0.971 0.948
CARD 0.71 0.999 0.421 0.592
DeepARG 0.965 0.998 0.93 0.963
AMRPlusPlusb 0.691 0.867 0.449 0.592
Meta-MARCc 0.848 0.847 0.85 0.848
  1. aThe precision, recall, and F1-score are only for ARG
  2. bAMR++ requires the input in a paired fastq format. So, we simulated the fastq data from our test protein dataset. Details can be seen in the supplementary
  3. cMeta-MARC can work with both assembly and raw data; we tested it with the assembled sequences (our test dataset)