Skip to main content

Table 1 Model performance on different training and evaluation data partitions

From: ACEP: improving antimicrobial peptides recognition through automatic feature fusion and amino acid embedding

Training set Evaluation set SENS(%) SPEC(%) ACC(%) MCC AUC (%)
Train Tune 95.76 83.85 87.80 0.7582 96.67
Train Test 93.39 90.44 91.92 0.8388 97.22
Train+Tune Test 92.42 94.17 93.39 0.8663 97.63
All Data All Data 98.26 99.66 98.96 0.9793 99.94
All Data 10-fold CV 91.37(± 1.05) 93.32(± 1.73) 92.46(± 0.87) 0.8474(± 0.01) 96.79(± 0.47)
  1. Note: Performance is shown for ACEP model built and evaluated on the datasets listed in columns 1 and 2, respectively, on metrics listed in columns 3-7. The bottom line shows 10-fold CV performance, and the standard deviation is shown in parentheses