Skip to main content

Table 7 ACT Results

From: Simple and efficient machine learning frameworks for identifying protein-protein interaction relevant articles and experimental methods used to study the interactions

Run number Label Accuracy (%) Specificity (%) Sensitivity (%) F1-Score (%) MCC AUC iP/R (%)
1 NBM-12-1k-td 80.02 80.90 75.06 53.26 0.449 61.29
2 NBM-12-400-td 81.00 81.75 76.81 55.08 0.472 62.13
3 NBM-12-1k-d 82.40 83.85 74.29 56.15 0.482 60.48
4 SVM-12-400-d 87.73 94.79 48.24 54.40 0.480 43.76
5 SVM-12-400-td 87.27 91.81 61.87 59.58 0.521 48.47
6 NBM-1-1k-td 77.80 77.84 77.58 51.46 0.432 57.44
7 NBM-1-400-td 78.05 78.15 77.47 51.71 0.434 57.56
8 NBM-1-1k-d 79.90 81.00 73.74 52.67 0.441 54.97
9 SVM-1-400-d 86.25 92.06 53.74 54.24 0.462 41.58
10 SVM-1-400-td 86.87 90.39 67.14 60.80 0.533 47.40
  1. The result of submitted ACT runs on the test data. Legend: MCC=Matthew’s correlation coefficient