Skip to main content

Table 3 Precision, recall and F1-score of InvBFM in SVM with different parameter

From: InvBFM: finding genomic inversions from high-throughput sequence data based on feature mining

Para.

Precision

Recall

F1-score

c:32, g:5

25.51%

72.69%

37.77%

c:32, g:1

26.71%

72.27%

39.01%

c:32, g:0.1

28.32%

72.27%

40.69%

c:32, g:0.01

29.94%

72.27%

42.34%

c:8, g:0.01

32.15%

71.85%

44.42%

  1. Threshold = 3*ISPE. The kernel of SVM is RBF, “c” stands for penalty factor and “g” stands for gamma