Benchmark Datasets

Click here to download benchmark datasets.

Table 1. Statistics compositions of the benchmark dataset

Dataset

No. of Sequences

Num_Pos a

Num_Neg b

Ratio c

PDNA-543

543

9,549

134,995

14

PDNA-41

41

734

14,021

19

PDNA-335

335

6,461

71,320

11

PDNA-52

52

973

16,225

17

PDNA-316

316

5,609

67,109

12

 a Num_Pos is the number of positive samples;

 b Num_Neg is the number of negtaive samples;

 c Ratio=Num_Neg/Num_Pos, which measures the imbalance degree of a dataset