Skip to main content

Table 3 The best clustering results in F-measure of CPF and alignment based models on different datasets

From: An improved alignment-free model for dna sequence similarity metric

 

UCLUST

CD-HIT

CPF

Dataset

F-measure

Number of

F-measure

Number of

F-measure

Number of

  

cluster

 

cluster

 

cluster

DS2

0.0623

197

0.2429

44

0.9755

6

DS3

0.0414

285

0.0620

189

0.9809

6

DS4

0.0633

183

0.1241

127

0.9761

6

HOG20

0.2590

197

0.2287

246

0.7791

20

HOG50

0.2197

484

0.1652

625

0.5576

50

HOG80

0.1871

897

0.1648

1033

0.5024

80

HOG100

0.1804

1185

0.1533

1433

0.4780

100

Settings

0.75≤T≤1

0.8≤T≤1

k=2