Skip to main content

Table 1 Basic properties of benchmark, IUPHAR and generic data sets

From: LPbyCD: a new scalable and interpretable approach for Link Prediction via Community Detection in bipartite networks

Data set

V1

V2

Interactions

Layers

|V|

|E|

Sparsity

Connected components

Enzyme

445

664

2926

3

1109

321832

0.524

1

GPCR

223

95

635

3

318

29853

0.592

1

IC

210

204

1476

3

414

44127

0.516

1

NR

54

26

90

3

80

1846

0.584

1

Kinase

68

442

1527

3

510

101266

0.780

1

IUPHAR

8137

2502

12456

6

10639

26706838

0.472

1

MovieLens

943

1682

100000

3

2625

1940394

0.563

1

Unicodelang

254

614

1255

3

868

218996

0.582

1