Skip to main content

Table 1 Characteristics of datasets. LPI stands for lncRNA-protein interaction, PPI represents protein–protein interaction, and DTI denotes drug-target interaction

From: Negative sampling strategies impact the prediction of scale-free biomolecular network interactions with machine learning

Dataset

Origin

Processed

Power law

Nodes

Edges

Nodes

Edges

LPI

NPInter v4.0 [63, 64]

LncRNA: 43,945

Pro: 3446

373,947

LncRNA: 27,257

Pro: 2440

214,957

2.12

RAID v2.0 [65, 66]

LncRNA: 1670

Pro: 8688

30,958

LncRNA: 1093

Pro: 5523

15,384

2.38

PPI

InBioMap [67, 68]

Pro: 11,727

175,298

Pro: 5915

69,082

5.50

STRING v11.5 [69, 70]

Pro: 14,173

178,896

Pro: 8234

79,670

6.78

BioGRID v4.4.214 [71, 72]

Pro: 23,096

111,249

Pro: 6530

33,560

4.0

HuRI [73, 74]

Pro: 8275

52,569

Pro: 5073

23,637

3.18

DTI

DrugBank v5.0 [75, 76]

/

/

Drug: 5994

Pro: 3502

16,598

2.595

DrugCentral [77, 78]

/

/

Drug: 1427

Pro: 1106

9477

2.38