Table 9 Performance across different SVD ranks for lncRNADisease v2.0, MNDR, and lncRNADisease v3.0. The best performance is denoted as bold.

From: Decoding potential lncRNA and disease associations through graph representation learning and gradient boosting with histogram

Dataset

Rank

Precision

Recall

Accuracy

F1-score

AUC

AUPR

lncRNADisease v2.0

rank = 5

0.8746 ± 0.0327

0.7997 ± 0.0399

0.8420 ± 0.0259

0.8347 ± 0.0283

0.9200 ± 0.0192

0.9292 ± 0.0177

rank = 8

0.8754 ± 0.0282

0.8207 ± 0.0389

0.8514 ± 0.0220

0.8464 ± 0.0243

0.9132 ± 0.0176

0.9169 ± 0.0215

rank = 16

0.8726 ± 0.0283

0.8340 ± 0.0337

0.8557 ± 0.0219

0.8523 ± 0.0230

0.9121 ± 0.0189

0.9102 ± 0.0273

MNDR

rank = 5

0.9174 ± 0.0137

0.9038 ± 0.0168

0.9111 ± 0.0103

0.9104 ± 0.0105

0.9688 ± 0.0057

0.9733 ± 0.0045

rank = 8

0.9190 ± 0.0142

0.8918 ± 0.0167

0.9065 ± 0.0095

0.9050 ± 0.0098

0.9670 ± 0.0052

0.9670 ± 0.0138

rank = 16

0.9186 ± 0.0154

0.9017 ± 0.0203

0.9107 ± 0.0120

0.9099 ± 0.0125

0.9661 ± 0.0076

0.9635 ± 0.0168

lncRNADisease 3.0

rank = 5

0.8961 ± 0.0133

0.8734 ± 0.0156

0.8859 ± 0.0095

0.8845 ± 0.0098

0.9536 ± 0.0061

0.9550 ± 0.0068

rank = 8

0.8899 ± 0.0148

0.8810 ± 0.0185

0.8859 ± 0.0119

0.8853 ± 0.0122

0.9521 ± 0.0066

0.9531 ± 0.0065

rank = 16

0.8780 ± 0.0138

0.8746 ± 0.0159

0.8764 ± 0.0111

0.8762 ± 0.0112

0.9450 ± 0.0071

0.9452 ± 0.0076

Back to article page