Skip to main content

Table 4 The performance of RLFDDA on each fold in cross-validation over C-dataset

From: RLFDDA: a meta-path based graph representation learning model for drug–disease association prediction

Fold

Acc.

AUC.

Prec.

Recall

F1-score

0

0.8996

0.9610

0.8980

0.9016

0.8998

1

0.8917

0.9643

0.9129

0.8661

0.8889

2

0.9114

0.9721

0.9300

0.8898

0.9095

3

0.8701

0.9544

0.8821

0.8543

0.8680

4

0.9075

0.9613

0.8966

0.9213

0.9087

5

0.9055

0.9610

0.9187

0.8898

0.9040

6

0.9055

0.9674

0.8992

0.9134

0.9063

7

0.8957

0.9663

0.8972

0.8937

0.8955

8

0.9035

0.9678

0.8897

0.9213

0.9052

9

0.9154

0.9622

0.9105

0.9213

0.9159

Overall

0.9006 ± 0.0121

0.9636 ± 0.0047

0.9035 ± 0.0136

0.8972 ± 0.0222

0.9002 ± 0.0129