Skip to main content

Table 3 The performance of RLFDDA on each fold in cross-validation over B-dataset

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

Fold

Acc.

AUC.

Prec.

Recall

F1-score

0

0.7858

0.8673

0.7707

0.8138

0.7917

1

0.7964

0.8727

0.7939

0.8008

0.7973

2

0.7972

0.8785

0.7889

0.8116

0.8001

3

0.7932

0.8760

0.7807

0.8154

0.7977

4

0.7796

0.8639

0.7691

0.7991

0.7838

5

0.7904

0.8753

0.7843

0.8013

0.7927

6

0.7959

0.8813

0.7927

0.8013

0.7970

7

0.7872

0.8702

0.7747

0.8100

0.7919

8

0.7831

0.8628

0.7784

0.7915

0.7849

9

0.7978

0.8802

0.7876

0.8154

0.8013

Overall

0.7907 ± 0.0061

0.8728 ± 0.0063

0.7821 ± 0.0084

0.8060 ± 0.0078

0.7938 ± 0.0057