Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Prediction and analysis of multiple protein lysine modified sites based on conditional wasserstein generative adversarial networks

Fig. 3

ROC curves of seven modification types with random forest in the tenfold cross-validation after PCC, CGAN and CWGAN. True positive rate (sensitivity) as the ordinate, false positive rate as the abscissa. The performance of random forest (RF) classification (baseline), RF with PCC screening, RF with PCC screening and CGAN augmentation, RF with PCC screening and CWGAN augmentation are visualized by green, yellow, purple and red, respectively. Acetylation (S1), Glycation (S2), Malonylation (S3), Methylation (S4), Succinylation (S5), Sumoylation (S6) and Ubiquitination (S7). (Python 3.8)

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us