Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data

Fig. 4

Performance comparison among different methods. a PR vs. ROC AUC plot for SGAN models, machine-learning models (left panel), and 23 in silico algorithms or tools (right panel). The shapes and colors represent the types of these methods. b–g Distribution of interpretation scores for somatic mutations in the testing dataset. The interpretation scores were predicted by b SGAN model using 1000 labeled variants, c SGAN model using 4000 labeled variants, d random forest model, e voting classifier, f MetaLR, and g FATHMM

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us