Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

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

Fig. 2

T-SNE plot of the training data set, includng 10,000 fake variants from the trained generator (training epoch is 50), 10,000 unlabeled variants and 2000 labeled variants (1000 oncogenic and 1000 benign variants) from an in-house database of expert-annotated somatic variants. a Gery data points are unlabeled variants. b Unlabeled variants with predicted interpretation scores are ranging from 0 to 1. And variants with high interpretation scores (close to red) are predicted as oncogenic

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us