Figure 2 | Scientific Reports

Figure 2

From: Subnetwork representation learning for discovering network biomarkers in predicting lymph node metastasis in early oral cancer

Figure 2

Subnetwork clustering using latent representation. This involves (1) applying a Gaussian mixture model to a given dense representation of the PPI network using a wide range of the number of components as parameters, (2) evaluating each model by calculating the BIC criterion, and (3) choosing the best model to create a subnetwork for a given PPI network.

Back to article page