Skip to main content
Fig. 5 | BMC Cancer

Fig. 5

From: Unsupervised machine learning-based stratification and immune deconvolution of liver hepatocellular carcinoma

Fig. 5

Bar plots of the absolute feature weights of the Multi-Omics Factor Analysis (MOFA), and the importance of features in the bottleneck layer from the autoencoder. The gene with the greatest feature weight across all latent factors for MOFA is ID4, with all clinical features having the least. HAMP has the greatest importance according to the autoencoder, with clinical features again having the least importance, although being more spread out

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us