Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: PathME: pathway based multi-modal sparse autoencoders for clustering of patient-level multi-omics data

Fig. 1

Conceptual overview about our approach: Multi-omics feature mapping to a specific pathway are summarized into a pathway level score via a sparse denoising multi-modal autoencoder architecture. Hidden layer 1 consists of up to [pj/2] hidden units per omics modality, where p_j is the number of features in omics type j. Hidden units for omics modality j are densely connected to input features of the same omics type, but there are no connections from input features of other data modalities. Hidden layer 2 consists of one hidden unit, which represents the overall multi-omics pathway score. Concatenation of P multi-omics pathway scores for each patient allows for application of consensus sparse NMF clustering in a subsequent step

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us