Fig. 7

Latent structure for supervised multimodal networks. From [33] and adapted from [38]. Assume two data types, \(\boldsymbol {\mathcal {G}}\) and \(\boldsymbol {\mathcal {X}}\). S describes the subset of features within \(\boldsymbol {\mathcal {X}}\) that relate to the disease outcome but not with any features within \(\boldsymbol {\mathcal {G}}\); H describes the subset of features within \(\boldsymbol {\mathcal {G}}\) that relate to the disease outcome but not with any features within \(\boldsymbol {\mathcal {X}}\); G and X describe the network where the subset of features within \(\boldsymbol {\mathcal {G}}\) relate to the subset of features within \(\boldsymbol {\mathcal {X}}\) that ultimately relate to the outcome; G^′ and X^′ denote the subset of features that relate to each other but not with the outcome; and finally each data type will have independent noise not related to each other or the outcome