Learning a Generative Model of Cancer Metastasis
This work addresses the problem of understanding cancer metastasis for biomedical researchers, but it is incremental as it builds on existing disentanglement methods and shows comparable performance to random forests.
The authors tackled the problem of modeling cancer metastasis by introducing a Unified Disentanglement Network (UFDN) trained on TCGA data, which learns a biologically relevant latent space for gene expression and enables interpolation between cancer types, such as from skin cutaneous melanoma to glioblastoma, revealing metagenes that recapitulate known mechanisms and suggest starting points for metastasis investigations.
We introduce a Unified Disentanglement Network (UFDN) trained on The Cancer Genome Atlas (TCGA). We demonstrate that the UFDN learns a biologically relevant latent space of gene expression data by applying our network to two classification tasks of cancer status and cancer type. Our UFDN specific algorithms perform comparably to random forest methods. The UFDN allows for continuous, partial interpolation between distinct cancer types. Furthermore, we perform an analysis of differentially expressed genes between skin cutaneous melanoma(SKCM) samples and the same samples interpolated into glioblastoma (GBM). We demonstrate that our interpolations learn relevant metagenes that recapitulate known glioblastoma mechanisms and suggest possible starting points for investigations into the metastasis of SKCM into GBM.