# Learning a Generative Model of Cancer Metastasis

## TL;DR

This paper presents a novel generative model, UFDN, trained on TCGA data that learns a biologically meaningful latent space, enabling interpolation between cancer types and revealing insights into metastasis mechanisms.

## Contribution

The paper introduces UFDN, a unified disentanglement network that models gene expression data for cancer classification and interpretable interpolation between cancer types.

## Key findings

- UFDN performs comparably to random forests in classification tasks.
- Interpolations between cancer types reveal biologically relevant gene expression patterns.
- Analysis uncovers potential mechanisms for skin melanoma metastasis to glioblastoma.

## Abstract

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.