Learning a Generative Model of Cancer Metastasis

2019/01/17 by Benjamin Kompa, Kompa, Benjamin, Beau Coker +1
Biochemistry, Genetics and Molecular Biology · Computer Science · #AI in cancer detection #Cancer Genomics and Diagnostics #FOS: Biological sciences #FOS: Computer and information sciences #Gene expression and cancer classification #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM)

paper · pdf · doi:10.48550/arxiv.1901.06023

openalex publication_date 2019/01/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• The Cancer Genome Atlas Pan-Cancer analysis project
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
• Dr.VAE: Drug Response Variational Autoencoder
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• A Unified Feature Disentangler for Multi-Domain Image Translation and\n Manipulation

Related

• From genome to phenome: Predicting multiple cancer phenotypes based on somatic genomic alterations via the genomic impact transformer
• Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction
• A Model of Selective Advantage for the Efficient Inference of Cancer Clonal Evolution
• The Cancer Genome Atlas Pan-Cancer analysis project
• Cancer Networks: A general theoretical and computational framework for understanding cancer