Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 132 - SLDS CSpeed 1
Type: Contributed
Date/Time: Monday, August 9, 2021 : 1:30 PM to 3:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #319076
Title: Multiomics-Based Tensor Decomposition for Breast Cancer Subtyping
Author(s): Qian Liu and Bowen Cheng and Pingzhao Hu*
Companies: University of Manitoba and University of Toronto and University of Manitoba
Keywords: tensor factorization; multiomics; breast cancer; clustering; subtype; survival analysis

Breast cancer is heterogeneous and consists of intrinsic components with various alterations. Combining multiply genomic sources to identify the intrinsic components and their heterogeneity is essential for precise clinical decision-making. In this study, we explore the heterogeneous intrinsic hallmarks of breast cancer by decomposing the integrated tensor of gene expression, copy number alteration, and DNA methylation information. This is achieved using advanced Bayesian tensor decomposition, which can extract multi-level latent representatives for both patients and genes. Gene set enrichment analysis is applied to estimate the key biological functions of the identified intrinsic genomic components. Patient stratification and survival analysis are performed based on the heterogeneity of these functional genomic components. The findings are evaluated using The Cancer Genome Atlas Breast Carcinoma (TCGA-BRCA) dataset. This study could provide insight into how multi-omics can identify functional intrinsic components of cancer and stratify patients into prognostically significant groups.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program