A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-07172015-094412


Type of Document Master's Thesis
Author Zhong, Xue
URN etd-07172015-094412
Title Sparse Network-regularized Nonnegative Matrix Factorization and Applications to Tumor Subtyping
Degree Master of Science
Department Biostatistics
Advisory Committee
Advisor Name Title
Yu Shyr Committee Chair
Xi Chen Committee Co-Chair
Keywords
  • sparse
  • network-regularized
  • nonnegative matrix factorization
  • tumor subtyping
  • classification
  • network-based stratification
  • somatic mutation
  • TCGA
Date of Defense 2015-07-11
Availability unrestricted
Abstract
Cancers are complex diseases and identification of clinically important subtypes has the potential to guide better prognosis and treatment. The utility of graph-regularized nonnegative matrix factorization (GNMF) has been demonstrated on tumor subtype identification based on exome-level mutation data. In a recent study, it revealed that using a panel of important genes achieved superior classification than using the full set of (exome-level) mutations. We hypothesized that combining sparse coding with GNMF will enable automatic selection of important genes to aid tumor subtyping as well as interpretations of the underlying pathways responsible for the subtypes. To test our hypothesis, we proposed a new formulation that incorporates a lasso-like penalty into GNMF to enable variable selection and sparse representation. We evaluated the proposed method for rich scenarios of simulated mutation cohorts, and further demonstrated the utility on real mutation data from large-scale sequencing studies.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  zhong.pdf 2.19 Mb 00:10:08 00:05:12 00:04:33 00:02:16 00:00:11

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.