Tumor Gene Expression Purification Using Infinite Mixture Topic Models

Tumor Gene Expression Purification Using Infinite Mixture Topic Models

Show other versions (1)

There is significant interest in using gene expression measurements to aid in the personalization of medical treatment. The presence of significant normal tissue contamination in tumor samples makes it difficult to use tumor expression measurements to predict clinical variables and treatment respon...

Full description

Bibliographic Details
Main Author: Deshwar, Amit Gulab
Other Authors: Wong, Willy
Language:en_ca
Published: 2013
Subjects:
Bayesian methods
Gene expression purficiation
Bayesian Nonparametric
Topic models
0984
0800
0544
Online Access:http://hdl.handle.net/1807/35597
id ndltd-TORONTO-oai-tspace.library.utoronto.ca-1807-35597
record_format oai_dc
spelling ndltd-TORONTO-oai-tspace.library.utoronto.ca-1807-355972013-11-01T04:11:51ZTumor Gene Expression Purification Using Infinite Mixture Topic ModelsDeshwar, Amit GulabBayesian methodsGene expression purficiationBayesian NonparametricTopic models098408000544There is significant interest in using gene expression measurements to aid in the personalization of medical treatment. The presence of significant normal tissue contamination in tumor samples makes it difficult to use tumor expression measurements to predict clinical variables and treatment response. I present a probabilistic method, TMMpure, to infer the expression profile of the cancerous tissue using a modified topic model that contains a hierarchical Dirichlet process prior on the cancer profiles. I demonstrate that TMMpure is able to infer the expression profile of cancerous tissue and improves the power of predictive models for clinical variables using expression profiles.Wong, Willy2013-062013-07-11T18:20:53ZNO_RESTRICTION2013-07-11T18:20:53Z2013-07-11Thesishttp://hdl.handle.net/1807/35597en_ca
collection NDLTD
language en_ca
sources NDLTD
topic Bayesian methods
Gene expression purficiation
Bayesian Nonparametric
Topic models
0984
0800
0544
spellingShingle Bayesian methods
Gene expression purficiation
Bayesian Nonparametric
Topic models
0984
0800
0544
Deshwar, Amit Gulab
Tumor Gene Expression Purification Using Infinite Mixture Topic Models
description There is significant interest in using gene expression measurements to aid in the personalization of medical treatment. The presence of significant normal tissue contamination in tumor samples makes it difficult to use tumor expression measurements to predict clinical variables and treatment response. I present a probabilistic method, TMMpure, to infer the expression profile of the cancerous tissue using a modified topic model that contains a hierarchical Dirichlet process prior on the cancer profiles. I demonstrate that TMMpure is able to infer the expression profile of cancerous tissue and improves the power of predictive models for clinical variables using expression profiles.
author2 Wong, Willy
author_facet Wong, Willy
Deshwar, Amit Gulab
author Deshwar, Amit Gulab
author_sort Deshwar, Amit Gulab
title Tumor Gene Expression Purification Using Infinite Mixture Topic Models
title_short Tumor Gene Expression Purification Using Infinite Mixture Topic Models
title_full Tumor Gene Expression Purification Using Infinite Mixture Topic Models
title_fullStr Tumor Gene Expression Purification Using Infinite Mixture Topic Models
title_full_unstemmed Tumor Gene Expression Purification Using Infinite Mixture Topic Models
title_sort tumor gene expression purification using infinite mixture topic models
publishDate 2013
url http://hdl.handle.net/1807/35597
work_keys_str_mv AT deshwaramitgulab tumorgeneexpressionpurificationusinginfinitemixturetopicmodels
_version_ 1716612145250041856

Similar Items