Dissertation/Thesis Abstract

Specification of sex-specific molecular biomarkers
by Lopez, Karen L., M.S., California State University, Long Beach, 2012, 93; 1517720
Abstract (Summary)

Ideally, treatments for patients would be standardized and uniform, based on the specific illness or disease, despite individual characteristic differences; however, numerous studies have revealed this not to be the case, since differences are seen in reactions to the same drug treatment reliant on the person's sex, thus undermining the traditional view of one-size-fits-all medicine. This study investigates the influence of sex on disease characteristics and risk factors. An algorithm is proposed to isolate a set of sex-specific genomic biomarkers using the Random Forest algorithm to rank the importance of genes from gene expression data. Cross-validation is used to isolate a feasible set of genes and to obtain performance of sex-specific biomarkers. The selected a set of sex-specific biomarkers will improve accuracy in classification of patients which will provide more effective treatment. The proposed procedure is applied to two gene expression datasets.

Indexing (document details)
Advisor: Moon, Hojin
School: California State University, Long Beach
School Location: United States -- California
Source: MAI 51/01M(E), Masters Abstracts International
Subjects: Molecular biology, Statistics, Health sciences
Publication Number: 1517720
ISBN: 9781267470812
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy