Current studentsExisting staffContact us
 

Computational modelling for breast cancer prognosis in precision medicine /

Simple item page
dc.contributor.authorLi, Xiaomei
dc.contributor.schoolUniversity of South Australia. UniSA STEM
dc.contributor.schoolUniSA STEM
dc.date.issued2022
dc.description1 ethesis (xx,193 pages) :
dc.descriptioncolour illustrations.
dc.descriptionIncludes bibliographical references (pages 152-193)
dc.description.abstractUnderstanding tumour heterogeneity is fundamental for improving breast cancer prognosis and working towards precision medicine. In this thesis, we develop computational methods and a software tool to address the following research questions posed by breast cancer heterogeneity: 1) how to develop a breast cancer prognosis method with stable prediction performance in different independent breast cancer cohorts; 2) how to examine the roles of miRNAs and lncRNAs in characterising breast cancer outcomes and subtypes; 3) how to utilise single-cell data to identify molecular signatures related to intra-tumour heterogeneity to improve breast cancer prognosis. The experiments on real breast cancer datasets demonstrated that the computational methods presented in the thesis outperformed the existing methods and provided new biological knowledge.
dc.description.dissertationThesis (PhD(Computer and Information Science)--University of South Australia, 2022.
dc.identifier.urihttps://hdl.handle.net/11541.2/30347
dc.language.isoen
dc.provenanceCopyright 2022 Xiaomei Li
dc.subjectComputational methods;breast cancer;prognosis
dc.subject.lcshBreast
dc.subject.lcshCancer
dc.subject.lcshComputational intelligence.
dc.subject.lcshPrognosis
dc.titleComputational modelling for breast cancer prognosis in precision medicine /
dc.typethesis
dcterms.accessRights506 0#$fstar $2Unrestricted online access
ror.fileinfo12250158530001831 13250158520001831 Li, Xiaomei - Thesis
ror.mmsid9916676027401831

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Li, Xiaomei - Thesis.pdf
Size:
3.11 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections