Publication:
Integrated Bioinformatics And Machine Learning Approach To Identify Chemotherapy Resistance Biomarkers And Develop Prognostic Models In Breast Cancer

Simple item page
dc.contributor.authorZhang, Hao
dc.date.accessioned2026-09-03T02:59:25Z
dc.date.available2026-09-03T02:59:25Z
dc.date.issued2025-09
dc.description.abstractChemoresistance remains a critical challenge in breast cancer treatment, limiting therapeutic efficacy and compromising long-term survival. This thesis adopts a multi-stage, integrative approach to address this issue, beginning with a bibliometric analysis to map global research trends and highlight methodological priorities in chemoresistance studies. Building upon these insights, large-scale multi-omics datasets representative of big data, including transcriptomic profiles from TCGA and GEO, were systematically analysed using bioinformatics techniques such as differential expression analysis and weighted gene co-expression network analysis (WGCNA). Subsequently, a machine learning–based feature selection strategy using least absolute shrinkage and selection operator (LASSO) regression was applied to identify the most predictive genes, followed by multivariate Cox proportional hazards regression analysis to construct a robust prognostic model.
dc.identifier.urihttps://erepo.usm.my/handle/123456789/24938
dc.language.isoen
dc.subjectIntegrated Bioinformatics And Machine Learning Approach To Identify Chemotherapy Resistance Biomarkers
dc.subjectDevelop Prognostic Models In Breast Cancer
dc.titleIntegrated Bioinformatics And Machine Learning Approach To Identify Chemotherapy Resistance Biomarkers And Develop Prognostic Models In Breast Cancer
dc.typeResource Types::text::thesis::doctoral thesis
dspace.entity.typePublication
oairecerif.author.affiliationUniversiti Sains Malaysia
Files
Collections
Institut Perubatan & Pergigian Termaju - Tesis