Examination Date
Spring 3-13-2026
Degree
Thesis
Degree Program
Bioinformatics
Examination Committee
Dr. Diptasri M. Mandal, Dr. Giulia Monticone, Dr. Chindo Hicks
Abstract
Triple-Negative Breast Cancer (TNBC) is a highly aggressive and immunogenic subtype of breast cancer that affects 10-20% of women with breast cancer in the United States. This project aims to discover potential biomarkers, driver genes, and cell types associated with TNBC by integrating multi-omics data and ML algorithms for the classification and discovery of potential biomarkers in TNBC.
This study finds potential diagnostic and prognostic biomarkers and driver genes associated with TNBC, using bulk RNA-seq data integrated with somatic mutations. Along with cell types associated with TNBC, driving the heterogeneity of the disease. ML models were developed and generalized to accurately classify patients using transcriptional data, along with biomarker extraction using feature importance scores. Functional enrichment analysis demonstrates the involvement of metabolic pathways associated with TNBC.
Recommended Citation
Anto Domnic Raj, Kristos Martin, "INTEGRATIVE MULTI-OMICS AND MACHINE LEARNING APPROACHES FOR TUMOR CLASSIFICATION AND DISCOVERY OF BIOMARKERS IN TRIPLE-NEGATIVE BREAST CANCER" (2026). School of Graduate Studies. 12.
https://digitalscholar.lsuhsc.edu/etd_sgs/12
Thesis Report Form