Utilizing Machine Learning Methods for Genomic Biomarker Discovery in Prostate and Bladder Cancer

Abstract

Cancer in all its forms of expression is a major cause of death. In this thesis, prostate and bladder cancer are examined for the purpose of genomic biomarker discovery. Genomic biomarkers are indicators stemming from the study of the genome, either in a very low level based on the genome sequence itself, or in a more abstract way such as measuring the level of gene expression in different disease groups. The latter method is pivotal for this work, since the available datasets consisted of RNA sequencing data, transformed to gene expression levels, as well as a multitude of clinical indicators. Based on this, various methods are utilized such as statistical modeling via logistic regression and regularization techniques (elastic-net), clustering, survival analysis through Kaplan-Meier curves, and heatmaps. The experimental work led to the discovery of two gene signatures capable of predicting Therapy Response and Disease Progression with considerable accuracy for bladder cancer patients, the correlation of clinical indicators such as Therapy Response and T-Stage at surgery with Disease Progression in a time-to-event manner, and to further exploring and validating the predictive potential of the preexisting HDDA10 genomic signature for prostate cancer patients.