Statistical methods and machine learning techniques for analyzing high-dimensional data in cancer biology: modeling t-cell receptor repertoire and methylation signatures in acute myeloid leukemia
This thesis is composed of two studies that utilizes different statistical methods to answer cancer research questions. The first study uses supervised and unsupervised statistical modeling on methylation array data from the BeatAML cohort to infer methylation signatures of AML. The second study presents a non-commercial and inexpensive protocol for measuring and monitoring adaptive dynamics in TCR clonotype repertoire using genomic DNA-based bulk sequencing.
Details
Title
Statistical methods and machine learning techniques for analyzing high-dimensional data in cancer biology: modeling t-cell receptor repertoire and methylation signatures in acute myeloid leukemia
Creator
Gurun-Demir, Burcu : Oregon Health and Science University
Contributor
Spellman, Paul Advisor (Oregon Health and Science University)
