Ünal, Ali Burak2017-08-042017-08-042017-072017-072017-08-04http://hdl.handle.net/11693/33530Cataloged from PDF version of article.Thesis (M.S.): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2017.Includes bibliographical references (leaves 68-73).Characterizing patient genomic alterations through next-generation sequencing technologies opens up new opportunities for re ning cancer subtypes. Di erent omics data provide di erent views into the molecular biology of the tumors. However, tumor cells exhibit high levels of heterogeneity, and di erent patients harbor di erent combinations of molecular alterations. On the other hand, different alterations may perturb the same biological pathways. In this work, we propose a novel clustering procedure that quanti es the similarities of patients from their alteration pro les on pathways via a novel graph kernel. For each pathway and patient pair, a vertex labeled undirected graph is constructed based on the patient molecular alterations and the pathway interactions. The proposed smoothed shortest path graph kernel (smSPK) assesses similarities of pair of patients with respect to a pathway by comparing their vertex labeled graphs. Our clustering procedure involves two steps. In the rst step, the smSPK kernel matrices for each pathway and data type are computed for patient pairs to construct multiple kernel matrices and in the ensuing step, these kernel matrices are input to a multi-view kernel clustering algorithm to stratify patients. We apply our methodology to 361 renal cell carcinoma patients, using somatic mutations, gene and protein expressions data. This approach yields subgroup of patients that di er signi cantly in their survival times (p-value 1:5 10􀀀8). The proposed methodology allows integrating other type of omics data and provides insight into disrupted pathways in each patient subgroup.xiv, 88 pages : charts (some color) ; 29 cmEnglishinfo:eu-repo/semantics/openAccessCancer subtypeGraph kernelMulti-view kernel clusteringKernel functionsClusteringThesisB156081