PAMOGK: A pathway graph kernel based multi-omics clustering approach for discovering cancer patient subgroups

Official URL: http://dx.doi.org/10.1101/834168

Accurate classification of patients into homogeneous molecular subgroups is critical for the developmentof effective therapeutics and for deciphering what drives these different subtypes to cancer. However, the extensivemolecular heterogeneity observed among cancer patients presents a challenge. The availability of multi-omic datacatalogs for large cohorts of cancer patients provides multiple views into the molecular biology of the tumorswith unprecedented resolution. In this work, we develop PAMOGK, which integrates multi-omics patient data andincorporates the existing knowledge on biological pathways. PAMOGK is well suited to deal with the sparsity ofalterations in assessing patient similarities. We develop a novel graph kernel which we denote as smoothed shortestpath graph kernel, which evaluates patient similarities based on a single molecular alteration type in the contextof pathway. To corroborate multiple views of patients evaluated by hundreds of pathways and molecular alterationcombinations, PAMOGK uses multi-view kernel clustering. We apply PAMOGK to find subgroups of kidney renalclear cell carcinoma (KIRC) patients, which results in four clusters with significantly different survival times (p-value =7.4e-10). The patient subgroups also differ with respect to other clinical parameters such as tumor stage andgrade, and primary tumor and metastasis tumor spreads. When we compare PAMOGK to 8 other state-of-the-artexisting multi-omics clustering methods, PAMOGK consistently outperforms these in terms of its ability to partitionpatients into groups with different survival distributions. PAMOGK enables extracting the relative importance ofpathways and molecular data types. PAMOGK is available at github.com/tastanlab/pamogk