Identifying and distinguishing cancer driver genes among thousands of candidate mutations remains a major challenge. Accurate identification of driver genes and driver mutations is critical for advancing cancer research and personalizing treatment based on accurate stratification of patients. Due to inter-tumor genetic heterogeneity, many driver mutations within a gene occur at low frequencies, which make it challenging to distinguish them from non-driver mutations. We have developed a novel method for identifying cancer driver genes. Our approach utilizes multiple complementary types of information, specifically cellular phenotypes, cellular locations, functions, and whole body physiological phenotypes as features. We demonstrate that our method can accurately identify known cancer driver genes and distinguish between their role in different types of cancer. In addition to confirming known driver genes, we identify several novel candidate driver genes. We demonstrate the utility of our method by validating its predictions in nasopharyngeal cancer and colorectal cancer using whole exome and whole genome sequencing.February 26, 2019 1/13 42 Public databases contain large volumes of information that relates genes or variants 43 to phenotypes (either on the cellular or whole body organism level), the specific 44 biological processes and molecular functions they can be involved in, or the cellular 45 locations at which a gene product is active. Phenotypes are systematically collected in 46 the context of genotype-phenotype relations, both from human clinical information [9], 47 from model organism experiments [10], and for cell models in cellular phenotype 48 databases [11]. Information about gene functions is collected in databases such as 49