Abstract 5148: CanDrA: Cancer-specific driver missense mutation annotation with optimized features.

Abstract

Listen

Translate article

Abstract Driver mutations are somatic mutations that provide growth advantage to tumor cells, while passenger mutations are those that are not functionally associated with oncogenesis. Distinguishing drivers from passengers is challenging because drivers occur much less frequently than passengers, they turn to have low prevalence, and their functions are multifactorial. Missense mutations are excellent candidates for driver identification, as they occur more frequently and are potentially easier to target than other types of mutations. Although several methods have been developed for predicting the functional impact of missense mutations, only a few are specifically designed for identifying driver mutations. As more mutations are being discovered, more accurate predictive models can be developed using machine learning approaches that systematically characterize the commonality and peculiarity of somatic mutations under specific cancer background. Here, we present such a Cancer Driver Annotation (CanDrA) tool that assesses the driver potential of missense somatic mutations based on a set of 95 structural and evolutionary features computed by over 10 functional prediction algorithms from SNVBOX, VEP, ANNOVAR and Mutation Assessor. Through feature optimization and supervised training, CanDrA outperforms existing tools in analysing the glioblastoma multiforme and the ovarian carcinoma data in The Cancer Genome Atlas (TCGA) and the Cancer Cell Line Encyclopedia project. Citation Format: Yong Mao, Han Chen, Han Liang, Funda Meric-Bernstam, Gordon Mills, Ken Chen. CanDrA: Cancer-specific driver missense mutation annotation with optimized features. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 5148. doi:10.1158/1538-7445.AM2013-5148