ICE: A Driver Genes Identification Method With Improved Cross-Entropy Measure

Cancer is inherently a complex disease and cancer somatic driver mutations within the cancer pathway often show mutually exclusive patterns in a group of patients, providing a novel signal to distinguish driver mutations from mass passenger mutations. However, in biological pathways, most mutated genes are low exclusivity and mutual exclusivity-based driver genes identification methods do not identify low exclusivity driver genes well. Furthermore, mutual exclusivity-based methods are largely influenced by the integrity of the biological network, resulting in their ineffectiveness in identifying driver genes. Therefore, in this paper, we propose a driver genes identification method with improved cross-entropy measure (ICE), which measures mutation frequencies of mutated genes in biological pathways while measuring mutual exclusivity through improved cross-entropy, thereby achieving complementary mutual exclusivity and mutation rates. Experimental results show that our method outperforms eight state-of-the-art methods in identifying driver genes, especially in identifying low-exclusivity genes. In addition, our method is more effective when protein networks and biological pathways are error-prone or incomplete.