Next-generation DNA sequencing technologies are enabling genome-wide measurements of somatic mutations in large numbers of cancer patients. A major challenge in interpretation of this data is to distinguish functional driver mutations that are important for cancer development from random, passenger mutations. A common approach to identify driver mutations is to find genes that are mutated at significant frequency in a large cohort of cancer genomes. This approach is confounded by the observation that driver mutations target multiple cellular signaling and regulatory pathways. Thus, each cancer patient may exhibit a different combination of mutations that are sufficient to perturb the necessary pathways. However, the current understanding of the somatic mutational process of cancer [3,5,6] places two additional constraints on the expected patterns of somatic mutations in a cancer pathway. First, an important cancer pathway should be perturbed in a large number of patients. Thus we expect that with genome-wide measurements of somatic mutations a driver pathway will exhibit high coverage, where most patients will have a mutation in some gene in the pathway. Second, since driver mutations are relatively rare and typically a single driver mutation is sufficient to perturb a pathway, a reasonable assumption is that most patients have a single driver mutation in a pathway. Thus, the genes in a driver pathway exhibit a pattern of mutually exclusive driver mutations, where driver mutations are observed in exactly one gene in the pathway in each patient. There are numerous examples of sets of mutually exclusive mutations [5,6].