Recently, researchers have made great progress towards uncovering the genetics behind autism and schizophrenia. By sequencing families, they have found de novo variants occurring only in affected individuals, and implicating hundreds of genes. With this wave of new information the question becomes how to tie these rare mutations together into a cohesive picture of disease risk. Biological networks represent an intuitive answer, as different mutations which converge on the same phenotype must share some underlying biological process. In this talk, I present our phenotype network, which uses biological function to assign each gene pair a score proportional to the likelihood that those genes are risk factors for the same disease. We search this network for strongly connected clusters containing putative disease genes from de novo events. Our method helps to select genes from larger genomic events, identify spurious results, and elucidate the real physical consequences of putative disease mutations leading to a better understanding of the pathophysiology of the diseases.