Initial results with EpiSwarm, a Swarm-based system investigating genetic epistasis

Many genetic diseases are not caused by the effects of a single gene, but rather, are due to multiple genes acting in concert. For complex diseases, looking at the effect of variation in a single gene may predict one disease outcome, while looking at the interactions of genetic variations across multiple genes gives us a richer understanding of the risk of disease, and may predict different outcomes. EpiSwarm is designed to model genetic epistasis (nonlinear effects among genes) using the swarm system. EpiSwarm rule agents act both as rules to explain epistatic phenomena as well as the machinery to organize the data into clusters of similar etiologies. The preliminary results reported here indicate that the system is a promising approach for visualizing and understanding clusters of disease outcomes for complex genetic diseases.