PALO: a probabilistic hill-climbing algorithm
Artificial Intelligence
Hi-index | 0.00 |
With the growth of genetic information, new methods and computational approaches are needed to understand the volume of data. In this paper, we first define a class of functions (additive epistatic effects (AEE) functions) which capture the notion of additive combination of epistatic effects. We propose an exhaustive bootstrapping methodology to search for an AEE function which most closely approximates an observed phenotype. Lastly, we present a computational approach, which takes advantage of several features of the CRAY SV1ex, to obtain an optimized implementation of this search method. The program has been tested with several test cases and good results are shown with varying amounts of noise added to the test phenotype.