 |
    |
Automating Genetic Network Inference with Minimal Physical Experimentation Using Coevolution
Josh C. Bongard and Hod Lipson
Computational Synthesis Laboratory, Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, New York 14850JB382@cornell.edu
HL274@cornell.edu
Abstract. A major challenge in system biology is the automatic inference of gene regulation network topology—an instance of reverse engineering—based on limited local data whose collection is costly and slow. Reverse engineering implies the reconstruction of a hidden system based only on input and output data sets generated by the target system. Here we present a generalized evolutionary algorithm that can reverse engineer a hidden network based solely on input supplied to the network and the output obtained, using a minimal number of tests of the physical system. The algorithm has two stages: the first stage evolves a system hypothesis, and the second stage evolves a new experiment that should be carried out on the target system in order to extract the most information. We present the general algorithm, which we call the estimation-exploration algorithm, and demonstrate it both for the inference of gene regulatory networks without the need to perform expensive and disruptive knockout studies, and the inference of morphological properties of a robot without extensive physical testing.
Keywords: Bioinformatics, System Identification, Evolutionary Robotics
LNCS 3102, p. 333 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004