TY - GEN

T1 - Evolutionary divide-and-conquer approach to inferring S-system models of genetic networks

AU - Ho, Shinn-Ying

AU - Hsieh, Chih Hung

AU - Yu, Fu Chieh

AU - Huang, Hui Ling

PY - 2005/10/31

Y1 - 2005/10/31

N2 - This paper proposes an efficient evolutionary divide-and-conquer approach (EDACA) to inferring S-system models of genetic networks from time-series data of gene expression. Inference of an S-system model has 2N(N+1) parameters to be optimized where N is the number of genes in a genetic network. To cope with higher dimensionality, the proposed approach consists of two stages where each uses a divide-and-conquer strategy. The optimization problem is first decomposed into N subproblems having 2(N+1) parameters each. At the first stage, each subproblem is solved using a novel intelligent genetic algorithm (IGA) with intelligent crossover based on orthogonal experimental design (OED). The intelligent crossover divides two parents into n pairs of parameter groups, economically identifies the potentially better one of two groups of each pair, and systematically obtains a potentially good approximation to the best one of all 2n combinations using at most 2n function evaluations. At the second stage, the obtained N solutions to the N subproblems are combined and refined using an OED-based simulated annealing algorithm (OSA) for handling noisy gene expression data. The effectiveness of EDACA is evaluated using simulated expression patterns with/without noise running on a single-CPU PC. It is shown that: 1) IGA is efficient enough to solve subproblems; 2) IGA is significantly superior to the existing method of using GA with simplex crossover; and 3) EDACA performs well in inferring S-system models of genetic networks from small-noise gene expression data.

AB - This paper proposes an efficient evolutionary divide-and-conquer approach (EDACA) to inferring S-system models of genetic networks from time-series data of gene expression. Inference of an S-system model has 2N(N+1) parameters to be optimized where N is the number of genes in a genetic network. To cope with higher dimensionality, the proposed approach consists of two stages where each uses a divide-and-conquer strategy. The optimization problem is first decomposed into N subproblems having 2(N+1) parameters each. At the first stage, each subproblem is solved using a novel intelligent genetic algorithm (IGA) with intelligent crossover based on orthogonal experimental design (OED). The intelligent crossover divides two parents into n pairs of parameter groups, economically identifies the potentially better one of two groups of each pair, and systematically obtains a potentially good approximation to the best one of all 2n combinations using at most 2n function evaluations. At the second stage, the obtained N solutions to the N subproblems are combined and refined using an OED-based simulated annealing algorithm (OSA) for handling noisy gene expression data. The effectiveness of EDACA is evaluated using simulated expression patterns with/without noise running on a single-CPU PC. It is shown that: 1) IGA is efficient enough to solve subproblems; 2) IGA is significantly superior to the existing method of using GA with simplex crossover; and 3) EDACA performs well in inferring S-system models of genetic networks from small-noise gene expression data.

UR - http://www.scopus.com/inward/record.url?scp=27144551934&partnerID=8YFLogxK

U2 - 10.1109/CEC.2005.1554750

DO - 10.1109/CEC.2005.1554750

M3 - Conference contribution

AN - SCOPUS:27144551934

SN - 0780393635

T3 - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings

SP - 691

EP - 698

BT - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings

Y2 - 2 September 2005 through 5 September 2005

ER -