Inference of S-system Models for Large-Scale Genetic Networks

  • Authors:

  • Shinn-Ying Ho;Chih-Hung Hsieh;Fu-Chieh Yu

  • Affiliations:

  • National Chiao Tung University, Taiwan;National Chiao Tung University, Taiwan;National Chiao Tung University, Taiwan

  • Venue:
  • ICDEW '05 Proceedings of the 21st International Conference on Data Engineering Workshops
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This study proposes an efficient evolutionary algorithm, Intelligent Genetic Algorithm (IGA), for inference of S-system models of large-scale genetic networks from the observed time-series data of gene expression patterns. High performance of IGA mainly arises from an intelligent crossover operation which applies orthogonal experimental design to speed up the search by using a systematic reasoning method instead of the conventional generate-and-go method. The proposed intelligent crossover employs a divide-andconquer technique to cope with the problem of a large number of S-system parameters. The effectiveness of IGA is evaluated using simulated expression patterns. The proposed IGA with an existing problem decomposition strategy can efficiently cope with the inference problem of S-system models with several dozen genes to significant accuracy using a single- CPU personal computer.