Evolutionary Synthesis of Stochastic Gene Network Models Using Feature-based Search Spaces

被引:2
作者
Imada, Janine [1 ]
Ross, Brian J. [1 ]
机构
[1] Brock Univ, St Catharines, ON L2S 3A1, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Genetic Programming; Stochastic; Statistical Features; Gene Regulatory Networks; Time Series; EXPRESSION; INFERENCE; DYNAMICS;
D O I
10.1007/s00354-009-0115-7
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A feature-based fitness function is applied in a genetic programming system to synthesize stochastic gene regulatory network models whose behaviour is defined by a time course of protein expression levels. Typically, when targeting time series data, the fitness function is based on a sum-of-errors involving the values of the fluctuating signal. While this approach is successful in many instances, its performance can deteriorate in the presence of noise and/or stochastic behaviour. This paper explores a fitness measure determined from a set of statistical features characterizing the time series' sequence of values, rather than the actual values themselves. Through a series of experiments involving modular gene regulatory network models based on the stochastic pi-calculus, it is shown to successfully target oscillating and non-oscillating signals. This practical and versatile fitness function offers an alternate approach, worthy of consideration for use in algorithms that evaluate noisy or stochastic behaviour.
引用
收藏
页码:365 / 390
页数:26
相关论文
共 49 条
[1]   Evolutionary modeling and inference of gene network [J].
Ando, S ;
Sakamoto, E ;
Iba, H .
INFORMATION SCIENCES, 2002, 145 (3-4) :237-259
[2]  
[Anonymous], ART INT SIM BEH C 20
[3]  
[Anonymous], ARXIV07124385
[4]  
[Anonymous], GECCO 08
[5]  
[Anonymous], THESIS BROCK U CANAD
[6]  
[Anonymous], ARTIFICIAL LIFE
[7]  
[Anonymous], EVOLUTIONARY COMPUTI
[8]  
[Anonymous], STOCHASTIC PI MACHIN
[9]  
[Anonymous], 2003, Genetic programming IV: routine human-competitive machine intelligence
[10]  
[Anonymous], GECCO 09