【摘要】 基于量子粒子群(QPSO)算法分析和重构了基因调控网络。利用S-系统模型进行基因调控网络的模拟,基本方法以真实实验数据与模拟数据的差的平方和作为目标函数进行迭代优化,只能预测数目很少的参数并且算法的收敛率很低。依据基因网络的稀疏性,提出了基于QPSO算法的逐步优化策略,将整个优化过程分为三个阶段,通过逐步确定无效参数的位置来简化模型。仿真实验基于QPSO算法逐步优化策略成功实现了一个包含5个节点60个参数的S-系统优化。更多还原

【Abstract】 This paper discussed the analysis and reconstruction of genetic regulatory network based on QPSO algorithm,defined the problem based on the S-system model as an estimation problem of the S-system parameter. Used the sum of squared errors between experimental values and predicted values as the objective optimization function in the basic method,but it could predict only a very small number of parameters and the convergence rate was low. Proposed the gradual optimization strategy based on QPSO algorithm with the sparsity of the genetic network. The optimization procedure became simper with the futile parameters gradually fixed. The dynamic of a small genetic network constructs with 60 parameters for 5 network variables is successfully inferred in experiments by the improved algorithm.更多还原