基于计算智能的时延基因调控网络建模研究

The modeling of gene regulatory network from gene expression data is one of the effective methods of systems biology research in recent years. To accurately construct gene regulatory networks (GRN) will greatly improve the accuracy of disease treatment, deepen understanding the cellular activities and the function mechanisms of causative genes, and have a profound impact on prevention, diagnosis and treatment of complex diseases. Gene regulatory network has the characteristics such as time-delayed and strongly nonlinear, so this project will utilize voting strategy to select reliable differential expressed genes from the high-throughput sequencing data. Combining with steady-state expression data, multi-step filtering strategy and differential equation model are proposed to model steady-state gene regulatory network. Combining with time expression data, flexible neural tree model is utilized for reverse engineering of time-delayed gene regulatory networks. Time-delayed S-system model is used to identify time-delayed and instantaneous regulatory relationships in order to construct time-delayed gene regulatory network. At last, the modeling framework of gene regulatory network can be eventually formed. This project will be a theoretical foundation for the analysis and understanding of complex life activity.

利用基因表达数据实现基因调控网络建模是近年来研究系统生物学的有效手段之一。准确地构建基因调控网络，会大大改善疾病治疗的精度，对于加深细胞活动和致病基因功能机制的理解以及复杂疾病的预防、诊断和治疗具有深远的影响。基于基因调控网络具有时延性和强非线性的特点，本课题在前期已获得高通量测序数据的基础上，利用投票原理检测可信度高的差异表达基因；结合稳态表达数据，利用多步过滤策略和微分方程模型实现稳态基因调控网络建模；结合时间表达数据，利用柔性神经树模型实现时延基因调控网络的反向工程建模；利用时滞S-system模型识别基因间的时延和瞬时调控关系，构造时延基因调控网络。最终形成一个基因调控网络的建模框架，为实现分析和了解复杂的生命活动奠定基础。

利用基因表达数据实现基因调控网络建模是近年来研究系统生物学的有效手段之一。准确地构建基因调控网络，会大大改善疾病治疗的精度，对于加深细胞活动和致病基因功能机制的理解以及复杂疾病的预防、诊断和治疗具有深远的影响。基于基因调控网络具有时延性和强非线性的特点，本课题在前期已获得高通量测序数据的基础上，设计预处理框架，筛选出与疾病相关可信度高的差异表达基因、SNPs和InDels。结合稳态基因表达数据，提出新颖的过滤适应值函数和非线性微分方程构建稳态基因调控网络；提出混合监督学习方法和过滤算法识别基因调控网络。结合时间表达数据，提出混合打分方法和复值柔性神经树模型实现时延基因调控网络的反向工程建模；提出并行限制性基因表达式编程和时滞S-system模型识别基因间的时延和瞬时调控关系，构造时延基因调控网络。最终形成一个基因调控网络的建模框架，为实现分析和了解复杂的生命活动奠定基础。