Parameter inference of general nonlinear dynamical models of gene regulatory networks from small and noisy time series

被引：10

作者：

Berrones, Arturo ^{[1
]}

Jimenez, Edgar ^{[2
]}

Aracelia Alcorta-Garcia, Maria ^{[2
]}

Almaguer, F-Javier ^{[2
]}

Pena, Brenda ^{[1
]}

机构：

[1] Univ Autonoma Nuevo Leon, Posgrado Ingn Sistemas, Fac Ingn Mecan & Elect, San Nicolas De Los Garza 66455, NL, Mexico

[2] Univ Autonoma Nuevo Leon, Posgrado Ingn Sistemas, Fac Ciencias Fis Matemat, San Nicolas De Los Garza 66455, NL, Mexico

来源：

NEUROCOMPUTING | 2016年 / 175卷

关键词：

CTRNN; Genetic regulatory networks; Genetic expression time series; Bayesian inference; DIFFERENTIAL EVOLUTION; ALGORITHMS;

D O I：

10.1016/j.neucom.2015.10.095

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new inference approach to general dynamic models of gene regulatory networks (GRN) is introduced. The methodology is based on a Maximum a Posteriori (MAP) smoothing of time series data from which mean field variables of the dynamics are estimated. The interactions are modeled by a Continuous Time Recurrent Neural Network (CTRNN). Parameter estimation of the CTRNN is performed without the need to numerically solve the system of nonlinear differential equations. The method is tested on a benchmark of real genetic networks and displays superior performance, in terms of the mean squared error of the expression dynamics, compared to other formalisms. (C) 2015 Elsevier B.V. All rights reserved.

引用

页码：555 / 563

页数：9

共 34 条

[1]

[Anonymous], 1996, BAYESIAN LEARNING NE

[2] Recovering data from scanned graphs: Performance of Frantz's g3data software [J].