Recurrent neural network based hybrid model for reconstructing gene regulatory network. (October 2016)

• Record Type: Journal Article
• Authors: Raza, Khalid; Alam, Mansaf
• Is Part Of: Computational biology and chemistry. Volume 64(2016)
• Page Start: 322
• Page End: 334
• Publication Date: 2016-10
• Subjects: Recurrent neural network -- Gene regulatory network model -- Gene expression -- Kalman filter; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2016.08.002
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: We proposed a recurrent neural network (RNN) based hybrid model of gene regulatory network (GRN). Due to noise in microarray data, extended Kalman filer has been introduced in the weight update equation of backpropagation through time (BPTT) training algorithm. We tested the proposed model on four different benchmark datasets − two real networks and two simulated network. On all four datasets, the proposed model outperforms the other similar kind of techniques. Also, 5% Gaussian noise has been injected into the dataset to test the performance of the propose model. The result proves that noises in the data have negligible effect on the performance of the model. This model can be much useful for disease response prediction, novel drug development and treatments. Abstract: One of the exciting problems in systems biology research is to decipher how genome controls the development of complex biological system. The gene regulatory networks (GRNs) help in the identification of regulatory interactions between genes and offer fruitful information related to functional role of individual gene in a cellular system. Discovering GRNs lead to a wide range of applications, including identification of disease related pathways providing novel tentative drug targets, helps to predict disease response, and also assists in diagnosing various diseases including cancer. Reconstruction of GRNs from available biological data is still an open problem. This paper proposes a recurrent neural network (RNN) based model of GRN, hybridized with generalized extended Kalman filter for weight update in backpropagation through time training algorithm. The RNN is a complex neural network that gives a better settlement between biological closeness and mathematical flexibility to model GRN; and is also able to capture complex, non-linear and dynamic relationships among variables. Gene expression data are inherently noisy and Kalman filter performs well for estimation problem even in noisy data. Hence, we applied non-linear version of Kalman filter, known as generalized extended Kalman filter, for weight update during RNN training. The developed model has been tested on four benchmark networks such as DNA SOS repair network, IRMA network, and two synthetic networks from DREAM Challenge. We performed a comparison of our results with other state-of-the-art techniques which shows superiority of our proposed model. Further, 5% Gaussian noise has been induced in the dataset and result of the proposed model shows negligible effect of noise on results, demonstrating the noise tolerance capability of the model.