Search results

Sort By:

Limit search:

Comprehensive Analyses of Gaussian Graphical Model under Different Biological Networks

100%

Dokuzoğlu D., Purutçuoğlu V.

Acta Physica Polonica A

2017

vol. 132

issue 3

1106-1111

Naturally, genes interact with each other by forming a complicated network and the relationship between groups of genes can be shown by different functions as gene networks. Recently, there has been a growing concern in uncovering these complex structures from gene expression data by modeling them mathematically. The Gaussian graphical model is one of the very popular parametric approaches for modelling the underlying types of biochemical systems. In this study, we evaluate the performance of this probabilistic model via different criteria, from the change in dimension of the systems to the change in the distribution of the data. Hereby, we generate high dimensional simulated datasets via copulas and apply them in Gaussian graphical model to compare sensitivity, specificity, F-measure and various other accuracy measures. We also assess its performance under real datasets. We consider that such comprehensive analyses can be helpful for assessing the limitation of this common model and for developing alternative approaches, to overcome its disadvantages.

Gibbs Sampling in Inference of Copula Gaussian Graphical Model Adapted to Biological Networks

100%

Purutçuoğlu V., Farnoudkia H.

Acta Physica Polonica A

2017

vol. 132

issue 3

1112-1117

Markov chain Monte Carlo methods (MCMC) are iterative algorithms that are used in many Bayesian simulation studies, where the inference cannot be easily obtained directly through the defined model. Reversible jump MCMC methods belong to a special type of MCMC methods, in which the dimension of parameters can change in each iteration. In this study, we suggest Gibbs sampling in place of RJMCMC, to decrease the computational demand of the calculation of high dimensional systems. We evaluate the performance of the suggested algorithm in three real benchmark datasets, by comparing the accuracy and the computational demand with its strong alternatives, namely, birth-death MCMC, RJMCMC and QUIC algorithms. From the comparative analyses, we detect that Gibbs sampling improves the computational cost of RJMCMC without losing the accuracy.

Refine search results

2 Acta Physica Polonica A

2 2017

2 Purutçuoğlu V.

1 Dokuzoğlu D.

1 Farnoudkia H.

Search results

Comprehensive Analyses of Gaussian Graphical Model under Different Biological Networks

Gibbs Sampling in Inference of Copula Gaussian Graphical Model Adapted to Biological Networks