A tutorial on learning with Bayesian networks
Learning in graphical models
Causality: models, reasoning, and inference
Causality: models, reasoning, and inference
Simulation Approaches to General Probabilistic Inference on Belief Networks
UAI '89 Proceedings of the Fifth Annual Conference on Uncertainty in Artificial Intelligence
Learning equivalence classes of bayesian-network structures
The Journal of Machine Learning Research
Constraint Minimization for Efficient Modeling of Gene Regulatory Network
PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics
Generating Synthetic Gene Regulatory Networks
PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics
Monte Carlo Strategies in Scientific Computing
Monte Carlo Strategies in Scientific Computing
| Hi-index | 0.00 |
In this paper, we apply Bayesian networks (BN) to infer gene regulatory network (GRN) model from gene expression data. This inference process, consisting of structure search and conditional probability estimation, is challenging due to the size and quality of the data that is currently available. Our previous studies for GRN reconstruction involving evolutionary search algorithm obtained a most plausible graph structure referred as Independence-map (or simply I-map). However, the limitations of the data (large number of genes and less samples) can result in many plausible structures that equally satisfy the data set. In the present study, given the network structures, we estimate the conditional probability distribution of each variable (gene) from the data set to deduce a unique minimal I-map. This is achieved by using Markov Chain Monte Carlo (MCMC) method whereby the search space is iteratively reduced resulting in the required convergence within a reasonable computation time. We present empirical results on both, the synthetic and real-life data sets and also compare our approach with the plain MCMC sampling approach. The inferred minimal I-map on the real-life yeast data set is also presented.