A scalable approach for inferring transcriptional regulation in the yeast cell cycle
Proceedings of the 2nd ACM Conference on Bioinformatics, Computational Biology and Biomedicine
| Hi-index | 0.00 |
The inference of Gene Regulatory networks (GRN) from microarrray data suffers from the low accuracy and the excessive computation time. Biological domain knowledge of the cellular process, from which the data is generated, is believed to be effective in addressing such challenges. In this paper, we have used two biological features of gene regulation of yeast cell cycle: 1) a high proportion of the Cell Cycle Regulated genes are periodically expressed, and 2) genes are both co-expressed and co-regulated. Together with the computational implementation of these features, we have learnt regulators of both individual and co-expressed genes using Dynamic Bayesian Networks. The proposed 2-stage GRN model has been found to be more computationally efficient and topologically accurate compared to other existing models.