Computational modelling strategies for gene regulatory network reconstruction
- Authors: Sehgal, Muhammad Shoaib B , Gondal, Iqbal , Dooley, Laurence
- Date: 2008
- Type: Text , Book chapter
- Relation: Studies in Computational Intelligence p. 207-220
- Full Text:
- Reviewed:
- Description: Gene Regulatory Network (GRN) modelling infers genetic interactions between different genes and other cellular components to elucidate the cellular functionality. This GRN modelling has overwhelming applications in biology starting from diagnosis through to drug target identification. Several GRN modelling methods have been proposed in the literature, and it is important to study the relative merits and demerits of each method. This chapter provides a comprehensive comparative study on GRN reconstruction algorithms. The methods discussed in this chapter are diverse and vary from simple similarity based methods to state of the art hybrid and probabilistic methods. In addition, the chapter also underpins the need of strategies which should be able to model the stochastic behavior of gene regulation in the presence of limited number of samples, noisy data, multi-collinearity for high number of genes.
Gene expression imputation techniques for robust post genomic knowledge discovery
- Authors: Sehgal, Muhammad Shoaib B , Gondal, Iqbal , Dooley, Laurence
- Date: 2008
- Type: Text , Book chapter
- Relation: Studies in Computational Intelligence p. 185-206
- Full Text: false
- Reviewed:
- Description: Microarrays measure expression patterns of thousands of genes at a time, under same or diverse conditions, to facilitate faster analysis of biological processes. This gene expression data is being widely used for diagnosis, prognosis and tailored drug discovery. Microarray data, however, commonly contains missing values, which can have high impact on subsequent biological knowledge discovery methods. This has been catalyst for the manifest of different imputation algorithms, including Collateral Missing Value Estimation (CMVE), Bayesian Principal Component Analysis (BPCA), Least Square Impute (LSImpute), Local Least Square Impute (LLSImpute) and K-Nearest Neighbour (KNN). This Chapter investigates the impact of missing values on post genomic knowledge discovery methods like, Gene Selection and Gene Regulatory Network (GRN) reconstruction. A framework for robust subsequent biological knowledge inference has been proposed which has shown significant improvements in the outcomes of Gene Selection and GRN reconstruction methods.