Inferring gene regulatory networks (GRNs) from time-course expression data is a major challenge in Bioinformatics. Advances in microarray technology have given rise to cheap and easy production of high-dimensional biological datasets, however, accurate analysis and prediction have been hampered by the curse of dimensionality problem whereby the number of features exponentially larger than the number of samples. Therefore, the need for the development of better statistical and predictive methods is continually on the increase. The main aim of this thesis is to develop dynamic Bayesian network (DBN) methods for analysis and prediction temporal biomedical data. A two stage computational bionetwork discovery approach is proposed. In the ovarian cancer case study, 39 out of 592 metabolomic features were selected by the Least Angle Shrinkage and Subset Operator (LASSO) with highest accuracy of 93% and 21 chemical compounds identified. The proposed approach is further improved by the application of swarm optimisation methods for parameter optimization. The improved method was applied to colorectal cancer diagnosis with 1.8% improvement in total accuracy, which was achieved with much less feature subsets of clinical importance than thousands of features when compared to previous studies. In order to address the modelling inefficiencies in inferring GRNs from time-course data, two nonlinear hybrid algorithms were proposed using support vector regression with DBN, and recurrent neural network with DBN. Experiments showed that the proposed method was better at predicting nonlinearities in GRNs than previous methods. Stratified analysis using Ovarian cancer time-course data further showed that the expression levels Prostrate differentiation factor and BTG family member 2 genes, were significantly increased by the cisplatin and oxaliplatin platinum drugs; while expression levels of Polo-like kinase and Cyclin B1 genes, were both decreased by the platinum drugs. The methods and results obtained may be useful in the designing of drugs and vaccines.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:757255 |
| Date | January 2017 |
| Creators | Akutekwe, Arinze |
| Contributors | Seker, Huseyin ; Yang, Shengxiang |
| Publisher | Northumbria University |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Source | http://nrl.northumbria.ac.uk/36183/ |
Page generated in 0.01 seconds