My PhD research focuses on the recommendation of optimal designs for two-colour microarray experiments. Two-colour microarrays are a technology used to investigate the behaviour of many thousands of genes in a single experiment. This technology has created the potential for making significant advances in the field of bioinformatics. Careful statistical design is crucial to realize the full potential of microarray technology. My research has focused on the recommendation of designs that are optimal in terms of precision for effects that are of scientific interest, making the most effective use of available resources. Based on statistical efficiency, the optimality criterion used is Pareto optimality. A design is defined to be Pareto optimal if there is no other design that leads to equal or greater precision for each effect of scientific interest and strictly greater precision for at least one. My PhD thesis was submitted in June and key aspects of my research are summarised below. Pareto optimality enables the recommendation of designs that are particularly efficient for the effects that are of scientific interest. I have developed methodology to cater for effects of interest that correspond to contrasts rather than solely considering parameters of the statistical linear model. My approach also caters for additional experimental considerations such as contrasts that are of equal scientific interest. During my PhD, I have provided advice regarding the design of two-colour microarray experiments aimed at discovering the genetic basis of medical conditions. For large experiments, it is not feasible to examine all possible designs in an exhaustive search for Pareto optimal designs. I have adapted the multiple objective metaheuristic method of Pareto simulated annealing to the microarray context. The aim of Pareto simulated annealing is to generate an approximation to the set of Pareto optimal designs in a relatively short time. At each iteration, a sample of generating designs is used to explore the design space in an efficient way. This involves the setting of a number of Pareto simulated annealing parameters and the development of appropriate quality measures. I have developed algorithms to search systematically for the optimal values of the tuning parameters based on Pareto simulated annealing and response surface methodology. / Thesis (Ph.D.) -- University of Adelaide, School of Mathematical Sciences, 2010
| Identifer | oai:union.ndltd.org:ADTP/288242 |
| Date | January 2010 |
| Creators | Sanchez, Penny S. |
| Source Sets | Australiasian Digital Theses Program |
| Detected Language | English |
Page generated in 0.0549 seconds