Optimization of cDNA Microarray Experimental Designs Using an Evolutionary Algorithm

Authors:
Cedric Gondro;Brian P. Kinghorn
Affiliations:
-;-
Venue:
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Year:
2008

Citing 5
Cited 0

How to solve it: modern heuristics

How to solve it: modern heuristics
Algorithm 97: Shortest path

Communications of the ACM
An experimental evaluation of a loop versus a reference design for two-channel microarrays

Bioinformatics
Multiobjective Evolutionary Algorithms: Analyzing the State-of-the-Art

Evolutionary Computation
Comparison of Multiobjective Evolutionary Algorithms: Empirical Results

Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The cDNA microarray is an important tool for generating large datasets of gene expression measurements.An efficient design is critical to ensure that the experiment will be able to address relevant biologicalquestions. Microarray experimental design can be treated as a multicriterion optimization problem. For thisclass of problems evolutionary algorithms (EAs) are well suited, as they can search the solution space andevolve a design that optimizes the parameters of interest based on their relative value to the researcher undera given set of constraints. This paper introduces the use of EAs for optimization of experimental designs ofspotted microarrays using a weighted objective function. The EA and the various criteria relevant to designoptimization are discussed. Evolved designs are compared with designs obtained through exhaustive searchwith results suggesting that the EA can find just as efficient optimal or near-optimal designs within atractable timeframe.