Microarray Quality Control using Artificial Neural Networks

Abstract: When using antibody microarrays to diagnose diseases, the process of quality control of the microarray data is an important step. Currently, a part of this process is performed manually by visual inspection. In this master project, we aim to automate the quality control in order to make it reproducible, as well as to find out which properties of the data that have the most to do with its quality. The tools we use for automation are artificial neural networks. From the microarray data, we construct variables based on the spot and background signal, as well as their spatial variations. We find that it is possible to reproduce the visual quality assessment with small networks using the mean and standard deviation of the microarrays' background as inputs. Finally, we introduce a new, calculable measure of quality and compare it to the visual quality control classification.