Title: Handling batch effects on cross-platform classification of microarray data

Authors: Worrawat Engchuan; Asawin Meechai; Sissades Tongsima; Jonathan H. Chan

Addresses: Data and Knowledge Engineering Laboratory (D-Lab), School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok 10140, Thailand ' Department of Chemical Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok 10140, Thailand ' Biostatistics and Informatics Laboratory, Genome Technology Research Unit, National Center for Genetic Engineering and Biotechnology (BIOTEC), Pathumthani 12120, Thailand ' Data and Knowledge Engineering Laboratory (D-Lab), School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok 10140, Thailand

Abstract: Gene-set-based microarray analysis is commonly applied in the classification of complex diseases. However, the robustness of a classifier is normally limited by the small number of samples in many microarray datasets. Although a merged dataset from multiple experiments may improve classification performance, batch effects or technical/biological variations among these experiments may eventually confound the analysis. Besides the batch effects, merging multiple microarray datasets from different platforms can generate missing values, due to a different number of covered genes. In this work, we extend previous works that focused on the missing value incident by further exploring the impact of batch effects on cross-platform classification. Two quality measures of data purity are proposed and two data imputation methods are compared. The results show that by doing batch correction the quality of the merged data is improved significantly. Furthermore, the classification performance is high when the normalised purity is above a certain threshold.

Keywords: batch effects; batch effect correction; classification; cross-platform analysis; microarray data; gene sets; complex diseases; data imputation; BPCA; kNN; ComBat; data purity; bioinformatics; k-nearest neighbour; gene expression data; feature selection.

DOI: 10.1504/IJAIP.2016.074775

International Journal of Advanced Intelligence Paradigms, 2016 Vol.8 No.1, pp.59 - 76

Received: 23 Mar 2015
Accepted: 27 May 2015
Published online: 17 Feb 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article