A flexible ensemble regression model of extreme learning machine for missing value imputation of DNA microarray data

Abstract

Missing value imputation (MVI) is important for DNA microarray data analysis because microarray data with missing values would significantly degrade the performance of the downstream analysis. Although there have been lots of MVI algorithms for dealing with the missing DNA microarray data, we note that most of them have a lack of robustness owing to only adopting the single model. In this paper, a flexible and robust MVI algorithm named EELMimpute is proposed to address missing DNA microarray data imputation problem. First, the algorithm constructs a relevant feature space for the missing target gene, where the relevant feature space only includes those co-expression genes of the target gene based on calculating their Pearson's correlation coefficients. Then, some fix-sized feature subspaces are randomly extracted from the relevant feature space to construct extreme learning machine (ELM) regression models between the extracted genes and the target gene. Furthermore, selecting those models without missing input gene values to construct the ensemble framework, and then imputing the missing gene by calculating the average output of all models included in the ensemble framework. Experimental results show that the EELMimpute algorithm is able to reduce the estimated errors in comparison with several previous imputation algorithms.