“…It has been known to us that DNA microarray technology provides researchers a high-throughput way to efficiently obtain the gene expression levels of a certain disease from different environments, subjects, tissues, and cell cycles and that microarray data analysis greatly facilitates the identification of disease genes and the diagnosis of cancers and tumor subtypes [1,2]. Accordingly, researchers have utilized a wealth of statistical analysis and machine learning models (e.g., classification, clustering, feature selection, network analysis, and causal inference) to analyze gene expression profiles towards understanding the underlying biological mechanisms [3,4]. However, both human and non-human factors, including, but not limited to, false positive PCR, inappropriate use of test chips, impurity of chip surface, and insufficient resolution of fluorescent images, can result in gene expression profiles with missing entries [5].…”