Um método de estimação de expressões gênicas de câncer de mama com base em correlação

Abstract

Gene expression data extracted through microarray technology often suffer from lost value issues due to problems such as dust or scratches on the slide. In breast cancer databases, the subsequent analysis and subtype classification can suffer greatly from missing data, so it is essential to address this problem. Several approaches to estimate these values in gene expression data have been developed, but the task is difficult due to factors such as the existence or not of a correlation structure in the data, the high dimensionality of the data (number of genes x number of samples), and the patterns and mechanisms of absence. In this research, we developed a method to estimate missing values in gene expressions of breast cancer, that deals with the high dimensionality of the data through the use of a set of genes that best characterize breast cancer and can contribute to a more accurate classification of subtypes.