Gene expression profile feature selection method based on MFA score and redundancy exclusion

Abstract

The invention relates to a gene expression profile feature selection method based on MFA score and redundancy exclusion. Feature selection and classification of oncogene expression profiles facilitate the early diagnosis of tumors, and the causes of the tumors are explained from the angle of gene expression. Firstly, a class inter neighbor matrix Wb and a class inter neighbor matrix Ww are structured through an MFA score algorithm, consequently a class inter Laplacian matrix Lb and a class inter Laplacian matrix Lw are obtained, and lastly genes are ranked. For the feature that gene expression data are high in redundancy, the correlation among the genes is judged through Pearson correlation coefficients, the high correlation genes, namely redundancy genes, are excluded, and finally a gene subset is obtained. The gene expression profile feature selection method based on the MFA score and redundancy exclusion is suitable for training samples distributed in any space, the number of dimensions of features is further reduced by excluding the redundancy genes, the complexity of the algorithm is small, and the high classification accuracy is obtained in experiments.

Description

technical field [0001] The invention relates to the technical field of bioinformatics tumor gene data processing, and relates to a feature selection method for tumor gene expression profiles. Background technique [0002] With the continuous development of bioinformatics, a large amount of gene expression data has been obtained, especially the gene expression data of tumors. Using machine learning to analyze these data and obtain classification feature genes is helpful for early diagnosis of tumors, and has been a hot spot in bioinformatics research in recent years. Since the dimensionality of tumor gene expression data is generally thousands or even tens of thousands, it will affect the efficiency of machine learning algorithms and even reduce the effect of learning. This is the so-called "curse of dimensionality". Selecting the genes with more classification information among the genes not only improves the learning efficiency and learning accuracy, but also has important...

AI Technical Summary

Problems solved by technology

However, the feature redundancy of tumor gene expression profiles is high, and this method cannot eliminate the redundancy, which affects the classification effect to a certain extent.

Images