Novel Regularization Method for Biomarker Selection and Cancer Classification.
Autor: Liu, Xiao-Ying; Wang, Sai; Zhang, Hai; Zhang, Hui; Yang, Zi-Yi; Liang, Yong
Publication year: 2020
IEEE/ACM transactions on computational biology and bioinformatics
issn:1557-9964 1545-5963
doi: 10.1109/TCBB.2019.2897301
Abstract:
Variable selection has attracted more attention in big data and machine learning fields. In high dimensional data analysis, many relevant variables or variable groups are widely found. For example, people pay more interests to biological pathway or regulatory network in microarray gene expression data. In recent years, regularization methods are commonly used approaches for variable selection. Existing regularization methods generally use L(2) penalty to evaluate the grouping effect and penalty with a fixed value of q to evaluate the variable sparsity, respectively. These methods typically produce a good performance with high efficiency, but they often require the data to satisfy a certain probability distribution. In this paper, we propose a novel complex harmonic regularization (CHR) penalty function, which can approximate the combination of [Formula: see text] and regularizations with adjustable p and q to select the groups of the relevant variables. The CHR penalty function can be effectively solved by a direct path seeking algorithm. We demonstrate that the proposed CHR penalty function performs better than the state-of-the-art regularization methods in selecting groups of relevant variables and classification.
Language: eng
Rights:
Pmid: 30716046
Tags: Humans; Algorithms; Transcriptome/genetics; Computational Biology; *Machine Learning; Gene Regulatory Networks/genetics; *Biomarkers, Tumor/genetics/metabolism; *Neoplasms/classification/genetics/metabolism
Link: https://pubmed.ncbi.nlm.nih.gov/30716046/
