Logo image
A SPARSE NEGATIVE BINOMIAL CLASSIFIER WITH COVARIATE ADJUSTMENT FOR RNA-SEQ DATA
期刊文章   同儕審查

A SPARSE NEGATIVE BINOMIAL CLASSIFIER WITH COVARIATE ADJUSTMENT FOR RNA-SEQ DATA

Tanbin Rahman, Hsin-En Huang, Yujia Li, An-Shun Tai, Wen-Ping Hseih, Colleen A. McClungGeorge Tseng
Annals of Applied Statistics, 卷.16(2), 頁碼.1071-1089
06/2022

摘要

Classification count data covariate adjustment RNA-seq data Statistics and Probability Modeling and Simulation Statistics Probability and Uncertainty
Supervised machine learning methods have been increasingly used in biomedical research and clinical practice. In transcriptomic applications, RNA-seq data have become dominating and have gradually replaced tradi-tional microarray, due to their reduced background noise and increased digital precision. Most existing machine learning methods are, however, designed for continuous intensities of microarray and are not suitable for RNA-seq count data. In this paper we develop a negative binomial model via general-ized linear model framework with double regularization for gene and covari-ate sparsity to accommodate three key elements: adequate modeling of count data with overdispersion, gene selection and adjustment for covariate effect. The proposed sparse negative binomial classifier (snbClass) is evaluated in simulations and two real applications of multidisease postmortem brain tissue RNA-seq data and cervical tumor miRNA-seq data to demonstrate its superior performance in prediction accuracy and feature selection.

相關連結

指標

1 檢視次數

詳細資料

Logo image