qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data

Classification on the basis of gene expression data derived from RNA-seq promises to become an important part of modern medicine. We propose a new classification method based on a model where the data is marginally negative binomial but dependent, thereby incorporating the dependence known to be pre...

Full description

Bibliographic Details
Main Authors:	Necla Koçhan, G. Yazgi Tutuncu, Gordon K. Smyth, Luke C. Gandolfo, Göknur Giner
Format:	Article
Language:	English
Published:	PeerJ Inc. 2019-12-01
Series:	PeerJ
Subjects:	Classification Gene expression RNA-seq Dependent count data Negative binomial distribution Quadratic discriminant analysis
Online Access:	https://peerj.com/articles/8260.pdf

id	doaj-391a4e2a63e44b91bfcf7b5831840265
record_format	Article
spelling	doaj-391a4e2a63e44b91bfcf7b58318402652020-11-25T02:14:10ZengPeerJ Inc.PeerJ2167-83592019-12-017e826010.7717/peerj.8260qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq dataNecla Koçhan0G. Yazgi Tutuncu1Gordon K. Smyth2Luke C. Gandolfo3Göknur Giner4Department of Mathematics, Izmir University of Economics, Izmir, TurkeyDepartment of Mathematics, Izmir University of Economics, Izmir, TurkeyBioinformatics Division, The Walter and Eliza Hall Institute of Medical Research, Melbourne, VIC, AustraliaBioinformatics Division, The Walter and Eliza Hall Institute of Medical Research, Melbourne, VIC, AustraliaBioinformatics Division, The Walter and Eliza Hall Institute of Medical Research, Melbourne, VIC, AustraliaClassification on the basis of gene expression data derived from RNA-seq promises to become an important part of modern medicine. We propose a new classification method based on a model where the data is marginally negative binomial but dependent, thereby incorporating the dependence known to be present between measurements from different genes. The method, called qtQDA, works by first performing a quantile transformation (qt) then applying Gaussian quadratic discriminant analysis (QDA) using regularized covariance matrix estimates. We show that qtQDA has excellent performance when applied to real data sets and has advantages over some existing approaches. An R package implementing the method is also available on https://github.com/goknurginer/qtQDA.https://peerj.com/articles/8260.pdfClassificationGene expressionRNA-seqDependent count dataNegative binomial distributionQuadratic discriminant analysis
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Necla Koçhan G. Yazgi Tutuncu Gordon K. Smyth Luke C. Gandolfo Göknur Giner
spellingShingle	Necla Koçhan G. Yazgi Tutuncu Gordon K. Smyth Luke C. Gandolfo Göknur Giner qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data PeerJ Classification Gene expression RNA-seq Dependent count data Negative binomial distribution Quadratic discriminant analysis
author_facet	Necla Koçhan G. Yazgi Tutuncu Gordon K. Smyth Luke C. Gandolfo Göknur Giner
author_sort	Necla Koçhan
title	qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data
title_short	qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data
title_full	qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data
title_fullStr	qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data
title_full_unstemmed	qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data
title_sort	qtqda: quantile transformed quadratic discriminant analysis for high-dimensional rna-seq data
publisher	PeerJ Inc.
series	PeerJ
issn	2167-8359
publishDate	2019-12-01
description	Classification on the basis of gene expression data derived from RNA-seq promises to become an important part of modern medicine. We propose a new classification method based on a model where the data is marginally negative binomial but dependent, thereby incorporating the dependence known to be present between measurements from different genes. The method, called qtQDA, works by first performing a quantile transformation (qt) then applying Gaussian quadratic discriminant analysis (QDA) using regularized covariance matrix estimates. We show that qtQDA has excellent performance when applied to real data sets and has advantages over some existing approaches. An R package implementing the method is also available on https://github.com/goknurginer/qtQDA.
topic	Classification Gene expression RNA-seq Dependent count data Negative binomial distribution Quadratic discriminant analysis
url	https://peerj.com/articles/8260.pdf
work_keys_str_mv	AT neclakochan qtqdaquantiletransformedquadraticdiscriminantanalysisforhighdimensionalrnaseqdata AT gyazgitutuncu qtqdaquantiletransformedquadraticdiscriminantanalysisforhighdimensionalrnaseqdata AT gordonksmyth qtqdaquantiletransformedquadraticdiscriminantanalysisforhighdimensionalrnaseqdata AT lukecgandolfo qtqdaquantiletransformedquadraticdiscriminantanalysisforhighdimensionalrnaseqdata AT goknurginer qtqdaquantiletransformedquadraticdiscriminantanalysisforhighdimensionalrnaseqdata
_version_	1724901306423836672

qtQDA: quantile transformed quadratic discriminant analysis for high-dimensional RNA-seq data

Similar Items