GradientScanSurv—An exhaustive association test method for gene expression data with censored survival outcome

Ming Yi, Ruoqing Zhu, Robert M. Stephens

Research output: Contribution to journalArticle

Abstract

Accurate assessment of the association between continuous variables such as gene expression and survival is a critical aspect of precision medicine. In this report, we provide a review of some of the available survival analysis and validation tools by referencing published studies that have utilized these tools. We have identified pitfalls associated with the assumptions inherent in those applications that have the potential to impact scientific research through their potential bias. In order to overcome these pitfalls, we have developed a novel method that enables the logrank test method to handle continuous variables that comprehensively evaluates survival association with derived aggregate statistics. This is accomplished by exhaustively considering all the cutpoints across the full expression gradient. Direct side-by-side comparisons, global ROC analysis, and evaluation of the ability to capture relevant biological themes based on current understanding of RAS biology all demonstrated that the new method shows better consistency between multiple datasets of the same disease, better reproducibility and robustness, and better detection power to uncover biological relevance within the selected datasets over the available survival analysis methods on univariate gene expression and penalized linear model-based methods.

Original languageEnglish (US)
Article numbere0207590
JournalPLoS One
Volume13
Issue number12
DOIs
StatePublished - Dec 1 2018

Fingerprint

Gene expression
Gene Expression
gene expression
Medicine
Survival Analysis
testing
Statistics
methodology
Precision Medicine
cell aggregates
ROC Curve
reproducibility
Linear Models
medicine
statistics
linear models
Biological Sciences
Research
Datasets

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

GradientScanSurv—An exhaustive association test method for gene expression data with censored survival outcome. / Yi, Ming; Zhu, Ruoqing; Stephens, Robert M.

In: PLoS One, Vol. 13, No. 12, e0207590, 01.12.2018.

Research output: Contribution to journalArticle

@article{f8f2b7cd3a8542acb7d32577b26cc892,
title = "GradientScanSurv—An exhaustive association test method for gene expression data with censored survival outcome",
abstract = "Accurate assessment of the association between continuous variables such as gene expression and survival is a critical aspect of precision medicine. In this report, we provide a review of some of the available survival analysis and validation tools by referencing published studies that have utilized these tools. We have identified pitfalls associated with the assumptions inherent in those applications that have the potential to impact scientific research through their potential bias. In order to overcome these pitfalls, we have developed a novel method that enables the logrank test method to handle continuous variables that comprehensively evaluates survival association with derived aggregate statistics. This is accomplished by exhaustively considering all the cutpoints across the full expression gradient. Direct side-by-side comparisons, global ROC analysis, and evaluation of the ability to capture relevant biological themes based on current understanding of RAS biology all demonstrated that the new method shows better consistency between multiple datasets of the same disease, better reproducibility and robustness, and better detection power to uncover biological relevance within the selected datasets over the available survival analysis methods on univariate gene expression and penalized linear model-based methods.",
author = "Ming Yi and Ruoqing Zhu and Stephens, {Robert M.}",
year = "2018",
month = "12",
day = "1",
doi = "10.1371/journal.pone.0207590",
language = "English (US)",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "12",

}

TY - JOUR

T1 - GradientScanSurv—An exhaustive association test method for gene expression data with censored survival outcome

AU - Yi, Ming

AU - Zhu, Ruoqing

AU - Stephens, Robert M.

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Accurate assessment of the association between continuous variables such as gene expression and survival is a critical aspect of precision medicine. In this report, we provide a review of some of the available survival analysis and validation tools by referencing published studies that have utilized these tools. We have identified pitfalls associated with the assumptions inherent in those applications that have the potential to impact scientific research through their potential bias. In order to overcome these pitfalls, we have developed a novel method that enables the logrank test method to handle continuous variables that comprehensively evaluates survival association with derived aggregate statistics. This is accomplished by exhaustively considering all the cutpoints across the full expression gradient. Direct side-by-side comparisons, global ROC analysis, and evaluation of the ability to capture relevant biological themes based on current understanding of RAS biology all demonstrated that the new method shows better consistency between multiple datasets of the same disease, better reproducibility and robustness, and better detection power to uncover biological relevance within the selected datasets over the available survival analysis methods on univariate gene expression and penalized linear model-based methods.

AB - Accurate assessment of the association between continuous variables such as gene expression and survival is a critical aspect of precision medicine. In this report, we provide a review of some of the available survival analysis and validation tools by referencing published studies that have utilized these tools. We have identified pitfalls associated with the assumptions inherent in those applications that have the potential to impact scientific research through their potential bias. In order to overcome these pitfalls, we have developed a novel method that enables the logrank test method to handle continuous variables that comprehensively evaluates survival association with derived aggregate statistics. This is accomplished by exhaustively considering all the cutpoints across the full expression gradient. Direct side-by-side comparisons, global ROC analysis, and evaluation of the ability to capture relevant biological themes based on current understanding of RAS biology all demonstrated that the new method shows better consistency between multiple datasets of the same disease, better reproducibility and robustness, and better detection power to uncover biological relevance within the selected datasets over the available survival analysis methods on univariate gene expression and penalized linear model-based methods.

UR - http://www.scopus.com/inward/record.url?scp=85058059959&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058059959&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0207590

DO - 10.1371/journal.pone.0207590

M3 - Article

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 12

M1 - e0207590

ER -