Semiparametric prognosis models in genomic studies

Shuangge Ma, Jian Huang, Mingyu Shi, Yang Li, Ben Chang Shia

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Development of high-throughput technologies makes it possible to survey the whole genome. Genomic studies have been extensively conducted, searching for markers with predictive power for prognosis of complex diseases such as cancer, diabetes and obesity. Most existing statistical analyses are focused on developing marker selection techniques, while little attention is paid to the underlying prognosis models. In this article, we review three commonly used prognosis models, namely the Cox, additive risk and accelerated failure time models. We conduct simulation and show that gene identification can be unsatisfactory under model misspecification.We analyze three cancer prog-nosis studies under the three models, and show that the gene identification results, prediction performance of all identified genes combined, and reproducibility of each identified gene are model-dependent. We suggest that in practical data analysis, more attention should be paid to the model assumption, and multiple models may need to be considered.

Original languageEnglish
Article numberbbp070
Pages (from-to)385-393
Number of pages9
JournalBriefings in Bioinformatics
Volume11
Issue number4
DOIs
Publication statusPublished - Feb 1 2010
Externally publishedYes

Fingerprint

Genes
Proportional Hazards Models
Neoplasms
Identification (control systems)
Obesity
Genome
Technology
Medical problems
Throughput
Surveys and Questionnaires

Keywords

  • Genomic studies
  • Model comparison
  • Semiparametric prognosis models

ASJC Scopus subject areas

  • Molecular Biology
  • Information Systems
  • Medicine(all)

Cite this

Semiparametric prognosis models in genomic studies. / Ma, Shuangge; Huang, Jian; Shi, Mingyu; Li, Yang; Shia, Ben Chang.

In: Briefings in Bioinformatics, Vol. 11, No. 4, bbp070, 01.02.2010, p. 385-393.

Research output: Contribution to journalArticle

Ma, Shuangge ; Huang, Jian ; Shi, Mingyu ; Li, Yang ; Shia, Ben Chang. / Semiparametric prognosis models in genomic studies. In: Briefings in Bioinformatics. 2010 ; Vol. 11, No. 4. pp. 385-393.
@article{95fe6a01fa0d46e5a861449bd93d99cf,
title = "Semiparametric prognosis models in genomic studies",
abstract = "Development of high-throughput technologies makes it possible to survey the whole genome. Genomic studies have been extensively conducted, searching for markers with predictive power for prognosis of complex diseases such as cancer, diabetes and obesity. Most existing statistical analyses are focused on developing marker selection techniques, while little attention is paid to the underlying prognosis models. In this article, we review three commonly used prognosis models, namely the Cox, additive risk and accelerated failure time models. We conduct simulation and show that gene identification can be unsatisfactory under model misspecification.We analyze three cancer prog-nosis studies under the three models, and show that the gene identification results, prediction performance of all identified genes combined, and reproducibility of each identified gene are model-dependent. We suggest that in practical data analysis, more attention should be paid to the model assumption, and multiple models may need to be considered.",
keywords = "Genomic studies, Model comparison, Semiparametric prognosis models",
author = "Shuangge Ma and Jian Huang and Mingyu Shi and Yang Li and Shia, {Ben Chang}",
year = "2010",
month = "2",
day = "1",
doi = "10.1093/bib/bbp070",
language = "English",
volume = "11",
pages = "385--393",
journal = "Briefings in Bioinformatics",
issn = "1467-5463",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Semiparametric prognosis models in genomic studies

AU - Ma, Shuangge

AU - Huang, Jian

AU - Shi, Mingyu

AU - Li, Yang

AU - Shia, Ben Chang

PY - 2010/2/1

Y1 - 2010/2/1

N2 - Development of high-throughput technologies makes it possible to survey the whole genome. Genomic studies have been extensively conducted, searching for markers with predictive power for prognosis of complex diseases such as cancer, diabetes and obesity. Most existing statistical analyses are focused on developing marker selection techniques, while little attention is paid to the underlying prognosis models. In this article, we review three commonly used prognosis models, namely the Cox, additive risk and accelerated failure time models. We conduct simulation and show that gene identification can be unsatisfactory under model misspecification.We analyze three cancer prog-nosis studies under the three models, and show that the gene identification results, prediction performance of all identified genes combined, and reproducibility of each identified gene are model-dependent. We suggest that in practical data analysis, more attention should be paid to the model assumption, and multiple models may need to be considered.

AB - Development of high-throughput technologies makes it possible to survey the whole genome. Genomic studies have been extensively conducted, searching for markers with predictive power for prognosis of complex diseases such as cancer, diabetes and obesity. Most existing statistical analyses are focused on developing marker selection techniques, while little attention is paid to the underlying prognosis models. In this article, we review three commonly used prognosis models, namely the Cox, additive risk and accelerated failure time models. We conduct simulation and show that gene identification can be unsatisfactory under model misspecification.We analyze three cancer prog-nosis studies under the three models, and show that the gene identification results, prediction performance of all identified genes combined, and reproducibility of each identified gene are model-dependent. We suggest that in practical data analysis, more attention should be paid to the model assumption, and multiple models may need to be considered.

KW - Genomic studies

KW - Model comparison

KW - Semiparametric prognosis models

UR - http://www.scopus.com/inward/record.url?scp=77955026459&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955026459&partnerID=8YFLogxK

U2 - 10.1093/bib/bbp070

DO - 10.1093/bib/bbp070

M3 - Article

VL - 11

SP - 385

EP - 393

JO - Briefings in Bioinformatics

JF - Briefings in Bioinformatics

SN - 1467-5463

IS - 4

M1 - bbp070

ER -