A comprehensive genetic approach for improving prediction of skin cancer risk in humans

Ana I. Vazquez, Gustavo de los Campos, Yann C Klimentidis, Guilherme J M Rosa, Daniel Gianola, Nengjun Yi, David B. Allison

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Prediction of genetic risk for disease is needed for preventive and personalized medicine. Genome-wide association studies have found unprecedented numbers of variants associated with complex human traits and diseases. However, these variants explain only a small proportion of genetic risk. Mounting evidence suggests that many traits, relevant to public health, are affected by large numbers of small-effect genes and that prediction of genetic risk to those traits and diseases could be improved by incorporating large numbers of markers into whole-genome prediction (WGP) models. We developed a WGP model incorporating thousands of markers for prediction of skin cancer risk in humans. We also considered other ways of incorporating genetic information into prediction models, such as family history or ancestry (using principal components, PCs, of informative markers). Prediction accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) estimated in a cross-validation. Incorporation of genetic information (i.e., familial relationships, PCs, or WGP) yielded a significant increase in prediction accuracy: from an AUC of 0.53 for a baseline model that accounted for nongenetic covariates to AUCs of 0.58 (pedigree), 0.62 (PCs), and 0.64 (WGP). In summary, prediction of skin cancer risk could be improved by considering genetic information and using a large number of single-nucleotide polymorphisms (SNPs) in a WGP model, which allows for the detection of patterns of genetic risk that are above and beyond those that can be captured using family history. We discuss avenues for improving prediction accuracy and speculate on the possible use of WGP to prospectively identify individuals at high risk.

Original languageEnglish (US)
Pages (from-to)1493-1502
Number of pages10
JournalGenetics
Volume192
Issue number4
DOIs
StatePublished - Dec 1 2012
Externally publishedYes

Fingerprint

Skin Neoplasms
Genome
Area Under Curve
Precision Medicine
Inborn Genetic Diseases
Preventive Medicine
Genome-Wide Association Study
Pedigree
ROC Curve
Single Nucleotide Polymorphism
Public Health
Genes

ASJC Scopus subject areas

  • Genetics

Cite this

Vazquez, A. I., de los Campos, G., Klimentidis, Y. C., Rosa, G. J. M., Gianola, D., Yi, N., & Allison, D. B. (2012). A comprehensive genetic approach for improving prediction of skin cancer risk in humans. Genetics, 192(4), 1493-1502. https://doi.org/10.1534/genetics.112.141705

A comprehensive genetic approach for improving prediction of skin cancer risk in humans. / Vazquez, Ana I.; de los Campos, Gustavo; Klimentidis, Yann C; Rosa, Guilherme J M; Gianola, Daniel; Yi, Nengjun; Allison, David B.

In: Genetics, Vol. 192, No. 4, 01.12.2012, p. 1493-1502.

Research output: Contribution to journalArticle

Vazquez, AI, de los Campos, G, Klimentidis, YC, Rosa, GJM, Gianola, D, Yi, N & Allison, DB 2012, 'A comprehensive genetic approach for improving prediction of skin cancer risk in humans', Genetics, vol. 192, no. 4, pp. 1493-1502. https://doi.org/10.1534/genetics.112.141705
Vazquez, Ana I. ; de los Campos, Gustavo ; Klimentidis, Yann C ; Rosa, Guilherme J M ; Gianola, Daniel ; Yi, Nengjun ; Allison, David B. / A comprehensive genetic approach for improving prediction of skin cancer risk in humans. In: Genetics. 2012 ; Vol. 192, No. 4. pp. 1493-1502.
@article{dd098a64a42348de82066e02a866ebf1,
title = "A comprehensive genetic approach for improving prediction of skin cancer risk in humans",
abstract = "Prediction of genetic risk for disease is needed for preventive and personalized medicine. Genome-wide association studies have found unprecedented numbers of variants associated with complex human traits and diseases. However, these variants explain only a small proportion of genetic risk. Mounting evidence suggests that many traits, relevant to public health, are affected by large numbers of small-effect genes and that prediction of genetic risk to those traits and diseases could be improved by incorporating large numbers of markers into whole-genome prediction (WGP) models. We developed a WGP model incorporating thousands of markers for prediction of skin cancer risk in humans. We also considered other ways of incorporating genetic information into prediction models, such as family history or ancestry (using principal components, PCs, of informative markers). Prediction accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) estimated in a cross-validation. Incorporation of genetic information (i.e., familial relationships, PCs, or WGP) yielded a significant increase in prediction accuracy: from an AUC of 0.53 for a baseline model that accounted for nongenetic covariates to AUCs of 0.58 (pedigree), 0.62 (PCs), and 0.64 (WGP). In summary, prediction of skin cancer risk could be improved by considering genetic information and using a large number of single-nucleotide polymorphisms (SNPs) in a WGP model, which allows for the detection of patterns of genetic risk that are above and beyond those that can be captured using family history. We discuss avenues for improving prediction accuracy and speculate on the possible use of WGP to prospectively identify individuals at high risk.",
author = "Vazquez, {Ana I.} and {de los Campos}, Gustavo and Klimentidis, {Yann C} and Rosa, {Guilherme J M} and Daniel Gianola and Nengjun Yi and Allison, {David B.}",
year = "2012",
month = "12",
day = "1",
doi = "10.1534/genetics.112.141705",
language = "English (US)",
volume = "192",
pages = "1493--1502",
journal = "Genetics",
issn = "0016-6731",
publisher = "Genetics Society of America",
number = "4",

}

TY - JOUR

T1 - A comprehensive genetic approach for improving prediction of skin cancer risk in humans

AU - Vazquez, Ana I.

AU - de los Campos, Gustavo

AU - Klimentidis, Yann C

AU - Rosa, Guilherme J M

AU - Gianola, Daniel

AU - Yi, Nengjun

AU - Allison, David B.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Prediction of genetic risk for disease is needed for preventive and personalized medicine. Genome-wide association studies have found unprecedented numbers of variants associated with complex human traits and diseases. However, these variants explain only a small proportion of genetic risk. Mounting evidence suggests that many traits, relevant to public health, are affected by large numbers of small-effect genes and that prediction of genetic risk to those traits and diseases could be improved by incorporating large numbers of markers into whole-genome prediction (WGP) models. We developed a WGP model incorporating thousands of markers for prediction of skin cancer risk in humans. We also considered other ways of incorporating genetic information into prediction models, such as family history or ancestry (using principal components, PCs, of informative markers). Prediction accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) estimated in a cross-validation. Incorporation of genetic information (i.e., familial relationships, PCs, or WGP) yielded a significant increase in prediction accuracy: from an AUC of 0.53 for a baseline model that accounted for nongenetic covariates to AUCs of 0.58 (pedigree), 0.62 (PCs), and 0.64 (WGP). In summary, prediction of skin cancer risk could be improved by considering genetic information and using a large number of single-nucleotide polymorphisms (SNPs) in a WGP model, which allows for the detection of patterns of genetic risk that are above and beyond those that can be captured using family history. We discuss avenues for improving prediction accuracy and speculate on the possible use of WGP to prospectively identify individuals at high risk.

AB - Prediction of genetic risk for disease is needed for preventive and personalized medicine. Genome-wide association studies have found unprecedented numbers of variants associated with complex human traits and diseases. However, these variants explain only a small proportion of genetic risk. Mounting evidence suggests that many traits, relevant to public health, are affected by large numbers of small-effect genes and that prediction of genetic risk to those traits and diseases could be improved by incorporating large numbers of markers into whole-genome prediction (WGP) models. We developed a WGP model incorporating thousands of markers for prediction of skin cancer risk in humans. We also considered other ways of incorporating genetic information into prediction models, such as family history or ancestry (using principal components, PCs, of informative markers). Prediction accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) estimated in a cross-validation. Incorporation of genetic information (i.e., familial relationships, PCs, or WGP) yielded a significant increase in prediction accuracy: from an AUC of 0.53 for a baseline model that accounted for nongenetic covariates to AUCs of 0.58 (pedigree), 0.62 (PCs), and 0.64 (WGP). In summary, prediction of skin cancer risk could be improved by considering genetic information and using a large number of single-nucleotide polymorphisms (SNPs) in a WGP model, which allows for the detection of patterns of genetic risk that are above and beyond those that can be captured using family history. We discuss avenues for improving prediction accuracy and speculate on the possible use of WGP to prospectively identify individuals at high risk.

UR - http://www.scopus.com/inward/record.url?scp=84870690746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870690746&partnerID=8YFLogxK

U2 - 10.1534/genetics.112.141705

DO - 10.1534/genetics.112.141705

M3 - Article

C2 - 23051645

AN - SCOPUS:84870690746

VL - 192

SP - 1493

EP - 1502

JO - Genetics

JF - Genetics

SN - 0016-6731

IS - 4

ER -