Something borrowed, something new

Precise prediction of outcomes from diverse genomic profiles

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Precise outcome predictions at an individual level from diverse genomic data is a problem of great interest as the focus on precision medicine grows. This typically requires estimation of subgroup-specific models which may differ in their mean and/or variance structure. Thus in order to accurately predict outcomes for new individuals, it's necessary to map them to a subgroup from which the prediction can be derived. The situation becomes more interesting when some predictors are common across subgroups and others are not. We describe a series of statistical methodologies under two different scenarios that can provide this mapping, as well as combine information that can be shared across subgroups, with information that is subgroup-specific. We demonstrate that prediction errors can be markedly reduced as compared to not borrowing strength at all.We then apply the approaches in order to predict colon cancer survival from DNA methylation profiles that vary by age groups, and identify those significant methylation sites that are shared across the age groups and those that are age-specific.

Original languageEnglish (US)
Title of host publicationMathematical and Statistical Applications in Life Sciences and Engineering
PublisherSpringer Singapore
Pages193-208
Number of pages16
ISBN (Electronic)9789811053702
ISBN (Print)9789811053696
DOIs
StatePublished - Dec 6 2017

Fingerprint

Genomics
Age Groups
Subgroup
Precision Medicine
Prediction
DNA Methylation
Colonic Neoplasms
Methylation
Survival
Predict
Prediction Error
Medicine
Predictors
Cancer
Profile
Vary
Scenarios
Necessary
Series
Methodology

ASJC Scopus subject areas

  • Mathematics(all)
  • Medicine(all)

Cite this

Rao, J. S., Fan, J., Kobetz, E., & Sussman, D. A. (2017). Something borrowed, something new: Precise prediction of outcomes from diverse genomic profiles. In Mathematical and Statistical Applications in Life Sciences and Engineering (pp. 193-208). Springer Singapore. https://doi.org/10.1007/978-981-10-5370-2_9

Something borrowed, something new : Precise prediction of outcomes from diverse genomic profiles. / Rao, Jonnagadda S; Fan, Jie; Kobetz, Erin; Sussman, Daniel A.

Mathematical and Statistical Applications in Life Sciences and Engineering. Springer Singapore, 2017. p. 193-208.

Research output: Chapter in Book/Report/Conference proceedingChapter

Rao, JS, Fan, J, Kobetz, E & Sussman, DA 2017, Something borrowed, something new: Precise prediction of outcomes from diverse genomic profiles. in Mathematical and Statistical Applications in Life Sciences and Engineering. Springer Singapore, pp. 193-208. https://doi.org/10.1007/978-981-10-5370-2_9
Rao JS, Fan J, Kobetz E, Sussman DA. Something borrowed, something new: Precise prediction of outcomes from diverse genomic profiles. In Mathematical and Statistical Applications in Life Sciences and Engineering. Springer Singapore. 2017. p. 193-208 https://doi.org/10.1007/978-981-10-5370-2_9
Rao, Jonnagadda S ; Fan, Jie ; Kobetz, Erin ; Sussman, Daniel A. / Something borrowed, something new : Precise prediction of outcomes from diverse genomic profiles. Mathematical and Statistical Applications in Life Sciences and Engineering. Springer Singapore, 2017. pp. 193-208
@inbook{68e487e3689b4ec285ab89114f97a5fe,
title = "Something borrowed, something new: Precise prediction of outcomes from diverse genomic profiles",
abstract = "Precise outcome predictions at an individual level from diverse genomic data is a problem of great interest as the focus on precision medicine grows. This typically requires estimation of subgroup-specific models which may differ in their mean and/or variance structure. Thus in order to accurately predict outcomes for new individuals, it's necessary to map them to a subgroup from which the prediction can be derived. The situation becomes more interesting when some predictors are common across subgroups and others are not. We describe a series of statistical methodologies under two different scenarios that can provide this mapping, as well as combine information that can be shared across subgroups, with information that is subgroup-specific. We demonstrate that prediction errors can be markedly reduced as compared to not borrowing strength at all.We then apply the approaches in order to predict colon cancer survival from DNA methylation profiles that vary by age groups, and identify those significant methylation sites that are shared across the age groups and those that are age-specific.",
author = "Rao, {Jonnagadda S} and Jie Fan and Erin Kobetz and Sussman, {Daniel A}",
year = "2017",
month = "12",
day = "6",
doi = "10.1007/978-981-10-5370-2_9",
language = "English (US)",
isbn = "9789811053696",
pages = "193--208",
booktitle = "Mathematical and Statistical Applications in Life Sciences and Engineering",
publisher = "Springer Singapore",

}

TY - CHAP

T1 - Something borrowed, something new

T2 - Precise prediction of outcomes from diverse genomic profiles

AU - Rao, Jonnagadda S

AU - Fan, Jie

AU - Kobetz, Erin

AU - Sussman, Daniel A

PY - 2017/12/6

Y1 - 2017/12/6

N2 - Precise outcome predictions at an individual level from diverse genomic data is a problem of great interest as the focus on precision medicine grows. This typically requires estimation of subgroup-specific models which may differ in their mean and/or variance structure. Thus in order to accurately predict outcomes for new individuals, it's necessary to map them to a subgroup from which the prediction can be derived. The situation becomes more interesting when some predictors are common across subgroups and others are not. We describe a series of statistical methodologies under two different scenarios that can provide this mapping, as well as combine information that can be shared across subgroups, with information that is subgroup-specific. We demonstrate that prediction errors can be markedly reduced as compared to not borrowing strength at all.We then apply the approaches in order to predict colon cancer survival from DNA methylation profiles that vary by age groups, and identify those significant methylation sites that are shared across the age groups and those that are age-specific.

AB - Precise outcome predictions at an individual level from diverse genomic data is a problem of great interest as the focus on precision medicine grows. This typically requires estimation of subgroup-specific models which may differ in their mean and/or variance structure. Thus in order to accurately predict outcomes for new individuals, it's necessary to map them to a subgroup from which the prediction can be derived. The situation becomes more interesting when some predictors are common across subgroups and others are not. We describe a series of statistical methodologies under two different scenarios that can provide this mapping, as well as combine information that can be shared across subgroups, with information that is subgroup-specific. We demonstrate that prediction errors can be markedly reduced as compared to not borrowing strength at all.We then apply the approaches in order to predict colon cancer survival from DNA methylation profiles that vary by age groups, and identify those significant methylation sites that are shared across the age groups and those that are age-specific.

UR - http://www.scopus.com/inward/record.url?scp=85043430774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043430774&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-5370-2_9

DO - 10.1007/978-981-10-5370-2_9

M3 - Chapter

SN - 9789811053696

SP - 193

EP - 208

BT - Mathematical and Statistical Applications in Life Sciences and Engineering

PB - Springer Singapore

ER -