Estimating conditional probabilities for the detection of unfavorable copy number alterations in a targeted therapy

Fang Han Hsu, Edward R. Dougherty, Yidong Chen, Erchin Serpedin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Emerging targeted therapies have shown benefits such as less toxicity and higher effectiveness in specific types of cancer treatment; however, the accessibility of these advantages may rely on correct identification of suitable patients, which remains highly immature. We assume that copy number profiles, being accessible genomic data via microarray techniques, can provide useful information regarding drug response and shed light on personalized therapy. Based on the mechanism of action (MOA) of trastuzumab in the HER2 signaling pathway, a Bayesian network model in which copy number alterations (CNAs) serve as latent parents modifying signal transduction is applied. Two model parameters M-score and R -value which stand for the qualitative and quantitative effects of CNAs on drug effectiveness and are functions of conditional probabilities (CPs), are defined. An expectation-maximization (EM) algorithm is developed for estimating CPs, M-scores, and R-values from continuous measures, such as microarray data. We show through simulations that the EM algorithm can outperform classical threshold-based methods in the estimation of CPs and thereby provide improved performance for the detection of unfavorable CNAs. Several candidates of unfavorable CNAs to the trastuzumab therapy in breast cancer are provided in a real data example.

Original languageEnglish
Article number6524018
Pages (from-to)2933-2942
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume60
Issue number10
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Microarrays
Signal transduction
Oncology
Bayesian networks
Toxicity
Statistical Models

Keywords

  • Bayesian network
  • copy number
  • drug response
  • expectation-maximization algorithm
  • gene expression

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Estimating conditional probabilities for the detection of unfavorable copy number alterations in a targeted therapy. / Hsu, Fang Han; Dougherty, Edward R.; Chen, Yidong; Serpedin, Erchin.

In: IEEE Transactions on Biomedical Engineering, Vol. 60, No. 10, 6524018, 2013, p. 2933-2942.

Research output: Contribution to journalArticle

@article{c204b99056054f4d9065b683a06f0108,
title = "Estimating conditional probabilities for the detection of unfavorable copy number alterations in a targeted therapy",
abstract = "Emerging targeted therapies have shown benefits such as less toxicity and higher effectiveness in specific types of cancer treatment; however, the accessibility of these advantages may rely on correct identification of suitable patients, which remains highly immature. We assume that copy number profiles, being accessible genomic data via microarray techniques, can provide useful information regarding drug response and shed light on personalized therapy. Based on the mechanism of action (MOA) of trastuzumab in the HER2 signaling pathway, a Bayesian network model in which copy number alterations (CNAs) serve as latent parents modifying signal transduction is applied. Two model parameters M-score and R -value which stand for the qualitative and quantitative effects of CNAs on drug effectiveness and are functions of conditional probabilities (CPs), are defined. An expectation-maximization (EM) algorithm is developed for estimating CPs, M-scores, and R-values from continuous measures, such as microarray data. We show through simulations that the EM algorithm can outperform classical threshold-based methods in the estimation of CPs and thereby provide improved performance for the detection of unfavorable CNAs. Several candidates of unfavorable CNAs to the trastuzumab therapy in breast cancer are provided in a real data example.",
keywords = "Bayesian network, copy number, drug response, expectation-maximization algorithm, gene expression",
author = "Hsu, {Fang Han} and Dougherty, {Edward R.} and Yidong Chen and Erchin Serpedin",
year = "2013",
doi = "10.1109/TBME.2013.2266356",
language = "English",
volume = "60",
pages = "2933--2942",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - Estimating conditional probabilities for the detection of unfavorable copy number alterations in a targeted therapy

AU - Hsu, Fang Han

AU - Dougherty, Edward R.

AU - Chen, Yidong

AU - Serpedin, Erchin

PY - 2013

Y1 - 2013

N2 - Emerging targeted therapies have shown benefits such as less toxicity and higher effectiveness in specific types of cancer treatment; however, the accessibility of these advantages may rely on correct identification of suitable patients, which remains highly immature. We assume that copy number profiles, being accessible genomic data via microarray techniques, can provide useful information regarding drug response and shed light on personalized therapy. Based on the mechanism of action (MOA) of trastuzumab in the HER2 signaling pathway, a Bayesian network model in which copy number alterations (CNAs) serve as latent parents modifying signal transduction is applied. Two model parameters M-score and R -value which stand for the qualitative and quantitative effects of CNAs on drug effectiveness and are functions of conditional probabilities (CPs), are defined. An expectation-maximization (EM) algorithm is developed for estimating CPs, M-scores, and R-values from continuous measures, such as microarray data. We show through simulations that the EM algorithm can outperform classical threshold-based methods in the estimation of CPs and thereby provide improved performance for the detection of unfavorable CNAs. Several candidates of unfavorable CNAs to the trastuzumab therapy in breast cancer are provided in a real data example.

AB - Emerging targeted therapies have shown benefits such as less toxicity and higher effectiveness in specific types of cancer treatment; however, the accessibility of these advantages may rely on correct identification of suitable patients, which remains highly immature. We assume that copy number profiles, being accessible genomic data via microarray techniques, can provide useful information regarding drug response and shed light on personalized therapy. Based on the mechanism of action (MOA) of trastuzumab in the HER2 signaling pathway, a Bayesian network model in which copy number alterations (CNAs) serve as latent parents modifying signal transduction is applied. Two model parameters M-score and R -value which stand for the qualitative and quantitative effects of CNAs on drug effectiveness and are functions of conditional probabilities (CPs), are defined. An expectation-maximization (EM) algorithm is developed for estimating CPs, M-scores, and R-values from continuous measures, such as microarray data. We show through simulations that the EM algorithm can outperform classical threshold-based methods in the estimation of CPs and thereby provide improved performance for the detection of unfavorable CNAs. Several candidates of unfavorable CNAs to the trastuzumab therapy in breast cancer are provided in a real data example.

KW - Bayesian network

KW - copy number

KW - drug response

KW - expectation-maximization algorithm

KW - gene expression

UR - http://www.scopus.com/inward/record.url?scp=84884544802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884544802&partnerID=8YFLogxK

U2 - 10.1109/TBME.2013.2266356

DO - 10.1109/TBME.2013.2266356

M3 - Article

VL - 60

SP - 2933

EP - 2942

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

M1 - 6524018

ER -