An integrated approach to anti-cancer drug sensitivity prediction

Noah Berlow, Saad Haider, Qian Wan, Mathew Geltzeiler, Lara Davis, Charles Keller, Ranadip Pal

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

A framework for design of personalized cancer therapy requires the ability to predict the sensitivity of a tumor to anticancer drugs. The predictive modeling of tumor sensitivity to anti-cancer drugs has primarily focused on generating functions that map gene expressions and genetic mutation profiles to drug sensitivity. In this paper, we present a new approach for drug sensitivity prediction and combination therapy design based on integrated functional and genomic characterizations. The modeling approach when applied to data from the Cancer Cell Line Encyclopedia shows a significant gain in prediction accuracy as compared to elastic net and random forest techniques based on genomic characterizations. Utilizing a Mouse Embryonal Rhabdomyosarcoma cell culture and a drug screen of 60 targeted drugs, we show that predictive modeling based on functional data alone can also produce high accuracy predictions. The framework also allows us to generate personalized tumor proliferation circuits to gain further insights on the individualized biological pathway.

Original languageEnglish (US)
Article number6808481
Pages (from-to)995-1008
Number of pages14
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume11
Issue number6
DOIs
StatePublished - Nov 1 2014

Fingerprint

Tumors
Cancer
Drugs
Prediction
Pharmaceutical Preparations
Predictive Modeling
Tumor
Neoplasms
Cell culture
Gene expression
Therapy
Genomics
Cells
Embryonal Rhabdomyosarcoma
Encyclopedias
Elastic Net
Functional Data
Cell Culture
Networks (circuits)
Random Forest

Keywords

  • Drug sensitivity prediction
  • Personalized cancer therapy

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Applied Mathematics

Cite this

An integrated approach to anti-cancer drug sensitivity prediction. / Berlow, Noah; Haider, Saad; Wan, Qian; Geltzeiler, Mathew; Davis, Lara; Keller, Charles; Pal, Ranadip.

In: IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 11, No. 6, 6808481, 01.11.2014, p. 995-1008.

Research output: Contribution to journalArticle

Berlow, Noah ; Haider, Saad ; Wan, Qian ; Geltzeiler, Mathew ; Davis, Lara ; Keller, Charles ; Pal, Ranadip. / An integrated approach to anti-cancer drug sensitivity prediction. In: IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2014 ; Vol. 11, No. 6. pp. 995-1008.
@article{5bbb532588dd4c38aeced68e5491be8a,
title = "An integrated approach to anti-cancer drug sensitivity prediction",
abstract = "A framework for design of personalized cancer therapy requires the ability to predict the sensitivity of a tumor to anticancer drugs. The predictive modeling of tumor sensitivity to anti-cancer drugs has primarily focused on generating functions that map gene expressions and genetic mutation profiles to drug sensitivity. In this paper, we present a new approach for drug sensitivity prediction and combination therapy design based on integrated functional and genomic characterizations. The modeling approach when applied to data from the Cancer Cell Line Encyclopedia shows a significant gain in prediction accuracy as compared to elastic net and random forest techniques based on genomic characterizations. Utilizing a Mouse Embryonal Rhabdomyosarcoma cell culture and a drug screen of 60 targeted drugs, we show that predictive modeling based on functional data alone can also produce high accuracy predictions. The framework also allows us to generate personalized tumor proliferation circuits to gain further insights on the individualized biological pathway.",
keywords = "Drug sensitivity prediction, Personalized cancer therapy",
author = "Noah Berlow and Saad Haider and Qian Wan and Mathew Geltzeiler and Lara Davis and Charles Keller and Ranadip Pal",
year = "2014",
month = "11",
day = "1",
doi = "10.1109/TCBB.2014.2321138",
language = "English (US)",
volume = "11",
pages = "995--1008",
journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",
issn = "1545-5963",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - An integrated approach to anti-cancer drug sensitivity prediction

AU - Berlow, Noah

AU - Haider, Saad

AU - Wan, Qian

AU - Geltzeiler, Mathew

AU - Davis, Lara

AU - Keller, Charles

AU - Pal, Ranadip

PY - 2014/11/1

Y1 - 2014/11/1

N2 - A framework for design of personalized cancer therapy requires the ability to predict the sensitivity of a tumor to anticancer drugs. The predictive modeling of tumor sensitivity to anti-cancer drugs has primarily focused on generating functions that map gene expressions and genetic mutation profiles to drug sensitivity. In this paper, we present a new approach for drug sensitivity prediction and combination therapy design based on integrated functional and genomic characterizations. The modeling approach when applied to data from the Cancer Cell Line Encyclopedia shows a significant gain in prediction accuracy as compared to elastic net and random forest techniques based on genomic characterizations. Utilizing a Mouse Embryonal Rhabdomyosarcoma cell culture and a drug screen of 60 targeted drugs, we show that predictive modeling based on functional data alone can also produce high accuracy predictions. The framework also allows us to generate personalized tumor proliferation circuits to gain further insights on the individualized biological pathway.

AB - A framework for design of personalized cancer therapy requires the ability to predict the sensitivity of a tumor to anticancer drugs. The predictive modeling of tumor sensitivity to anti-cancer drugs has primarily focused on generating functions that map gene expressions and genetic mutation profiles to drug sensitivity. In this paper, we present a new approach for drug sensitivity prediction and combination therapy design based on integrated functional and genomic characterizations. The modeling approach when applied to data from the Cancer Cell Line Encyclopedia shows a significant gain in prediction accuracy as compared to elastic net and random forest techniques based on genomic characterizations. Utilizing a Mouse Embryonal Rhabdomyosarcoma cell culture and a drug screen of 60 targeted drugs, we show that predictive modeling based on functional data alone can also produce high accuracy predictions. The framework also allows us to generate personalized tumor proliferation circuits to gain further insights on the individualized biological pathway.

KW - Drug sensitivity prediction

KW - Personalized cancer therapy

UR - http://www.scopus.com/inward/record.url?scp=84919484455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919484455&partnerID=8YFLogxK

U2 - 10.1109/TCBB.2014.2321138

DO - 10.1109/TCBB.2014.2321138

M3 - Article

VL - 11

SP - 995

EP - 1008

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

SN - 1545-5963

IS - 6

M1 - 6808481

ER -