Genetic programming for anticancer therapeutic response prediction using the NCI-60 dataset

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Statistical methods, and in particular machine learning, have been increasingly used in the drug development workflow. Among the existing machine learning methods, we have been specifically concerned with genetic programming. We present a genetic programming-based framework for predicting anticancer therapeutic response. We use the NCI-60 microarray dataset and we look for a relationship between gene expressions and responses to oncology drugs Fluorouracil, Fludarabine, Floxuridine and Cytarabine. We aim at identifying, from genomic measurements of biopsies, the likelihood to develop drug resistance. Experimental results. and their comparison with the ones obtained by Linear Regression and Least Square Regression, hint that genetic programming is a promising technique for this kind of application. Moreover, genetic programming output may potentially highlight some relations between genes which could support the identification of biological meaningful pathways. The structures that appear more frequently in the "best" solutions found by genetic programming are presented. (C) 2009 Elsevier Ltd. All rights reserved.
Original languageUnknown
Pages (from-to)1395-1405
JournalComputers & Operations Research
Volume37
Issue number8
DOIs
Publication statusPublished - 1 Jan 2010

Cite this

@article{4fdd58a113564d08aef24c3b3a31ed45,
title = "Genetic programming for anticancer therapeutic response prediction using the NCI-60 dataset",
abstract = "Statistical methods, and in particular machine learning, have been increasingly used in the drug development workflow. Among the existing machine learning methods, we have been specifically concerned with genetic programming. We present a genetic programming-based framework for predicting anticancer therapeutic response. We use the NCI-60 microarray dataset and we look for a relationship between gene expressions and responses to oncology drugs Fluorouracil, Fludarabine, Floxuridine and Cytarabine. We aim at identifying, from genomic measurements of biopsies, the likelihood to develop drug resistance. Experimental results. and their comparison with the ones obtained by Linear Regression and Least Square Regression, hint that genetic programming is a promising technique for this kind of application. Moreover, genetic programming output may potentially highlight some relations between genes which could support the identification of biological meaningful pathways. The structures that appear more frequently in the {"}best{"} solutions found by genetic programming are presented. (C) 2009 Elsevier Ltd. All rights reserved.",
keywords = "schema, crossover, feature-selection, data, Genetic, learning, Microarray, Machine, general, dna-microarray, identification, molecular, programming, NCI-60, expression, drugs, therapy, patterns, Regression, subtree-swapping, classification, microarray, cdna, cancer, Anticancer, theory",
author = "Leonardo Vanneschi",
note = "ISI Document Delivery No.: 561ZU Times Cited: 3 Cited Reference Count: 48 Archetti, Francesco Giordani, Ilaria Vanneschi, Leonardo Pergamon-elsevier science ltd Oxford Si",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/j.cor.2009.02.015",
language = "Unknown",
volume = "37",
pages = "1395--1405",
journal = "Computers & Operations Research",
issn = "0305-0548",
publisher = "PERGAMON-ELSEVIER SCIENCE LTD",
number = "8",

}

Genetic programming for anticancer therapeutic response prediction using the NCI-60 dataset. / Vanneschi, Leonardo.

In: Computers & Operations Research, Vol. 37, No. 8, 01.01.2010, p. 1395-1405.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Genetic programming for anticancer therapeutic response prediction using the NCI-60 dataset

AU - Vanneschi, Leonardo

N1 - ISI Document Delivery No.: 561ZU Times Cited: 3 Cited Reference Count: 48 Archetti, Francesco Giordani, Ilaria Vanneschi, Leonardo Pergamon-elsevier science ltd Oxford Si

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Statistical methods, and in particular machine learning, have been increasingly used in the drug development workflow. Among the existing machine learning methods, we have been specifically concerned with genetic programming. We present a genetic programming-based framework for predicting anticancer therapeutic response. We use the NCI-60 microarray dataset and we look for a relationship between gene expressions and responses to oncology drugs Fluorouracil, Fludarabine, Floxuridine and Cytarabine. We aim at identifying, from genomic measurements of biopsies, the likelihood to develop drug resistance. Experimental results. and their comparison with the ones obtained by Linear Regression and Least Square Regression, hint that genetic programming is a promising technique for this kind of application. Moreover, genetic programming output may potentially highlight some relations between genes which could support the identification of biological meaningful pathways. The structures that appear more frequently in the "best" solutions found by genetic programming are presented. (C) 2009 Elsevier Ltd. All rights reserved.

AB - Statistical methods, and in particular machine learning, have been increasingly used in the drug development workflow. Among the existing machine learning methods, we have been specifically concerned with genetic programming. We present a genetic programming-based framework for predicting anticancer therapeutic response. We use the NCI-60 microarray dataset and we look for a relationship between gene expressions and responses to oncology drugs Fluorouracil, Fludarabine, Floxuridine and Cytarabine. We aim at identifying, from genomic measurements of biopsies, the likelihood to develop drug resistance. Experimental results. and their comparison with the ones obtained by Linear Regression and Least Square Regression, hint that genetic programming is a promising technique for this kind of application. Moreover, genetic programming output may potentially highlight some relations between genes which could support the identification of biological meaningful pathways. The structures that appear more frequently in the "best" solutions found by genetic programming are presented. (C) 2009 Elsevier Ltd. All rights reserved.

KW - schema

KW - crossover

KW - feature-selection

KW - data

KW - Genetic

KW - learning

KW - Microarray

KW - Machine

KW - general

KW - dna-microarray

KW - identification

KW - molecular

KW - programming

KW - NCI-60

KW - expression

KW - drugs

KW - therapy

KW - patterns

KW - Regression

KW - subtree-swapping

KW - classification

KW - microarray

KW - cdna

KW - cancer

KW - Anticancer

KW - theory

U2 - 10.1016/j.cor.2009.02.015

DO - 10.1016/j.cor.2009.02.015

M3 - Article

VL - 37

SP - 1395

EP - 1405

JO - Computers & Operations Research

JF - Computers & Operations Research

SN - 0305-0548

IS - 8

ER -