Can neural network constraints in GP provide power to detect genes associated with human disease?

William S. Bush, Alison A. Motsinger, Scott M. Dudek, Marylyn Deriggi Ritchie

Research output: Contribution to journalConference article

6 Citations (Scopus)

Abstract

A major goal of human genetics is the identification of susceptibility genes associated with common, complex diseases. Identifying gene-gene and gene-environment interactions which comprise the genetic architecture for a majority of common diseases is a difficult challenge. To this end, novel computational approaches have been applied to studies of human disease. Previously, a GP neural network (GPNN) approach was employed. Although the GPNN method has been quite successful, a clear comparison of GPNN and GP alone to detect genetic effects has not been made. In this paper, we demonstrate that using NN evolved by GP can be more powerful than GP alone. This is most likely due to the confined search space of the GPNN approach, in comparison to a free form GP. This study demonstrates the utility of using GP to evolve NN in studies of the genetics of common, complex human disease.

Original languageEnglish (US)
Pages (from-to)44-53
Number of pages10
JournalLecture Notes in Computer Science
Volume3449
StatePublished - Sep 19 2005
EventEvoWorkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC - Lausanne, Switzerland
Duration: Mar 30 2005Apr 1 2005

Fingerprint

Genes
Neural Networks
Gene
Neural networks
Gene-environment Interaction
Susceptibility
Search Space
Demonstrate
Likely
Human
Genetics

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Bush, William S. ; Motsinger, Alison A. ; Dudek, Scott M. ; Ritchie, Marylyn Deriggi. / Can neural network constraints in GP provide power to detect genes associated with human disease?. In: Lecture Notes in Computer Science. 2005 ; Vol. 3449. pp. 44-53.
@article{30b45d5ecfe443a38ed2f3630a0a33ae,
title = "Can neural network constraints in GP provide power to detect genes associated with human disease?",
abstract = "A major goal of human genetics is the identification of susceptibility genes associated with common, complex diseases. Identifying gene-gene and gene-environment interactions which comprise the genetic architecture for a majority of common diseases is a difficult challenge. To this end, novel computational approaches have been applied to studies of human disease. Previously, a GP neural network (GPNN) approach was employed. Although the GPNN method has been quite successful, a clear comparison of GPNN and GP alone to detect genetic effects has not been made. In this paper, we demonstrate that using NN evolved by GP can be more powerful than GP alone. This is most likely due to the confined search space of the GPNN approach, in comparison to a free form GP. This study demonstrates the utility of using GP to evolve NN in studies of the genetics of common, complex human disease.",
author = "Bush, {William S.} and Motsinger, {Alison A.} and Dudek, {Scott M.} and Ritchie, {Marylyn Deriggi}",
year = "2005",
month = "9",
day = "19",
language = "English (US)",
volume = "3449",
pages = "44--53",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",

}

Can neural network constraints in GP provide power to detect genes associated with human disease? / Bush, William S.; Motsinger, Alison A.; Dudek, Scott M.; Ritchie, Marylyn Deriggi.

In: Lecture Notes in Computer Science, Vol. 3449, 19.09.2005, p. 44-53.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Can neural network constraints in GP provide power to detect genes associated with human disease?

AU - Bush, William S.

AU - Motsinger, Alison A.

AU - Dudek, Scott M.

AU - Ritchie, Marylyn Deriggi

PY - 2005/9/19

Y1 - 2005/9/19

N2 - A major goal of human genetics is the identification of susceptibility genes associated with common, complex diseases. Identifying gene-gene and gene-environment interactions which comprise the genetic architecture for a majority of common diseases is a difficult challenge. To this end, novel computational approaches have been applied to studies of human disease. Previously, a GP neural network (GPNN) approach was employed. Although the GPNN method has been quite successful, a clear comparison of GPNN and GP alone to detect genetic effects has not been made. In this paper, we demonstrate that using NN evolved by GP can be more powerful than GP alone. This is most likely due to the confined search space of the GPNN approach, in comparison to a free form GP. This study demonstrates the utility of using GP to evolve NN in studies of the genetics of common, complex human disease.

AB - A major goal of human genetics is the identification of susceptibility genes associated with common, complex diseases. Identifying gene-gene and gene-environment interactions which comprise the genetic architecture for a majority of common diseases is a difficult challenge. To this end, novel computational approaches have been applied to studies of human disease. Previously, a GP neural network (GPNN) approach was employed. Although the GPNN method has been quite successful, a clear comparison of GPNN and GP alone to detect genetic effects has not been made. In this paper, we demonstrate that using NN evolved by GP can be more powerful than GP alone. This is most likely due to the confined search space of the GPNN approach, in comparison to a free form GP. This study demonstrates the utility of using GP to evolve NN in studies of the genetics of common, complex human disease.

UR - http://www.scopus.com/inward/record.url?scp=24644454835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644454835&partnerID=8YFLogxK

M3 - Conference article

VL - 3449

SP - 44

EP - 53

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -