Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma

Yasuyuki Tomita, Shuta Tomida, Yuko Hasegawa, Yoichi Suzuki, Taro Shirakawa, Takeshi Kobayashi, Hiroyuki Honda

Research output: Contribution to journalArticle

50 Citations (Scopus)

Abstract

Background: Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease. Results: To predict development of childhood allergic asthma (CAA) and select susceptible SNPs, we used an ANN with a parameter decreasing method (PDM) to analyze 25 SNPs of 17 genes in 344 Japanese people, and select 10 susceptible SNPs of CAA. The accuracy of the ANN model with 10 SNPs was 97.7% for learning data and 74.4% for evaluation data. Important combinations were determined by effective combination value (ECV) defined in the present paper. Effective 2-SNP or 3-SNP combinations were found to be concentrated among the 10 selected SNPs. Conclusion: ANN can reliably select SNP combinations that are associated with CAA. Thus, the ANN can be used to characterize development of complex diseases caused by multiple factors. This is the first report of automatic selection of SNPs related to development of multifactorial disease from SNP data of more than 300 patients.

Original languageEnglish
Article number120
JournalBMC Bioinformatics
Volume5
DOIs
Publication statusPublished - Sep 1 2004
Externally publishedYes

Fingerprint

Asthma
Single nucleotide Polymorphism
Nucleotides
Polymorphism
Prediction Model
Single Nucleotide Polymorphism
Artificial Neural Network
Neural networks
Genes
Gene
Neural Network Model
Screening
Predict
Neural Networks (Computer)
Evaluation
Learning

ASJC Scopus subject areas

  • Medicine(all)
  • Structural Biology
  • Applied Mathematics

Cite this

Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma. / Tomita, Yasuyuki; Tomida, Shuta; Hasegawa, Yuko; Suzuki, Yoichi; Shirakawa, Taro; Kobayashi, Takeshi; Honda, Hiroyuki.

In: BMC Bioinformatics, Vol. 5, 120, 01.09.2004.

Research output: Contribution to journalArticle

Tomita, Yasuyuki ; Tomida, Shuta ; Hasegawa, Yuko ; Suzuki, Yoichi ; Shirakawa, Taro ; Kobayashi, Takeshi ; Honda, Hiroyuki. / Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma. In: BMC Bioinformatics. 2004 ; Vol. 5.
@article{9026b9ddc62c44478eaf53657865ac7b,
title = "Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma",
abstract = "Background: Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease. Results: To predict development of childhood allergic asthma (CAA) and select susceptible SNPs, we used an ANN with a parameter decreasing method (PDM) to analyze 25 SNPs of 17 genes in 344 Japanese people, and select 10 susceptible SNPs of CAA. The accuracy of the ANN model with 10 SNPs was 97.7{\%} for learning data and 74.4{\%} for evaluation data. Important combinations were determined by effective combination value (ECV) defined in the present paper. Effective 2-SNP or 3-SNP combinations were found to be concentrated among the 10 selected SNPs. Conclusion: ANN can reliably select SNP combinations that are associated with CAA. Thus, the ANN can be used to characterize development of complex diseases caused by multiple factors. This is the first report of automatic selection of SNPs related to development of multifactorial disease from SNP data of more than 300 patients.",
author = "Yasuyuki Tomita and Shuta Tomida and Yuko Hasegawa and Yoichi Suzuki and Taro Shirakawa and Takeshi Kobayashi and Hiroyuki Honda",
year = "2004",
month = "9",
day = "1",
doi = "10.1186/1471-2105-5-120",
language = "English",
volume = "5",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma

AU - Tomita, Yasuyuki

AU - Tomida, Shuta

AU - Hasegawa, Yuko

AU - Suzuki, Yoichi

AU - Shirakawa, Taro

AU - Kobayashi, Takeshi

AU - Honda, Hiroyuki

PY - 2004/9/1

Y1 - 2004/9/1

N2 - Background: Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease. Results: To predict development of childhood allergic asthma (CAA) and select susceptible SNPs, we used an ANN with a parameter decreasing method (PDM) to analyze 25 SNPs of 17 genes in 344 Japanese people, and select 10 susceptible SNPs of CAA. The accuracy of the ANN model with 10 SNPs was 97.7% for learning data and 74.4% for evaluation data. Important combinations were determined by effective combination value (ECV) defined in the present paper. Effective 2-SNP or 3-SNP combinations were found to be concentrated among the 10 selected SNPs. Conclusion: ANN can reliably select SNP combinations that are associated with CAA. Thus, the ANN can be used to characterize development of complex diseases caused by multiple factors. This is the first report of automatic selection of SNPs related to development of multifactorial disease from SNP data of more than 300 patients.

AB - Background: Screening of various gene markers such as single nucleotide polymorphism (SNP) and correlation between these markers and development of multifactorial disease have previously been studied. Here, we propose a susceptible marker-selectable artificial neural network (ANN) for predicting development of allergic disease. Results: To predict development of childhood allergic asthma (CAA) and select susceptible SNPs, we used an ANN with a parameter decreasing method (PDM) to analyze 25 SNPs of 17 genes in 344 Japanese people, and select 10 susceptible SNPs of CAA. The accuracy of the ANN model with 10 SNPs was 97.7% for learning data and 74.4% for evaluation data. Important combinations were determined by effective combination value (ECV) defined in the present paper. Effective 2-SNP or 3-SNP combinations were found to be concentrated among the 10 selected SNPs. Conclusion: ANN can reliably select SNP combinations that are associated with CAA. Thus, the ANN can be used to characterize development of complex diseases caused by multiple factors. This is the first report of automatic selection of SNPs related to development of multifactorial disease from SNP data of more than 300 patients.

UR - http://www.scopus.com/inward/record.url?scp=11344282232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11344282232&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-5-120

DO - 10.1186/1471-2105-5-120

M3 - Article

C2 - 15339344

AN - SCOPUS:11344282232

VL - 5

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 120

ER -