[논문]정규상호정보와 지지벡터기계를 이용한 천식 관련 단일염기다형성 유전형 자료 분석

이중섭; 김승현; 신기섭; 임규철

초록
AI-Helper

서론: 천식에는 아스피린 과민증 (aspirin hypersensitivity)에 따라 아스피린 불내성 (aspirin intolerant asthma, AIA)과 내성 천식 (aspirin tolerant asthma, ATA) 두 가지 유형이 있다. 천식과 관련된 유전적 위험 요인들은 집중적으로 또한 광범위하게 연구되고 있다. 그러나 단일염기다형성들의 조합의 효과에 대해서는 거의 평가되지 않았다. 본 논문에서는 두 유형의 천식 진단에 유용한 단일염기다형성의 최상의 조합을 찾는다. 방법: 본 논문에서는 246명의 천식환자들을 조사하였다. (94명은 아스피린 불내성 천식을 152명은 아스피린 내성 천식을 가지고 있다) 그리고 천식과 관련된 것으로 추측되는 25개의 단일염기다형성들을 분석하였다. 단일염기다형성의 조합의 정규상호정보 값을 계산하여 높은 정규상호정보 값을 갖는 단일염기다형성들의 조합을 선택하고 선택된 조합들의 예측 정확도를 지지벡터기계를 사용하여 계산하였다. 결과: 최상의 조합은 4개짜리이고 ALOX5_p1_1708, B2ADR_q1_46, CCR3_p1_520, CysLTR1_p1_534로 구성된 모델이다. 이것은 0.053의 정규상호정보 값과 71.14%의 ATA 질병에 대한 예측 정확도를 갖는다.

Abstract ▼ AI-Helper

Introduction: There are two types of asthma according to aspirin hypersensitivity: aspirin intolerant asthma (AIA) and aspirin tolerant asthma (ATA). The genetic risk factors that are related with asthma have been investigated intensively and extensively. However the combinatory effects of single nu...

Introduction: There are two types of asthma according to aspirin hypersensitivity: aspirin intolerant asthma (AIA) and aspirin tolerant asthma (ATA). The genetic risk factors that are related with asthma have been investigated intensively and extensively. However the combinatory effects of single nucleotide polymorphisms (SNPs) have hardly been evaluated. In this paper we searched the best set of SNPs that are useful to diagnose the two types of asthma. Methods: We examined 246 asthmatic patients (94 having aspirin intolerant asthma and 152 having aspirin tolerant asthma) and analyzed 25 SNPs typed in them, which are suspected to be associated with asthma. Normalized mutual information values of combinations of typed SNPs are calculated, and those with high normalized mutual information values are selected. We use support vector machines to evaluate the prediction accuracy of the selected combinations. Results: The best combination model turns out four-locus and consists of ALOX5_p1_1708, B2ADR_q1_46, CCR3_p1_520, CysLTR1_p1_634. Its normalized mutual information value is 0.053 and the accuracy in predicting ATA disease risk among asthmatic patients is 71.14%.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

In [2], Kim et al used the multifactor dimensionality reduction (MDR) method to identify the best model predicting AIA disease risk among asthmatic patients. In this paper, we exploit normalized mutual information and support vector machines to predict ATA disease risk among them. First using normalized mutual information values, we reveal sets of SNPs that separate phe- onotypically distinct classes of the sample according to their genotype signatures.

제안 방법

between AIA and ATA. By applying norma lized mutual information, more than single SNP can be related so that we can explore the synergistic effect of three, four and five SNPs on asthma, Finally, we discussed how to predict asthma type from SNPs on the basis of SVM method. The results of this study can also be used as basic information between SNPs and disease or among SNPs for further implementation such as cluster analysis or gene-gene interaction.
In the first step, the NMI was used to ana lyze the association of combinations of 3 SNPs with asthma and determine which combinations of SNPs were best in classifying the types of asthma (AIA or ATA). We calculated NMI values of all 3-SNP combinations using Equation (2), and selec ted 20 combinations with highest NMI values.
We calculated NMI values of all 3-SNP combinations using Equation (2), and selec ted 20 combinations with highest NMI values. In the second step, we applied support vector machine method, with the Gaussian radial basis function kernel, to evaluate the prediction accuracy of each of top 20 SNP combinations. Here we used SVM- light program[7], and the accuracy was obtained by the leave-one-out validation method.
Then the method of support vector machine is used to evaluate the prediction accuracies of the selected sets of SNPs. The main contribution of the current work is to provide an efficient method for selecting a set of SNPs that is associated with disease phenotype.
First using normalized mutual information values, we reveal sets of SNPs that separate phe- onotypically distinct classes of the sample according to their genotype signatures. Then the method of support vector machine is used to evaluate the prediction accuracies of the selected sets of SNPs. The main contribution of the current work is to provide an efficient method for selecting a set of SNPs that is associated with disease phenotype.

대상 데이터

Twenty-five SNPs were selected for analysis and the genotype data of 246 asthmatics (94 with AIA and 152 with ATA) are provided by Ajou University Medical Center. The mean age and sex proportion between AIA and ATA groups are not different.

이론/모형

In the second step, we applied support vector machine method, with the Gaussian radial basis function kernel, to evaluate the prediction accuracy of each of top 20 SNP combinations. Here we used SVM- light program[7], and the accuracy was obtained by the leave-one-out validation method. This result is summarized in Table 2, and it shows that the high est accuracy is achieved by the combination of 1st, 7th and 22nd SNPs.

성능/효과

Applying the MDR method to the same SNP data, we found that the best 4-SNP combination predict ing ATA disease risk among asthmatic patients is B2ADR__ql_46, CCR3_j)2_17f CysLTRl_pl_634, TBXA2R„ ql_795 and the prediction accuaracy is 59.75%. The best SNP combination found in this paper provide us higher prediction accuracy than the one obtained by the MDR method.
The results of this study can also be used as basic information between SNPs and disease or among SNPs for further implementation such as cluster analysis or gene-gene interaction. In conclusion, our results suggest that effect of multi-locus genetic interaction exists in the susceptibility to aspirin tolerance in asthmatic patients, which will help to better understand the complex genetic basis of ATA. The best 4-SNP combination model found in the previous section can be applied as a potential gene marker for diagnosing ATA.

후속연구

By applying norma lized mutual information, more than single SNP can be related so that we can explore the synergistic effect of three, four and five SNPs on asthma, Finally, we discussed how to predict asthma type from SNPs on the basis of SVM method. The results of this study can also be used as basic information between SNPs and disease or among SNPs for further implementation such as cluster analysis or gene-gene interaction. In conclusion, our results suggest that effect of multi-locus genetic interaction exists in the susceptibility to aspirin tolerance in asthmatic patients, which will help to better understand the complex genetic basis of ATA.

참고문헌 (7)

Tsalenko, A., Ben-Dor, A., Cox, N., et al., 'Methods for analysis and visualization of SNP genotype data for complex diseases,' Pac. Symp. Biocomput., vol.8, pp.548-561, 2003
S. H. Kim H. H. Jeong, B. Y. Cho, et al, 'Association of four-locus gene interaction with aspirinintolerant asthma in Korean asthmatics,' J. Clin. Immunol., vol.4, no.4, pp.336-342, 2008

상세보기
Cover, T. M. and Thomas, J. A., Elements of Information Theory, 2nd Ed., Wiley, 2006
Furey, T. S., Cristianini, N., Duffy, N., et al, 'Support vector machine classification and validation of cancer tissue samples using microarray expression data,' Bioinformatics, vol.16, no.10, pp. 906-914, 2006

상세보기
Zhou, X., Wang, X., Dougherty, E. R., et al. 'Gene clustering based on clusterwide mutual information,' J. Comput. Biol., vol.11, no.1, pp.147-161, 2004

상세보기
http://en.wikipedia.org/wiki/Mutual_information
http://svmlight.joachims.org/

이 논문을 인용한 문헌

저자의 다른 논문 :

LOADING...

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

정규상호정보와 지지벡터기계를 이용한 천식 관련 단일염기다형성 유전형 자료 분석
Analysis of Asthma Related SNP Genotype Data Using Normalized Mutual Information and Support Vector Machines 원문보기

초록
AI-Helper

Abstract ▼ AI-Helper

주제어

AI 본문요약
AI-Helper

문제 정의

제안 방법

대상 데이터

이론/모형

성능/효과

후속연구

참고문헌 (7)

이 논문을 인용한 문헌

저자의 다른 논문 :

연구과제 타임라인

관련 콘텐츠

원문 보기

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

정규상호정보와 지지벡터기계를 이용한 천식 관련 단일염기다형성 유전형 자료 분석 Analysis of Asthma Related SNP Genotype Data Using Normalized Mutual Information and Support Vector Machines 원문보기

초록 용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

주제어

AI 본문요약 엑셀 다운로드 AI-Helper

문제 정의

제안 방법

대상 데이터

이론/모형

성능/효과

후속연구

참고문헌 (7)

이 논문을 인용한 문헌

저자의 다른 논문 :

이중섭 (3) 김승현 (1) 신기섭 (1)

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

관련 콘텐츠

원문 보기

원문 URL 링크

이 논문과 함께 이용한 콘텐츠

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

정규상호정보와 지지벡터기계를 이용한 천식 관련 단일염기다형성 유전형 자료 분석
Analysis of Asthma Related SNP Genotype Data Using Normalized Mutual Information and Support Vector Machines 원문보기

초록
AI-Helper

AI 본문요약
AI-Helper