| Home | E-Submission | Sitemap | Editorial Office |  
J Health Info Stat > Volume 36(2); 2011 > Article
J Health Info Stat 2011;36(2):193-200.
신축망 정규화 로지스틱 회귀모형을 이용한 대사체 지표의 발굴
Identification of Metabolomic Markers via Logistic Regression Model with Elastic-Net Regularization
Kyung A Kim
In this study, we newly proposed to apply multiple logistic regression with elastic-net regularization to identify metabolomic markers that predict origins of herbal medicines.
Herbal medicines were collected from two different origins, Korea and China. For each origin, 30 samples were extracted and profiled by nuclear magnetic resonance (NMR) technology, After binning and normalization, we obtained 60 profiles containing density of 240 metabolites, Logistic regression was applied with elastic-net regularization to identify metabolomics markers and build a classifier. We compared the performance of our classifier with the classifier based on orthogonal partial least squares-discriminant analysis (OPLS-DA), which has been commonly used in metabolomics.
A total of 14 metabolomic markers were selected to construct the classifier discriminating Korean and Chinese herbal medicines. In predicting the origin of additional samples, our classifier had no misclassification, while the OPLS-DA classifier showed 25˚ o misclassification rate.
These results suggest that our method would have advantages against the OPLS-DA, including lower misclassification rate, better interpretability, and no need of an additional analysis for marker identification.
Key words: Classification, Logistic regression, Variable selection, Elastic-net, Regularization, Metabolomics
PDF Links  PDF Links
Full text via DOI  Full text via DOI
Download Citation  Download Citation
Related article
Application of the Logistic Regression Model in Health Research  1986 ;11(1)
Editorial Office
The Korean Society of Health Informatics and Statistics
680 gukchaebosang-ro, Jung-gu, Daegu, 41944, Korea
E-mail: koshis@hanmail.net
About |  Browse Articles |  Current Issue |  For Authors and Reviewers
Copyright © The Korean Society of Health Informatics and Statistics.                 Developed in M2PI