Generic placeholder image

Current Computer-Aided Drug Design


ISSN (Print): 1573-4099
ISSN (Online): 1875-6697

Efficacy Prediction of Jamu Formulations by PLS Modeling

Author(s): Farit M. Afendi, Latifah K. Darusman, Aki Hirai Morita, Md. Altaf-Ul-Amin, Hiroki Takahashi, Kensuke Nakamura, Ken Tanaka and Shigehiko Kanaya

Volume 9, Issue 1, 2013

Page: [46 - 59] Pages: 14

DOI: 10.2174/1573409911309010005

Price: $65


Indonesian herbal medicines made from mixtures of several plants are called “Jamu.” The efficacy of a particular Jamu is determined by its ingredients i.e. the composition of the plants. Thus, we modeled the ingredients of Jamu formulas using Partial Least Squares Discriminant Analysis (PLS-DA) in order to predict their efficacy. The plants used in each Jamu medicine served as the predictors, whereas the efficacy of each Jamu provided the responses. Utilizing response predictions obtained from PLS-DA, we predicted the efficacies of Jamu formulations using two methods: maximum response prediction and maximum probability. In predictions of Jamu efficacy, the maximum response prediction method produced a smaller error than that the maximum probability method. Furthermore, utilizing the PLSDA coefficient matrix, we determined the efficacy for which a plant is most useful, based on its largest coefficients.

Keywords: Efficacy, Jamu, main ingredients, medicinal plant, multivariate analysis, PLS-DA, regression coefficient, response prediction, formulation, modelling

Rights & Permissions Print Export Cite as
© 2023 Bentham Science Publishers | Privacy Policy