Document Detail


Exploration of linear modelling techniques and their combination with multivariate adaptive regression splines to predict gastro-intestinal absorption of drugs.
MedLine Citation:
PMID:  16859855     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
In general, linear modelling techniques such as multiple linear regression (MLR), principal component regression (PCR) and partial least squares (PLS), are used to model QSAR data. This type of data can be very complex and linear modelling techniques often model only a limited part of the information captured in the data. In this study, it was tried to combine linear techniques with the flexible non-linear technique multivariate adaptive regression splines (MARS). Models were built using an MLR model, combined with either a stepwise procedure or a genetic algorithm for variable selection, a PCR model or a PLS model as starting points for the MARS algorithm. The descriptive and predictive power of the models was evaluated in a QSAR context and compared to the performances of the individual linear models and the single MARS model. In general, the combined methods resulted in significant improvements compared to the linear models and can be considered valuable techniques in modelling complex QSAR data. For the used data set the best model was obtained using a combination of PLS and MARS. This combination resulted in a model with a Pearson correlation coefficient of 0.90 and a cross-validation error, evaluated with 10-fold cross-validation of 9.9%, pointing at good descriptive and high predictive properties.
Authors:
E Deconinck; D Coomans; Y Vander Heyden
Related Documents :
18095435 - Comparing uncertainty resulting from two-step and global regression procedures applied ...
12342755 - A multistate model for coronary heart disease--an application to different prevention s...
15298485 - Rates of claims for cumulative trauma disorder of the upper extremity in ontario worker...
2627025 - Alternative models of the stress buffering hypothesis.
11888955 - Prospective testing of two models based on clinical and oximetric variables for predict...
18078485 - A proportional hazards cure model for the analysis of time to event with frequently uni...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2006-07-21
Journal Detail:
Title:  Journal of pharmaceutical and biomedical analysis     Volume:  43     ISSN:  0731-7085     ISO Abbreviation:  J Pharm Biomed Anal     Publication Date:  2007 Jan 
Date Detail:
Created Date:  2006-12-12     Completed Date:  2007-03-13     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8309336     Medline TA:  J Pharm Biomed Anal     Country:  England    
Other Details:
Languages:  eng     Pagination:  119-30     Citation Subset:  IM    
Affiliation:
Department of Analytical Chemistry and Pharmaceutical Technology, Pharmaceutical Institute, Vrije Universiteit Brussel-VUB, Laarbeeklaan 103, B-1090 Brussels, Belgium.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Genetics
Intestinal Absorption
Intestines / metabolism*
Least-Squares Analysis
Linear Models
Models, Statistical
Multivariate Analysis
Pharmaceutical Preparations / chemistry,  metabolism*
Predictive Value of Tests
Principal Component Analysis
Quantitative Structure-Activity Relationship
Stomach / metabolism*
Chemical
Reg. No./Substance:
0/Pharmaceutical Preparations

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Enantiospecific assay of citadiol--a key intermediate of escitalopram by liquid chromatography on Ch...
Next Document:  Selective solid-phase extraction of cholesterol using molecularly imprinted polymers and its applica...