PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 15807514

Optimized block-wise variable combination by particle swarm optimization for partial least squares modeling in quantitative structure-activity relationship studies.

Wei-Qi Lin·Jian-Hui Jiang·Qi Shen·Guo-Li Shen·Ru-Qin Yu
View original source ↗Export metadata ↓

Abstract

The use of numerous descriptors that are indicative of molecular structure is becoming common in quantitative structure-activity relationship (QSAR) studies. As all of the descriptors might carry more or less molecular information, it seems more advisable to investigate the possible variable combination rather than variable selection. In this paper, an optimized block-wise variable combination (OBVC) by particle swarm optimization based on partial least squares modeling has been proposed for variable combination. An F statistic is also introduced to determine the dimensionality of the PLS model. The performance is assessed using two QSAR data sets. Experimental results have shown the good performance of this technique compared to those obtained by stepwise regression.

Explore related subjects

AminesAngiotensin IILeast-Squares AnalysisModels, ChemicalMolecular StructureQuantitative Structure-Activity RelationshipTriazolesJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Wei-Qi Lin, Jian-Hui Jiang, Qi Shen, Guo-Li Shen, Ru-Qin Yu. Optimized block-wise variable combination by particle swarm optimization for partial least squares modeling in quantitative structure-activity relationship studies.. https://doi.org/10.1021/ci049890i

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Identification of enantioselective extractants for chiral separation of amines and aminoalcohols.

The major obstacle for the introduction of fractional reactive extraction as a chiral separation method in the chemical and pharmaceutical industries is the lack of versatile enantioselective extractants. Therefore, a rational approach is developed to transfer the extensive knowledge of chiral selectors reported in the literature on chiral recognition and other chiral separation techniques to extraction. Based on a similarity in separation mechanisms, it was expected that chiral selectors originating from a technique in which chiral recognition takes place in the liquid phase are most likely to function as enantioselective extractant. Using this approach, a selection of promising extractants was made from the literature and experimentally evaluated for the enantioseparation of aminoalcohols and amines. As a result, four enantioselective extractant systems, namely, dibutyl-L-tartrate with boric acid, N-(2-hydroxydodecyl)-L-hydroxyproline Cu(II) complex, N-dodecyl-L-hydroxyproline Cu(II) complex, and azophenolic crown ether, have been identified. The azophenolic crown ether system performed the best and demonstrated an enantioselectivity between 1.3-5.0 for five out of six test compounds. Identification of the enantioselective extractant systems was highly facilitated by the developed rational transfer approach that, although partially qualitative, appeared capable of reducing more than 50 encountered candidates to only three promising systems for further experimental evaluation. Therefore, it is expected that this approach can be successfully applied to identify enantioselective extractants for other classes of enantiomers as well.

Amines↗