Features of the principal component analysis for the classification of biologically active compounds in terms of molecular descriptors

Autor:	L. I. Gabrielyan, A. S. Kabankin
Rok vydání:	2006
Předmět:	Pharmacology Training set business.industry Chemistry Stereochemistry Pharmacology toxicology Pattern recognition Class (philosophy) Set (abstract data type) Order (biology) Dimension (vector space) Molecular descriptor Drug Discovery Principal component analysis Artificial intelligence business
Zdroj:	Pharmaceutical Chemistry Journal. 40:307-311
ISSN:	1573-9031 0091-150X
DOI:	10.1007/s11094-006-0116-5
Popis:	Features of the principal component analysis, which can be used to decrease the dimension of the space of initial molecular descriptors in the search for classification rules predicting the activity of new compounds, are considered in application to the class of adamantane and indole derivatives possessing hepatoprotector activity. It is shown that (i) when the number of molecular descriptors is greater than the number of compounds in the training set, a preliminary selection of descriptors in the initial set is necessary to determine the principal components ensuring the optimum classification of compounds with respect to the given activity type, and (ii) in order to obtain the most effective classification rules, it is necessary to take into account the principal components with small and very small contributions to the total dispersion of the initial molecular descriptors.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::631af9fe5c52eea63bcf9ad9d01edc73 https://doi.org/10.1007/s11094-006-0116-5 Zobrazit plný text záznamu Plný text ve formátu PDF