Pattern recognition display methods for the analysis of computed molecular properties
- 1 March 1989
- journal article
- research article
- Published by Springer Nature in Journal of Computer-Aided Molecular Design
- Vol. 3 (1) , 55-65
- https://doi.org/10.1007/bf01590995
Abstract
Pattern recognition methods, particularly the ‘unsupervised learning’ techniques, are well suited for the preliminary analysis of the large data sets produced by computer chemistry. The use of linear and non-linear display methods for such exploratory analysis are exemplified with the aid of two data sets of biologically active molecules. Advantages and disadvantages of these techniques are discussed.Keywords
This publication has 12 references indexed in Scilit:
- Physicochemical characteristics of non-electrolytes and their uptake by Brugia pahangi and Dipetalonema viteaeMolecular and Biochemical Parasitology, 1987
- Computer program suite for the calculation, storage and manipulation of molecular property and activity descriptorsJournal of Molecular Graphics, 1987
- Principal component analysisPublished by Springer Nature ,1980
- Chance factors in studies of quantitative structure-activity relationshipsJournal of Medicinal Chemistry, 1979
- Applications of computerized pattern recognition: A survey of correlations between pharmacological activities and mass spectraJournal of Mass Spectrometry, 1976
- An orthogonal feature selection methodPattern Recognition, 1976
- Discriminant analysis of the relation between physical properties and the inhibition of monoamine oxidase by aminotetralins and aminoindansJournal of Medicinal Chemistry, 1974
- Pattern recognition. II. Linear and nonlinear methods for displaying chemical dataJournal of the American Chemical Society, 1973
- Pattern recognition. Powerful approach to interpreting chemical dataJournal of the American Chemical Society, 1972
- A Nonlinear Mapping for Data Structure AnalysisIEEE Transactions on Computers, 1969