MASS-SPECTRAL CLASSIFIERS FOR SUPPORTING SYSTEMATIC STRUCTURE ELUCIDATION

Authors
VARMUZA K WERTHER W
Citation
K. Varmuza et W. Werther, MASS-SPECTRAL CLASSIFIERS FOR SUPPORTING SYSTEMATIC STRUCTURE ELUCIDATION, Journal of chemical information and computer sciences, 36(2), 1996, pp. 323-333
Citations number
48
Categorie Soggetti
Information Science & Library Science","Computer Application, Chemistry & Engineering","Computer Science Interdisciplinary Applications",Chemistry,"Computer Science Information Systems
Journal title
Journal of chemical information and computer sciences → ACNP
ISSN journal
00952338
Volume
36
Issue
2
Year of publication
1996
Pages
323 - 333
Database
ISI
SICI code
0095-2338(1996)36:2<323:MCFSSS>2.0.ZU;2-W
Abstract
A set of mass spectral classifiers has been developed to recognize pre sence or absence of 70 substructures or more general structural proper ties in a molecule. Classification is based on numerical transformatio n of low resolution mass spectral data, automatic selection of appropr iate features, multivariate discriminant methods, and estimation of th e reliability of the classification answer. Examples demonstrate appli cations in structure elucidation together with automatic isomer genera tion as well as combination with results obtained by the CHEMICS syste m.