Neural Network-Graph Theory Approach to the Prediction of the Physical Properties of Organic Compounds

A new computational scheme is developed to predict physical properties of organic compounds on the basis of their molecular structure. The method uses graph theory to encode the structural information which is the numerical input for a neutral network. Calculated results for a series of saturated hy...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of Chemical Information and Computer Sciences 1994-07, Vol.34 (4), p.832-839
Hauptverfasser:	Gakh, Andrei A, Gakh, Elena G, Sumpter, Bobby G, Noid, Donald W
Format:	Artikel
Sprache:	eng
Schlagworte:	02 PETROLEUM 40 CHEMISTRY ALGORITHMS CALCULATION METHODS COMPUTER ARCHITECTURE HYDROCARBONS MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS MOLECULAR STRUCTURE NEURAL NETWORKS ORGANIC COMPOUNDS PHYSICAL PROPERTIES THEORETICAL DATA
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A new computational scheme is developed to predict physical properties of organic compounds on the basis of their molecular structure. The method uses graph theory to encode the structural information which is the numerical input for a neutral network. Calculated results for a series of saturated hydrocarbons demonstrate average accuracies of 1--2% with maximum deviations of 12--14%.
ISSN:	0095-2338 1520-5142
DOI:	10.1021/ci00020a017