Journal of Chemical Software
Online ISSN : 1883-8359
Print ISSN : 0918-0761
ISSN-L : 0918-0761
Development of NEural network simulator for structure-activity COrrelation of molecules : Neco
Yoshimi ISUUmpei NAGASHIMAHaruo HOSOYATomoo AOYAMA
Author information
JOURNALS FREE ACCESS

1994 Volume 2 Issue 2 Pages 76-94

Details
Abstract

A perceptron type neural network simulator for structure-activity correlation of molecules, Neco, has been developed with two different pre-education methods : back propagation method and reconstruction of weight matrix method.
Since the program was written in C, it is executable on popular Unix workstations. The number of intermediate layered units in intermediate layer and intermediate layer itself can be set arbitrarily by the user.
As an example of application, conformations of norbornene isomers were predicted using 13C-NMR data. The predicted conformations are in excellent agreement with experiments.
By reconstructing the weight matrix, it was suggested that 13C -NMR data of only two specified carbons in the norbornene skeleton have strong correlation with the conformation (exo and endo) of the main branch. This was verified by the parameter scan method.

Information related to the author
© Society of Computer Chemistry, Japan
Next article
feedback
Top