Using Artificial Neural Networks to Predict Biological Activity from Simple Molecular Structural Considerations
作者:
Frank R. Burden,
期刊:
Quantitative Structure‐Activity Relationships
(WILEY Available online 1996)
卷期:
Volume 15,
issue 1
页码: 7-11
ISSN:0931-8771
年代: 1996
DOI:10.1002/qsar.19960150103
出版商: WILEY‐VCH Verlag
关键词: Artificial neural networks (ANN);dihydrofolate reductase inhibitors;molar refractivity;hydrophobicity;prediction of biological activity
数据来源: WILEY
摘要:
AbstractSome simple molecular structural considerations relating to atom type were used as the independent variable inputs to an artificial neural network with the dependent variables consisting of the physicochemical parameters molecular refractivity and hydrophobicity. The low root mean squared error in each case was sufficiently low for the further mapping of biological activity to be attempted. A set of 236 dihydrofolate reductase inhibitors, for which the biological activity was known, was fitted in a similar manner and again producing a low root mean squared error. It is concluded that neural networks can be used to predict biological activity, within a series of closely related molecules, from molecular structural considerations alone so saving much effort in synthesis andin vivotesting with new candidate molecules.
点击下载:
PDF
(446KB)
返 回