Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/27967
Title: | Selective Descriptor Pruning for QSAR/QSPR Studies Using Artificial Neural Networks | Contributor(s): | Turner, Joseph V (author)![]() |
Publication Date: | 2003-05 | DOI: | 10.1002/jcc.10148 | Handle Link: | https://hdl.handle.net/1959.11/27967 | Abstract: | Selection of optimal descriptors in quantitative structure-activity-property relationship (QSAR/QSPR) studies has been a perennial problem. Artificial Neural Networks (ANNs) have been used widely in QSAR/QSPR studies but less widely in descriptor selection. The current study used ANNs to select an optimal set of descriptors using large numbers of input variables. The effects of clean, noisy, and random input descriptors with linear, nonlinear, and periodic data on synthetic and real data QSAR/QSPR sets were examined. The optimal set of descriptors could be determined using a signal-to-noise ratio method. The optimal values for the rho parameter, which relates sample size to network architecture, were found to vary with the type of data. ANNs were able to detect meaningful descriptors in the presence of large numbers of random false descriptors. | Publication Type: | Journal Article | Source of Publication: | Journal of Computational Chemistry, 24(7), p. 891-897 | Publisher: | John Wiley & Sons, Inc | Place of Publication: | United States of America | ISSN: | 1096-987X 0192-8651 |
Fields of Research (FoR) 2008: | 030402 Biomolecular Modelling and Design 030799 Theoretical and Computational Chemistry not elsewhere classified 030404 Cheminformatics and Quantitative Structure-Activity Relationships |
Socio-Economic Objective (SEO) 2008: | 860803 Human Pharmaceutical Treatments (e.g. Antibiotics) | Peer Reviewed: | Yes | HERDC Category Description: | C1 Refereed Article in a Scholarly Journal |
---|---|
Appears in Collections: | Journal Article School of Rural Medicine |
Files in This Item:
File | Size | Format |
---|
SCOPUSTM
Citations
16
checked on Aug 24, 2024
Page view(s)
1,950
checked on Aug 11, 2024
Download(s)
2
checked on Aug 11, 2024
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.