✦ LIBER ✦
The Comparison of Molecular Surfaces by Neural Networks and its Applications to Quantitative Structure Activity Studies
✍ Scribed by Polański, Jarosław ;Gasteiger, Johann ;Wagener, Markus ;Sadowski, Jens
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 342 KB
- Volume
- 17
- Category
- Article
- ISSN
- 1611-020X
No coin nor oath required. For personal study only.
✦ Synopsis
Self-organizing Kohonen neural networks can be used to obtain quantitative structure-activity relationships. Simple molecules have been selected to discuss the essential features of the transformation. Descriptors calculated from maps obtained from comparative studies with template molecules applied to the analysis of compounds derived from butane, as well as ethylcarboxylates and nitro-and cyanoanilines (sweet-tasting compounds) can be correlated with various molecular effects.