New QSAR Methods Applied to Sturcture - Activity Mapping and Combinatorial Chemistry

Frank R Burden, David A Winkler

Research output: Contribution to journalArticleResearchpeer-review

49 Citations (Scopus)

Abstract

A comparison is made of a number of computationally efficient molecular indices with a view to the screening of very large virtual data sets of molecules. The use of Bayesian regularized neural networks is discussed, and their virtue in eliminating the need for validation sets, and potentially even test sets, is emphasized. The concept of a virtual receptor is introduced, and this is illustrated by the results of screening a database of 40 000 molecules.

Original languageEnglish
Pages (from-to)236-242
Number of pages7
JournalJournal of Chemical Information and Computer Sciences
Volume39
Issue number2
Publication statusPublished - 1999

Cite this