A number of companies are using ChemTree software from Golden Helix for in silico screening and revolutionizing their discovery efforts. Below are abstracts from a couple of papers in which researchers describe their application of ChemTree to in silico screening. Also, an example of using in silico screening to boost hit rates with anti-HIV compounds is described here.

Application of ChemTree to sequential screening and estimating solubility:

S Stanley Young, Sean Ekins & Christophe G Lambert (2002) "So many targets, so many compounds, but so few resources" Current Drug Discovery, December 2002.

Abstract:Ten years ago, a large pharmaceutical company might have had a few hundred thousand compounds in its library, but now with combinatorial and parallel chemistries the number of compounds commercially available has expanded beyond two million. How do you decide which ones to pursue? Advances in robotics and miniaturization certainly make the 'in vitro screen everything' approach possible, but is this approach the most time-efficient and cost-effective strategy?

Application of ChemTree to predicting mutagenicity

Young, S.S.; Gombar, V.K.; Emptage, M.R.; Cariello, N.F. and Lambert, C.G., (2002) “Mixture De-Convolution and Analysis of Ames Mutagenicity Data”, Chemometrics and Intelligent Laboratory Systems, v.60 pp. 5-11.

Abstract: Mixtures abound in chemistry; two or more compounds may be present in the same sample, the same biological effect may be produced by two different mechanisms, or two compounds might bind to a receptor in different orientations or even in different places. Sometimes, results are given in summary form. For example, a chemical may be declared a mutagen due to any of several assay results from an Ames test. Clearly, a single mathematical model is not going to hold for data sets where such multiplicities of phenomena are represented. We need molecular descriptors and statistical methods which enable us to deconvolute such mixtures. Our idea is to combine topological chemical descriptors -- augmented atoms and through-bond distance measures -- with a statistical technique, segmentation recursive partitioning, that is capable of dealing with mixtures. The benefit is the ability to develop structure-activity relationships for large, heterogeneous data sets. We successfully demonstrate the effectiveness of the above descriptors and the technique of recursive partitioning with ames test results taken from public sources.