Bozeman, Montana (December 12, 2002) - Golden Helix, Inc. (GHI) announced today a new release of ChemTree®, reconfigured into three process specific modules, with a powerful multivariate analysis capability.
The Multivariate Analysis module of ChemTree® was developed in response to the many chemists seeking this capability. The powerful recursive partitioning technique enables chemists to understand SAR rules that define optimal compounds across multiple measures of compound fitness. For instance, ChemTree® can simultaneously analyze the results of screening a set of compounds against several efficacy and/or ADME/Tox targets. Using a sequential screening model it is possible to efficiently prosecute the more expensive ADME/Tox screens. Utilizing this tool early in the screening process reduces attrition rates for compounds in later stages by optimizing for efficacy, safety, and ADME/Tox simultaneously. Since most of the money in drug discovery and development is spent on failures, the ability to reduce the attrition rate by even a modest fraction can save millions in overall R& D expenditures.
The software is powered by the patented GHI recursive partitioning (RP) engine, known to be the fastest RP algorithm in the world. The modules are built around an intuitive interface with strong visualization capability. Users can choose the modules that fit their work process, purchasing all three or a tailored combination. Any chemoinformatician who uses computation to accelerate research will find the new ChemTree® modules essential new tools.
ChemTree features include: SAR Analysis, Multiple Trees, GUCCI (a feature that simultaneously clusters compounds according to structure, activity and binding mechanism), Cherry Picking, and a Multivariate Analysis feature for the analysis of multiple targets and ADME/Tox analysis. Current ChemTree users have reported hit rate increases of an order of magnitude.
The ChemTree recursive partitioning method employs hypothesis testing with p-values to partition entries according to relationships between dependent and independent variables. Both normal and binomial distributions are supported for the response. Predictors can be binary, continuous, ordinal or nominal type. The software singles out the most significant variables. The partitioning mechanism continues until there are no further significant splits. Complex data associations and correlations are viewed in a single easy-to-view screen.
Golden Helix software runs in a user friendly, interactive mode for in-depth analysis or in a batch mode environment to run repetitive analytical and predictive tasks. In addition to application licenses, Golden Helix offers training and consulting services and tailors analysis methodologies to specific customer needs.
About Golden Helix, Inc.
Founded in 1998 in Bozeman, MT, Golden Helix is a leading provider of data analysis software products and services designed to accelerate life science research and increase pharmaceutical R&D productivity. The company's products enable hundreds of researchers at the world's top pharmaceutical, biotech and non-profit research organizations to discover the genes that cause disease, improve target and lead discovery processes, and advance pharmacogenetic initiatives. Its products have been cited in nearly 100 peer reviewed publications that detail ground-breaking research for discovering the genetic and environmental basis of disease and creating safer and more effective medicines.
Golden Helix is committed to Accelerating the Quest for Significance.
For more information, please visit www.goldenhelix.com.
Director of Marketing
Golden Helix, Inc.