Golden Helix ChemTree

ChemTree Drug Discovery Software Product Summary

ChemTree® Drug Discovery Software is statistical analysis software based on recursive partitioning. It facilitates intelligent, target specific compound selection for High Throughput Screening (HTS). The software takes the compound structures and results from a screen, generates a model that predicts the results based on molecular features, and applies that model to untested compounds - thereby increasing hit rates on future testing. On average, this sequential process can increase hit rates by 500% to 1600% while simultaneously reducing the number of compounds tested by 80% or more, thus generating substantial savings. (Analysis of a Large Structure/Biology Activity Data Set Using Recursive Partitioning, JCICS, A. Rusinko et al., V. 39 (6))

Definition

Sequential High Throughput Screening is the iterative process of screening a sample of compounds for activity, analyzing the results, and selecting a new set of compounds for screening based on what has been learned from the previous screens. Selection of compounds is driven by finding Structure Activity Relationships (SARs) within the screened compounds and using those relationships to drive further selection.

ChemTree Drug Discovery Software Product Benefits:

Reduce your company's clinical failures through better discovery:

• Eliminate failures before they enter clinical trials by optimizing for efficacy, safety and ADMET earlier
• Enable earlier and more cost-effective ADMET optimization through low throughput in vitro/in silico screening
• Reduce attrition rate of compounds in later stages of pipeline by optimizing for efficacy, safety and ADME/Tox at the same time
• Simultaneously optimize many screening endpoints with multivariate recursive partitioning (RP)

Save time and resources by prioritizing what you screen next:

• Increase hit rates from 10 - 100 times through intelligent "Cherry Picking"
• Maximize hit rates through focused combinatorial synthesis
• Generate nanomolar concentration leads with the sequential screening process
• Automate screening analysis tasks to accelerate your drug discovery pipeline
• Resurrect failed screening attempts Uncover QSAR relationships to accelerate lead optimization:
• Give lead optimization chemists a jump start by automatically highlighting the 'business end' of a molecule
• Capture the most from your screening investment by learning from both actives and inactives
• Accelerate the identification of lead series through structure/activity clustering
• Gain deeper chemical insight by automatic detection of interacting molecular features
• Derive value from noisy HTS data using ensemble averaging of many RP trees

Other benefits:

• ChemTree® is reliable, easy to use and can be learned in one day.
• ChemTree® handles large amounts of data.
• ChemTree® supports your current compound selection process.
  

The Bottom Line:

ChemTree gives you two appealing alternatives:

• Test many fewer compounds to reach your screening goals and save substantial sums of money, time and effort, or
• Continue to test the same total number of compounds per assay but increase the number of hits you find

Product features:

High throughput screening customization:

• Generates predictive models for binding activity that work even if multiple binding sites are present. Models can predict active candidates from enormous corporate compound collections, third party suppliers, and combinatorial libraries, targeting the compound acquisition process.
• Simultaneously analyzes multiple assays screened on the same set of compounds and optimizes acquisition of new, selective compounds.
• Uses intuitive and whole-molecule based chemical descriptors for finding structure activity relationships. Includes functional groups, distance-based descriptors, and Burden numbers.
• Enhances selection of compounds - which should minimize the chance of side effects.
• Displays compounds while highlighting the functional groups promoting and/or inhibiting activity.

Powerful statistical methodology:

• Provides univariate and multivariate, multi-way decision tree recursive partitioning analysis.
• Allows presentation of complex analysis results of multiple targets in a way that is easy for chemists to understand.
• Uses statistical methods to prevent over fitting.
• Incorporates chemical structural information mapping biological activity to chemical features.
  

Advanced computer science:

• Uses proprietary fast algorithms for decision-tree building.
• Takes advantage of parallel processing, where available.
• Analyzes extremely large, complex data sets in real time. Takes minutes to compute an analysis, not days.
• Supports data analysis in both automatic and interactive exploratory modes.
• Provides a simple graphical user interface.
  

Available Platforms:

ChemTree currently runs under Windows 98/NT/2000, Mac OS X and Linux. Other ports are available upon request for most UNIX variants.