‹‹ Back to SVS Home

PICT

ChemTree® Manual

Version 5.1.0

Copyright ©2000-2007

Golden Helix Inc.



[Picture]
Welcome to ChemTree® !

ChemTree is a premier tool for extracting useful information from your data. At its heart is a sophisticated data analysis engine enhanced to support your ability to analyze compound screening data. Golden Helix offers three ways for you to learn the capabilities and features of ChemTree.

The first and most immediate approach is this manual. In it you will find directions for installing ChemTree, tutorials on its use, and a comprehensive reference. You will need to read the section on installing the product. Also, we strongly recommend that you read the tutorials.

We recognize the difficulties learning any new skill from a book or manual no matter how well it is written. So, as a second approach to learning about ChemTree, we strongly recommend that you visit our web site at http://www.goldenhelix.comand sign up for a web-based seminar. The seminar can be set up to accommodate your schedule and its content can be tailored to meet your specific needs. The time spent in the seminar has proven to be a very effective way for new users to jump start their productivity with ChemTree and seasoned users to quickly acclimate to new features.

Finally, Golden Helix also offers on site training on ChemTree. The on-site training is very beneficial for teams of people. Contact our sales staff to discuss your on site training options.

We are always looking for ways to improve ChemTree both in its basic capabilities as well as in its ability to inter-operate with other tools used in your work. ChemTree now has a feedback mechanism which is intended to encourage you to communicate feature requests, bugs(!), as well as your experiences with the product.

We look forward to hearing from you.

Christophe Lambert
President & CEO of Golden Helix

Trademarks Used

ChemTree is a registered trademark of Golden Helix Inc.  Microsoft, Microsoft SQL, Transact-JQL, Excel, Access and ODBC are registered trademarks of Microsoft, Inc. Oracle, Oracle PL-SQL and SQL Server are registered trademarks of Oracle, Inc. IBM and DB2 are registered trademarks of IBM. SAS is a registered trademark of SAS, Inc. Sybase is a registered trademark of Sybase,Inc. Any other incidentally used names that are registered trademarks are trademarks of their respective owners.
Contents
I  Installing ChemTree and Acquiring Data
1 Installing and Initializing ChemTree
 1.1 Installation Overview
 1.2 Release Notes
2 Welcome to ChemTree
 2.1 Goals for this Chapter
 2.2 Recursive Partitioning Primer
 2.3 The ChemTree Basic Workflow
 2.4 Tutorial 1: Performing the Basic Workflow in GUI Mode
 2.5 Tutorial 2: Cherry Picking Compounds Using ChemTree
3 Navigating the Main Screen
 3.1 Main Screen Overview
 3.2 Project Viewer Window
 3.3 Navigator Nodes
 3.4 The File Menu
 3.5 Tools Menu
 3.6 The Help Menu
4 Importing Your Data Into ChemTree
 4.1 General Considerations
 4.2 Mathematical Considerations
 4.3 Importing Data
5 Scripting and Other Integrated Statistical Tools
 5.1 Overview
 5.2 The Python Shell Window
 5.3 Running Scripts
 5.4 Selecting a Script Server
 5.5 Example Scripts
 5.6 Scripting Reference
 5.7 S-PLUS Integration
 5.8 R Integration
6 Using the Spreadsheet Viewer
 6.1 Spreadsheet Overview
 6.2 Manipulating, Filtering and Preparing Data Using the Spreadsheet
 6.3 Navigating the Spreadsheet Menus
II  Recursive Partitioning
7 Interactive Tree Analysis
 7.1 Tree Analysis Overview
 7.2 Setting Options for Tree Analysis
 7.3 Working with Nodes
 7.4 Manually Splitting Nodes
 7.5 Defining Splits
 7.6 The File Menu
 7.7 The Tree Menu
 7.8 The Font Menu - Resizing and Formatting Tree View
8 Prediction Recipes
 8.1 Training and Validation Recipe
 8.2 Getting the Best Prediction Performance
9 Random Tree Generation
 9.1 Random Tree Overview
 9.2 Creating a Random Tree Model
 9.3 Multitree Model Browsing - Tree View
10 Multivariate Tree Analysis
 10.1 Multivariate Analysis Overview
 10.2 Using More Than One Dependent Variable
11 Histogram Node Analysis
 11.1 Histogram Overview
 11.2 Viewing Split Data Histograms
12 Viewing the Observation Distance Matrix
 12.1 Observation Distance Matrix Overview
 12.2 Viewing Observation Distance Matrix
 12.3 Printing and Saving the Observation Distance Matrix
13 The Correlation Interaction View
 13.1 Correlation Interaction Overview
 13.2 Viewing Correlation Interactions
14 P-Value Plot
 14.1 Plotting P-values
 14.2 P-Value plot types
 14.3 The P-value Plot
 14.4 Reset View
 14.5 Copy to Clipboard
 14.6 Axis Selector
 14.7 Zooming into the Graph
 14.8 File Menu
 14.9 Create Bitmap
 14.10 Print Image
 14.11 P-Value Spreadsheet
15 Text Viewer
 15.1 Text Viewer Overview
 15.2 Navigating the Text Viewer Menus
16 Regression Analysis (Optional Module)
 16.1 Overview
 16.2 Performing Analysis
III  The Science Behind ChemTree
17 Formulas and Theories
 17.1 Split-Prediction Methodology
 17.2 Normally Distributed Response Binomial Predictor
 17.3 Normally Distributed Response Continuous-Ordinal Predictor
 17.4 Normally Distributed Response Categorical Predictor
 17.5 Linear Regression with Continuous Response
 17.6 Permutation Test Methodology (Optional Module)
 17.7 Results from Linear Regression
 17.8 Binomially Distributed Response Binary Predictor
 17.9 Binomially Distributed Response Continuous/Ordinal Predictor
 17.10 Binomially Distributed Response Categorical Predictor
 17.11 Categorical Response
 17.12 Logistic Regression with Binomial Response
 17.13 Results from Logistic Regression
 17.14 Caveats
 17.15 The False Discovery Rate and the Simes Method
A EULA
B REFERENCES
C BUG FIX HISTORY
 C.1 Bugs Fixed in Version 5.1.0 of ChemTree
 C.2 Bugs Fixed in Version 5.0.0 of ChemTree
 C.3 Bugs Fixed in Version 4.1.0 of ChemTree
 C.4 Bugs Fixed in Version 4.0.3 of ChemTree
 C.5 Bugs Fixed in Version 4.0.0 of ChemTree
 C.6 Bugs Fixed in Version 3.2.2 of ChemTree