Introduction

ADMEWORKS ModelBuilder is a tool for building mathematical models that can later be used for predicting various chemical and biological properties of compounds. The models are based on values of physicochemical, topological, geometrical, and electronic properties derived from the molecular structure - called descriptors.
Descriptor generator programs in ADMEWORKS ModelBuilder come mostly from ADAPT, the software system to study

Features

Main features of ModelBuilder Enterprise:

• Quantitative/qualitative Structure-Activity Relation's analysis
• Advanced results visualization capabilities
• Multiple statistical methods for generating predictive models: Perceptron, Iterative Least Squares Method, Multiple Linear Regression, Stepwise Regression, Leap-and-Bounds Regression, and Genetic Algorithm.
• No Limit on the no. of molecules to be exported
• Customizable cross-validation of models
• Multivariate/pattern recognition data analysis
• ADMET data analysis
• More than 500 predefined descriptors and an unlimited number of substructure-related descriptors
• Interactive graphs that display property distribution, predicted vs. actual activity, property correlations, clustering of samples and properties and others
• Interactive graphical feature and outlier selection tools
• Automated statistical tools for feature and sample selection
• Several classification models like FuzzyALS,ADA Boost, SVM, KNN
• SDF and CSV file import/export

Main features of ModelBuilder Standard:

• Quantitative/qualitative Structure-Activity Relation's analysis
• Advanced results visualization capabilities
• Multiple statistical methods for generating predictive models: Perceptron, Iterative Least Squares Method, Multiple Linear Regression, Stepwise Regression, Leap-and-Bounds Regression, and Genetic Algorithm
• Customizable cross-validation of models
• 500 molecules can be exported for studies
• Multivariate/pattern recognition data analysis
• ADMET data analysis
• More than 500 predefined descriptors and an unlimited number of substructure-related descriptors
• Interactive graphs that display property distribution, predicted vs. actual activity, property correlations, clustering of samples and properties and others
• Several classification models like LDA, KNN, Interactive -DF
• Interactive graphical feature and outlier selection tools

Applications

Use ADMEWORKS ModelBuilder to:

• Predict properties of compounds
• Perform ADMET analysis
• Virtually screen large libraries for molecules with desirable property profiles
• Support hit finding and lead optimisation decisions
• Data mine databases and compound libraries
• Speed up innovation

Software Offerings

• ADMEWORKS ModelBuilder Enterprise
• ADMEWORKS ModelBuilder Standard

-