• Model building using the Learn method.
• Use a model to make a Prediction
• Fingerprint Methods
• 3D QSAR
• Learning Theory

There are four regression algorithms built into ICM:

• Partial Least Squares (plsRegression)
• Principal Component Regression(pcRegression)
• Nearest Neighbor Kernel Regression (nnkernelRegression)
• Random Forest Regression

Two Classification algorithms:

• Bayesian Classifier
• Random Forest (randomForest)

All 2D molecular property predictors are calculated using fragment-based contributions and 3D models use Atomic Property Fields .

For 2D fingerprints we developed an original method for splitting a molecule into a set of linear or non-linear fragments of different length and representation levels and then each chemical pattern found is converted into a descriptor.

In order to perform 'learn and predict' in ICM information must be stored in a table, molecular table or csv file. See the tables chapter for more information on ICM tables. Both chemical compounds and numeric data can be source for building prediction models.