Forge Score Machine Learning

Calculates predicted activity for molecules using a Machine Learning model generated with Forge™ or the 'Forge Build Machine Learning' node. Unless a 2D kNN model was generated the molecules must be pre-aligned in a manner consistent with the original model to make sensible predictions- the falign program or the 'Forge Align' node are ideal for this.

Please refer to the Forge manual for a detailed description of the science behind Machine Learning models in Forge and the corresponding model building options.

This node wraps the Forge Score executable 'fscore', which must be installed with a valid license for this node to work. If this is installed in the default location on Windows, then it should be found automatically. Otherwise, you must either set the 'Cresset Home' preference or the CRESSET_HOME environment variable to the base Cresset software install directory. You may also set the 'fscore Path' preference or the CRESSET_FORGESCORE_EXE environment variable to point directly at the executable itself.

The Forge Score Machine Learning node can be configured to use additional resources to perform calculations. The time taken for the node to run will be drastically reduced using the Cresset's Engine Broker. To use this facility either set the 'Cresset Engine Broker' preference or the CRESSET_BROKER environment variable to point to the location of your local Engine Broker. If you do not currently have the Cresset Engine Broker then contact Cresset ( for pricing on local and cloud based brokers.

For more information visit or contact us at



Structure Column
The column in the first input datatable containing the molecules to fit to the Machine Learning model. Except for 2D kNN models the molecules must be pre-aligned.
Assign formal charges to input molecules
If checked, the protonation states for the input molecules are set using Cresset's charging rules. Acids will be deprotonated, primary amines protonated, etc.
Automatically calculate the number of neighbors to consider
If checked, then the optimal number of neighbors as determined by Forge or the Forge Build Machine Learning node will be used. This option is ignored for model types other than kNN.
Number of neighbors to consider when fitting compounds to the model
Manually sets the number of neighbors k to use when fitting compounds to the model. The q^2 information for this setting can be viewed by using the Forge Project Viewer node the Forge Model Info node on the Forge project containing the model. This option is ignored for model types other than kNN

Input Ports

The molecules to fit to the model. Except for 2D kNN models, all molecules must be pre-aligned.
A Forge project containing the model. The 'Forge Build Machine Learning' node or the fbuild program are ideal for creating the Forge project.

Output Ports

The input molecules with their predicted activity. For kNN models the 'distance to model' and 'activity error' information is also added to the molecules.


This node has no views




You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.