MAD Learner

This node is an independent implementation of:
Eckert, Hanna; Bajorath, Juergen
Determination and Mapping of Activity-Specific Descriptor Value Ranges for the Identification of Active Compounds
J. Med. Chem. (2006), 49, 2284–2293.
The method calculates a set of 2D descriptors for the active molecules. A score is calculated for each descriptor such that the score is higher if overlap of the value distribution for the actives with the value distribution of a huge reference is smaller. All descriptors are than ranked by their scores. The model will consist of the n highest-ranked descriptors.
The Model Evaluate node can be used to calculate predictions.

Options

Molecule Field
Field containing the active molecules
Partial Charges
Some descriptors require the precalculation of partial charges. For consistency reasons charges have to be calculated the same way for the training and the test set.
Minimum number of descriptors
Minimum number of descriptors that should be included in the model independent of their scores.
Score Threshold
Minimum descriptor score required for a descriptor to be included in the model unless the minimum number of descriptor in the model has not been reached.

Input Ports

Icon
Active Molecules

Output Ports

Icon
MOE MAD Model

Popular Predecessors

Popular Successors

  • No recommendations found

Views

MAD Learner
Summary

Workflows

  • No workflows found

Links

Developers

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.