Fingerprint Model Learner (deprecated)

This Node Is Deprecated — This node is kept for backwards-compatibility, but the usage in new workflows is no longer recommended. The documentation below might contain more information.

A fingerprint model is a fingerprint description of a set of molecules. The goal of the fingerprint model is to capture consensus features of interest in the source data. Fingerprints of all the molecules in the source set are included in the model along with scoring criteria that will determine how similar the fingerprint of a new molecule is to those of the original set, collectively.When evaluated, a fingerprint model will generate either a hit/miss result (1 (hit) or 0), or a value in the range [0..1]. The fingerprint being tested is compared to each fingerprint in the model using the specified similarity metric. The results of these comparisons are combined according to the specified scoring function and the kind of result desired.<br />The Model Evaluate node can be used to calculate predictions.

Options

Molecule Field
Field(s) containing the molecules
Fingerprint
Select fingerprint that should be used to create the model
Fingerprint (other)
Name of the other fingerprint.
Metric
Select similarity metric. For Shape Fingerprints Inverse Distance must be selected.
Similarity (other)
Name of Similarity Function (leave blank for default)
Score
<b>Maximum:</b> The maximum of the individual similarity scores is output.<br /><b>Minimum:</b> The minimum of the individual similarity scores is output.<br /><b>Average:</b> The average of the individual similarity scores is output.<br /><b>Distance:</b> The overall distance of the similarities, calculated to be the square root of the averaged sum of the squares, is output.

Input Ports

Icon
Active Molecules

Output Ports

Icon
MOE Fingerprint Model

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

Summary
Displays Runtime Information

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.