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.
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.
To use this node in KNIME, install the extension MOE Extensions for KNIME from the below update site following our NodePit Product and Node Installation Guide:
A zipped version of the software site can be downloaded here.
Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
Try NodePit Runner!