02_Bioactivity_Prediction_Transform

This workflow is the second one executed by the Model Factory. It removes artifacts and computes chemical fingerprints using RDKit cheminformatics library (http://www.rdkit.org).

Input: The input of the node contains the path to the file as loaded by the load workflow ("filePath") along with additional parameters specific for a data set (e.g. assay_id)
Output: Include the path to the file for the test data set (filePath_Test) and the Training Data Set ("filePath_Train").

This workflow is part of the model factory eco system. Please refer to our blogpost for further details