Model Optimization and Selection

This workflow deploys an advanced parameter optimzation protocol with four machine learning methods. In this implementation the choice of features and one hyperparameter per method are being optimized. The dataset represents a subset of 844 compounds evaluated for activity against CDPK1. More information on the set is available https://www.ebi.ac.uk/chemblntd/#tcams_dataset. See Set 19.


This is a companion discussion topic for the original entry at https://kni.me/w/-ATVMu9EmIURm8kr

Hi guys,
the Model Optimization and Selection Workflow works good, thanks for that :-).
My question is how do I get the chemical structures out of the numbers of the confusion matrix.
Well I mean, if there are 5 true positives, how can I display the structure of these five true positives?

Thanks a lot for your help.
All the best,
Pascal

Hi Pascal,
Great to hear that you are enjoying using the workflow.
We display the confusion matrix via the Generic Javascript view. To display the confusion matrix together with the chemical structures in a single interactive view, you could use the Scorer (JavaScript) and the Tile View nodes in a component. I uploaded a possible example to KNIME Hub https://kni.me/w/R0axFQk1-d2M8Tc5

Pay attention that the data youā€™d need for the Scorer is available in the Score Model metanode at the output of the CASE Switch Data (end) node (Node 211). And in order to display the images of the molecules, you could generate them with the Renderer to Image node.

Best,
Daria

2 Likes

many thanks, daria :slight_smile: