Icon

Model Prediction Chemistry

This workflow snippet demonstrates how to use a trained bioactivity model to predict the bioactivity of new molecules. The model was trained in the previous workflow snippet "Machine Learning Chemistry" (see https://kni.me/w/aJOlJNgWjHwAUnP5) and is read in using the Model Reader node. Similar to the previouse workflow snippet, the RDKit fingerprint is calculated for each molecule and the Random Forest Predictor applies the model on the new molecules.
The results can be inspected in the "Visualise Prediction" component.


This workflow snippet demonstrates how to use a trained model to predict bioactivity of chemical structures. RDKit fingerprintmolecules.tableuse model to predict on new dataread trained modelconvert smiles to images RDKit Fingerprint Table Reader Random ForestPredictor Model Reader Renderer to Image VisualisePredictions This workflow snippet demonstrates how to use a trained model to predict bioactivity of chemical structures. RDKit fingerprintmolecules.tableuse model to predict on new dataread trained modelconvert smiles to imagesRDKit Fingerprint Table Reader Random ForestPredictor Model Reader Renderer to Image VisualisePredictions

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: janinamothes
Created at: 2021-10-01
On NodePit since: 2021-12-18
Last update: 2024-04-30
Created with KNIME version: v4.4.1
Tags: Life SciencesCheminformaticsbioactivityModel Prediction

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!