Icon

ML Prototyping for Bioactivity Data

This workflow demonstrates model building for a bioactivity data set with several machine learning methods and binary fingerprints of molecules.
The input data needs molecules in an SD file and a column containing the activity (the outcome that should be predicted). A fingerprint type can be chosen and set in the configuration. A report summarizing the input data and the modeling results can be downloaded after the workflow completion.



The data set represents a subset of 844 compounds evaluated for activity against CDPK1. 181 compounds inhibited CDPK1 with IC50 below 1uM and have "active" as their class.More information is available at https://chembl.gitbook.io/chembl-ntd/#deposited-set-19-5th-march-2016-uw-kinase-screening-hitsSee Set 19. Send data to reporting Choose a data file for uploadConfigure fingerprint computingROC CurvePositive Class Statistics TableAUCactive vs. inactivefile namefile URLInteractive View to explore molecular propertiesConfiguremolecular propertiescomputingRDKit From Molecule Renderer to Image RDKit DescriptorCalculation RDKit Fingerprint File Upload Choose fingerprint Image to Report Data to Report Data to Report Data to Report Data to Report Data to Report Select Compounds forMachine Learning Define Metadata and SelectMolecular Properties SDF Reader Build Models Summarizeinput data Results The data set represents a subset of 844 compounds evaluated for activity against CDPK1. 181 compounds inhibited CDPK1 with IC50 below 1uM and have "active" as their class.More information is available at https://chembl.gitbook.io/chembl-ntd/#deposited-set-19-5th-march-2016-uw-kinase-screening-hitsSee Set 19. Send data to reporting Choose a data file for uploadConfigure fingerprint computingROC CurvePositive Class Statistics TableAUCactive vs. inactivefile namefile URLInteractive View to explore molecular propertiesConfiguremolecular propertiescomputingRDKit From Molecule Renderer to Image RDKit DescriptorCalculation RDKit Fingerprint File Upload Choose fingerprint Image to Report Data to Report Data to Report Data to Report Data to Report Data to Report Select Compounds forMachine Learning Define Metadata and SelectMolecular Properties SDF Reader Build Models Summarizeinput data Results

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: daria_knime
Created at: 2018-05-03
On NodePit since: 2022-07-04
Last update: 2024-04-26
Created with KNIME version: v4.5.2
Tags: CheminformaticsWebportalData VisualizationFingerprintMachine LearningRDKitBIRTReportingROCLife Sciences

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

Try NodePit Runner!