Icon

Drug Discovery Workflow

Major steps: 1. Importing known CNS active compounds with their bioactivity data 2. Preprocessing the imported compounds (structure standardisation, duplicate filtering) 3. Clustering the molecules and selecting a scaffold for virtual compound library generation 4. Generation of virtual compounds via reaction-based chemical library enumeration 5. Filtering the enumerated virtual compounds based on their CNS MPO score 6. Searching for real, accessible analogues of the best virtual compounds 7. Filtering the real analogues based on their CNS MPO score 8. Predicting the activity of the real analogue molecules using a classification model built from the original known actives +1. Analyzing the overlap between the enumerated virtual compounds and their real analogues Import SDfile with CNS-active molecules (D2 displacement)Compound set preprocessingScaffold selectionR-group decompositionVirtual library enumerationSearch for real compounds similari to the virtual moleculesThe most promising compoundsVirtual molecules with high CNS MPO scoreReal molecules with high CNS MPO scoreOverlap of the virtual and real spacesModel building & classificationExport promising molecules MolImporter Structure standardisationand duplicate filtering Hierarchical clusteringfor scaffold selection Analysis of the substituentson the selected scaffold Generation of a virtual compoundlibrary via reaction enumeration Getting similar molecules fromthe Enamine REAL database Row Filter CNS MPO score-based filteringof the virtual compounds CNS MPO score-based filteringof the real anlogue molecules Overlap analyis between thevirtual and the real space Activity prediction forthe real molecules MolExporter Visualization of the activityand CNS MPO score results Major steps: 1. Importing known CNS active compounds with their bioactivity data 2. Preprocessing the imported compounds (structure standardisation, duplicate filtering) 3. Clustering the molecules and selecting a scaffold for virtual compound library generation 4. Generation of virtual compounds via reaction-based chemical library enumeration 5. Filtering the enumerated virtual compounds based on their CNS MPO score 6. Searching for real, accessible analogues of the best virtual compounds 7. Filtering the real analogues based on their CNS MPO score 8. Predicting the activity of the real analogue molecules using a classification model built from the original known actives +1. Analyzing the overlap between the enumerated virtual compounds and their real analogues Import SDfile with CNS-active molecules (D2 displacement)Compound set preprocessingScaffold selectionR-group decompositionVirtual library enumerationSearch for real compounds similari to the virtual moleculesThe most promising compoundsVirtual molecules with high CNS MPO scoreReal molecules with high CNS MPO scoreOverlap of the virtual and real spacesModel building & classificationExport promising molecules MolImporter Structure standardisationand duplicate filtering Hierarchical clusteringfor scaffold selection Analysis of the substituentson the selected scaffold Generation of a virtual compoundlibrary via reaction enumeration Getting similar molecules fromthe Enamine REAL database Row Filter CNS MPO score-based filteringof the virtual compounds CNS MPO score-based filteringof the real anlogue molecules Overlap analyis between thevirtual and the real space Activity prediction forthe real molecules MolExporter Visualization of the activityand CNS MPO score 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: dbarna
Created at: 2020-03-17
On NodePit since: 2022-08-21
Last update: 2024-11-21
Created with KNIME version: v4.6.0

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

Try NodePit Runner!