Icon

TeachOpenCADD

TeachOpenCADD - a teaching platform for computer-aided drug design using KNIME

The TeachOpenCADD KNIME (v1.0.5) pipeline consists of eight inter-connected workflows (W1-8) , each containing one topic in computer-aided drug design.
The pipeline is illustrated using the epidermal growth factor receptor (EGFR), but can easily be applied to other targets of interest. Topics include how to fetch, filter and analyze compound data associated with a query targe.

URL: Zenodo DOI https://doi.org/10.5281/zenodo.3475085

TeachOpenCADD: A teaching platform for computer-aided drug design using KNIME
W1
W4
W2
W5
W6
W7
W3
W8
Dominique Sydow, Michele Wichmann, Jaime Rodríguez-Guerra, Daria Goldmann, Gregory Landrum, andAndrea Volkamer
Dataset ranked bysimilarity to query compound
4. Ligand-based screening: compound similarity
Similarity to query
Scatter plot
Highlighted MCS
Table View (JavaScript)
Dataset ranked bysimilarity to query compound
4. Ligand-based screening: compound similarity
Dataset filtered & formatted bybioactivity and SMILES Note: Database query can be slow.
1. Data acquisition from ChEMBL
Tanimoto similarity
Enrichment Plotter (legacy)
Keep only top 2000 molsNote: Remove this nodewhen running your own dataset
Row Filter
Gefitinib
Query compound
Dataset filtered by X-ray,resolution & presence of ligand Note: Target ChEMBL ID can only be changed inside the metanode
8. Protein data acquisition: Protein Data Bank (PDB)
Dataset filtered byunwanted substructures
3. Molecular filtering: unwanted substructures
ML classifier(applicable to new compounds)
7. Ligand-based screening: machine learning
Filtered compound set
Table View (JavaScript)
Compound set
Table View (JavaScript)
Phys. chem. properties
Box Plot (JavaScript)
Gefitinib
Query compound
Score view
Evaluate model
Input target ChEMBL ID
Line Plot (JavaScript)
Diverse subset from clusters
Table View (JavaScript)
Compounds without PAINS/Brenk
Table View (JavaScript)
ROC curve
Evaluate model
Dataset filtered by Lipinski's rule of five
2. Molecular filtering: ADME and lead-likeness criteria
Get MCS for largest cluster in dataset
6. Maximum common substructures
Compounds with PAINS/Brenk
Table View (JavaScript)
Dataset clustered byFingerprint similarity Note: Clustering takes time!
5. Compound clustering

Nodes

Extensions

Links