Standardization workflow for QSAR-ready chemical structures pretreatment.

Performs required structure standardization tasks (related to salts/solvents, tautomers/mesomers, mixtures, inorganics, metals, aromaticity, 2D/3D...) prior to QSAR modeling or prediction. Starts from structures in SDF or SMILES format and produces standardized structures in different formats based on the selected parameters:
- Dimensions: 2D/3D
- Rings: Kekule or aromatic
- Format: SDF/SMILES
It also provides the list of failed structures and a summary file with initial and QSAR-ready smiles as well as InChI and InChIKeys.
The parameters selected by default are suggested for use in OPERA.

All configuration required is available in the input component. The workflow will then adapt and run autonomously.

The workflow can also be executed in batch mode using the command line:
<knime path>\knime.exe -reset -nosplash -nosave -application org.knime.product.KNIME_BATCH_APPLICATION -workflowDir="knime-workspace/QSAR-ready_2.5.8" -workflow.varaiable=cmd_input,"<input path>\inputfile",String

Reference:
Mansouri, K., Grulke, C.M., Judson, R.S. et al. OPERA models for predicting physicochemical properties and environmental fate endpoints. J Cheminform 10, 10 (2018). https://doi.org/10.1186/s13321-018-0263-1

External resources

• GitHub repository
• KNIME Hub