QSAR Workflows

From CDK-Taverna 2.0 Wiki

Jump to: navigation, search

This section describes workflows for QSAR descriptor calculation and result processing.

Contents

QSAR descriptor calculation workflow

This workflow calculates QSAR properties and saves them as a CSV file. The molecules are read iteratively from a SD file. Additionally it writes out the molecules with unknown atom types, salt counter ions, curated molecule library with UUIDs and the used calculation time of every QSAR descriptor as a CSV file.Furthermore explicit hydrogens are added and a Hueckel aromaticity detection is performed.
Go to MyExperiment

Draft of the QSAR descriptor calculation workflow.

Configuration annotations:

  • The file writers 1,2,3 should write out a single file. So the "One File Per Iteration" checkbox must be unchecked.
  • The file writers 4,6 should write out a single file for each iteration. Here the "One File Per Iteration" checkbox must be checked.
    The time CSV files contain the cumulated duration of each QSAR descriptor
    The QSAR descriptor value CSV files should be merged with the Merge QSAR CSV files workflow.
  • Set the list handling of activity 5 to dot product.
Folder structure example.

Merge QSAR CSV files workflow

This workflow merges QSAR descriptor CSV files into a single CSV file. Therefore it loads the CSV files from hard disk and builds a single QSAR descriptor vector. Afterwards the vector is converted in a one single CSV file and saved to hard disk.
Go to MyExperiment

Draft of the Merge QSAR CSV files workflow.

Configuration annotations:

  • The input activity supports multiple file selection.
  • Set the list handling of the second activity to dot product.

Curate QSAR descriptor CSV file workflow

This workflow erases descriptor entries which were not calculated. Therefor the CSF files are loaded and afterwards processed. At the end the curated CSV file is written to hard disk. The curation method can be chosen in the curation activity.
Go to MyExperiment

Draft of the Curate QSAR descriptor CSV file workflow.

Configuration annotations:

  • Set the list handling of the second and third activity to dot product.
  • Before setting the curation method use the Calculate QSAR Vector Statistics activity to analyse the CSV file.

Get Molecular Weight Distribution From QSAR Vector workflow

This workflow calculates a molecular weight distribution from given QSAR vector. Therefor it reads a CSV from hard disk and converts it into a QSAR vector. Finally the molecular weight distribution is written to hard disk as a CSV file.

Draft of the Get Molecular Weight Distribution From QSAR Vector workflow.
Molecular Weight Distribution example.

Contact

For further questions, feel free to contact us at the CDK-Taverna mailing list:
https://lists.sourceforge.net/lists/listinfo/cdk-taverna

Personal tools