Skip to content

Latest commit

 

History

History
 
 

RDKit_UGM_2019

README.md

Open Source pKa Predictions

Prerequisites to Run the Notebook

In addition to Jupyter, IPython and Python 3.6 (or higher) the following libraries are required:

  • Matplotlib
  • Numpy
  • Pandas
  • RDKit
  • Scikit-Learn
  • Seaborn

Dataset

The monoprotic pKa dataset was derived from the raw data of ChEMBL25 and DataWarrior. The pKa calculator plugin of Marvin[1] was used for pKa prediction and for the determination of the titratable groups.

Every SDF entry has four properties:

  • ID - A unique identifier over this dataset
  • pKa - The pKa value retrieved from DataWarrior and ChEMBL25 (may be averaged)
  • pKa_CX - The pKa value predicted by Marvin[1]
  • atom - The atom index of the titratable group

Author

Marcel Baltruschat - GitHub, E-Mail

License

The content of this folder is licensed under the MIT License - see the LICENSE.md file for details.

References

[1] Marvin 19.15.0, 2019, ChemAxon, http://www.chemaxon.com