Benefit of Retraining pKa Models Studied Using Internally Measured Data.

Journal: Journal of chemical information and modeling
Published Date:

Abstract

The ionization state of drugs influences many pharmaceutical properties such as their solubility, permeability, and biological activity. It is therefore important to understand the structure property relationship for the acid-base dissociation constant pKa during the lead optimization process to make better-informed design decisions. Computational approaches, such as implemented in MoKa, can help with this; however, they often predict with too large error especially for proprietary compounds. In this contribution, we look at how retraining helps to greatly improve prediction error. Using a longitudinal study with data measured over 15 years in a drug discovery environment, we assess the impact of model training on prediction accuracy and look at model degradation over time. Using the MoKa software, we will demonstrate that regular retraining is required to address changes in chemical space leading to model degradation over six to nine months.

Authors

  • Peter Gedeck
    †Novartis Institute for Tropical Diseases Pte. Ltd., 10 Biopolis Road, #05-01 Chromos, Singapore 138670, Singapore.
  • Yipin Lu
    ‡Novartis Institute for Biomedical Research, 5300 Chiron Way, Emeryville, California 94608, United States.
  • Suzanne Skolnik
    §Novartis Institute for Biomedical Research, 250 Massachusetts Ave, Cambridge, Massachusetts 02139, United States.
  • Stephane Rodde
    ∥Novartis Institute for Biomedical Research, Postfach, CH-4002 Basel, Switzerland.
  • Gavin Dollinger
    ‡Novartis Institute for Biomedical Research, 5300 Chiron Way, Emeryville, California 94608, United States.
  • Weiping Jia
    Department of Endocrinology and Metabolism, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai Clinical Center for Diabetes, Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Diabetes Institute Shanghai 200233, China.
  • Giuliano Berellini
    §Novartis Institute for Biomedical Research, 250 Massachusetts Ave, Cambridge, Massachusetts 02139, United States.
  • Riccardo Vianello
    ∥Novartis Institute for Biomedical Research, Postfach, CH-4002 Basel, Switzerland.
  • Bernard Faller
    ∥Novartis Institute for Biomedical Research, Postfach, CH-4002 Basel, Switzerland.
  • Franco Lombardo
    §Novartis Institute for Biomedical Research, 250 Massachusetts Ave, Cambridge, Massachusetts 02139, United States.