Best of both worlds: An expansion of the state of the art pK a model with data from three industrial partners.

Autor: Fraczkiewicz R; Simulations Plus, Inc., 42505 10th Street West, Lancaster, CA 93534, USA., Quoc Nguyen H; Genentech Inc., Discovery Chemistry, 1 DNA Way, South San Francisco, CA 94080, USA., Wu N; Genentech Inc., Discovery Chemistry, 1 DNA Way, South San Francisco, CA 94080, USA., Kausch-Busies N; Bayer AG, Research & Development, Crop Science, 40789, Monheim, Germany., Grimbs S; Bayer AG, Research & Development, Crop Science, 40789, Monheim, Germany., Sommer K; Bayer AG, Research & Development, Crop Science, 40789, Monheim, Germany., Ter Laak A; Bayer AG, Research & Development, Pharmaceuticals, 13353, Berlin, Germany., Günther J; Bayer AG, Research & Development, Pharmaceuticals, 13353, Berlin, Germany., Wagner B; F. Hoffmann-La Roche AG, Roche Pharma Research and Early Development, 4070, Basel, Switzerland., Reutlinger M; F. Hoffmann-La Roche AG, Roche Pharma Research and Early Development, 4070, Basel, Switzerland.
Jazyk: angličtina
Zdroj: Molecular informatics [Mol Inform] 2024 Oct; Vol. 43 (10), pp. e202400088. Date of Electronic Publication: 2024 Jun 21.
DOI: 10.1002/minf.202400088
Abstrakt: In a unique collaboration between Simulations Plus and several industrial partners, we were able to develop a new version 11.0 of the previously published in silico pK a model, S+pKa, with considerably improved prediction accuracy. The model's training set was vastly expanded by large amounts of experimental data obtained from F. Hoffmann-La Roche AG, Genentech Inc., and the Crop Science division of Bayer AG. The previous v7.0 of S+pKa was trained on data from public sources and the Pharmaceutical division of Bayer AG. The model has shown dramatic improvements in predictive accuracy when externally validated on three new contributor compound sets. Less expected was v11.0's improvement in prediction on new compounds developed at Bayer Pharma after v7.0 was released (2013-2023), even without contributing additional data to v11.0. We illustrate chemical space coverage by chemistries encountered in the five domains, public and industrial, outline model construction, and discuss factors contributing to model's success.
(© 2024 The Author(s). Molecular Informatics published by Wiley-VCH GmbH.)
Databáze: MEDLINE
Externí odkaz: