Abstract
We developed highly predictive classification models for human liver microsomal (HLM) stability using the apparent intrinsic clearance (CLint, app) as the end point. HLM stability has been shown to be an important factor related to the metabolic clearance of a compound. Robust in silico models that predict metabolic clearance are very useful in early drug discovery stages to optimize the compound structure and to select promising leads to avoid costly drug development failures in later stages. Using Random Forest and Bayesian classification methods with MOE, E-state descriptors, ADME Keys, and ECFP_6 fingerprints, various highly predictive models were developed. The best performance of the models shows 80 and 75% prediction accuracy for the test and validation sets, respectively. A detailed analysis of results will be shown, including an assessment of the prediction confidence, the significant descriptors, and the application of these models to drug discovery projects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kwon Y (2001) Handbook of essential pharmocokinetics, pharmacodynamics and drug metabolism for industrial scientists, 1st edn. Springer, Berlin
Jolivette LJ, Ekins S (2007) Adv Clin Chem 43:131
Taylor C, Janisewski J, Whalen K (2006) Integrated high-throughput ADME: a 384-well human liver microsome assay to determine metabolic profiles of 1800 compounds per week. Poster, AAPS. Annual Meeting
JMP 5.1.1, SAS Publishing, SAS Campus Drive, Cary, NC 27513–2414
Molecular Operating Environment (MOE) software 2005.06, Chemical Computing Group Inc., 1255 University Street, Montreal, Quebec, Canada, H3B 3 × 3
Hall LH, Kier LB (1999) Molecular structure description: the electrotopological state. Academic, New York
The ADME keys were coded by Jing Lu from different resources: The majority of the ADME keys were not from literature. Only a small portion was from J. of Chemical and Computer Information Science 1997, 37, 329. The other sources include common functional groups and rings liable to metabolism based on personal understanding, ISIS Keys, Hetero rings from John Blake, A few fragments from Pfizer at Nagoya, Japan
ISIS/Base, Version 2.1.3; Molecular Design Ltd. (14600 Catalina Street, Irvine, CA 92714
Pipeline Pilot 4.5 is a program of SciTegic (Accelrys, Inc.), 10188 Telesis Court. Suite 100, San Diego, CA 92121–4779 USA (http://www/scitegic.com/)
Rogers D, Brown RD, Hahn M (2005) J Biomol Screen 10(7):682
Morgan HL (1965) J Chem Doc 5:107
Brieman L (2001) Mach Learn 45:5
Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP (2003) J Chem Inf Comput Sci 43:1947
R Development Core Team (2004) R: a language and environment for statistical computing. http://www.R-project.org
Migliavacca E (2003) Mini-Rev Med Chem 3:831
Dunn G, Everitt B (1995) Clinical biostatistics: an introduction to evidence-based medicine. Edward Arnold, London
Carhart RE, Smith DE, Venkataraghavan R (1985) J Chem Inf Comput Sci 25:64
Acknowledgment
We would like to thank Rob Goulet and Shao-Tien Sng for their technical support to implement the model in Rgate, Genevieve Paderes and Klaus Dress for providing use cases, Cornel Catana, Ben Burke, Meihua Tu, Jason Hughes, Chad Stoner, Marcel de Groot, and Eric Gifford for their scientific discussions. Special thanks goes to Dan Ortwine for the critical reading of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, P.H., Cucurull-Sanchez, L., Lu, J. et al. Development of in silico models for human liver microsomal stability. J Comput Aided Mol Des 21, 665–673 (2007). https://doi.org/10.1007/s10822-007-9124-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10822-007-9124-0