A Probabilistic Approach to Classifying Metabolic Stability

Abstract

Metabolic stability is an important property of drug molecules that should-optimally-be taken into account early on in the drug design process. Along with numerous medium- or high-throughput assays being implemented in early drug discovery, a prediction tool for this property could be of high value. However, metabolic stability is inherently difficult to predict, and no commercial tools are available for this purpose. In this work, we present a machine learning approach to predicting metabolic stability that is tailored to compounds from the drug development process at Bayer Schering Pharma. For four different in vitro assays, we develop Bayesian classification models to predict the probability of a compound being metabolically stable. The chosen approach implicitly takes the "domain of applicability" into account. The developed models were validated on recent project data at Bayer Schering Pharma, showing that the predictions are highly accurate and the domain of applicability is estimated correctly. Furthermore, we evaluate the modeling method on a set of publicly available data.

Computational Tools And Resources For Metabolism-Related Property Predictions. 2. Application To Prediction Of Half-Life Time In Human Liver Microsomes

“…Other studies, for example Schwaighofer et al [7], had used a value of 30 min. We only recomputed the GUSAR models with this longer cut-off time.…”

“…The same endpoint was also analyzed by Sakiyama et al in 2008 [6], for 2439 compounds using MOE descriptors and four different mathematical approaches: random forest, support vector machine (SVM), logistic regression and recursive partitioning. In 2008, Schwaighofer et al [7] developed human and rodent liver microsomal stability models for more than 3000 compounds from Bayer Schering Pharma in-house data using Dragon descriptors and a Gaussian process classifier. In 2010, Hu et al [8] used more than 15,000 compounds to build classification models for prediction of human and rodent half-life microsomal stability data based on SciTegic’s FCFP_6 fingerprints using a naive Bayesian classifier.…”

Two-Dimensional (2D) In Silico Models for Absorption, Distribution, Metabolism, Excretion and Toxicity (ADME/T) in Drug Discovery

“…In another study, Bayesian classification models were developed for predicting the probability of a compound being metabolically stable or unstable. The models were validated using in-house project data which ultimately proved the higher accuracy and applicability of the models [33]. A similar study used random forest and Bayesian classification methods for developing in silico models for human liver microsomal stability [35].…”

“…Prediction of metabolic stability using classical QSAR/QSPR methods has not attracted much attention as can be seen from the smaller number of reports involving such studies [reviewed in ref. 33]. In 2008, two studies used machine learning methods to predict/classify metabolic stability of pharmaceuticals [33,34].…”

“…33]. In 2008, two studies used machine learning methods to predict/classify metabolic stability of pharmaceuticals [33,34]. In one study, a data set of 1952 proprietary compounds belonging to the metabolically stable and unstable classes were used.…”