A probabilistic approach to classifying metabolic stability

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.     

Applications of high throughput microsomal stability assay in drug discovery

High throughput in vitro microsomal stability assays are widely used in drug discovery as an indicator for in vivo stability, which affects pharmacokinetics. This is based on in-depth research involving a limited number of model drug-like compounds that are cleared predominantly by cytochrome P450 metabolism. However, drug discovery compounds are often not drug-like, are assessed with high throughput assays, and have many potential uncharacterized in vivo clearance mechanisms. Therefore, it is important to determine the correlation between high throughput in vitro microsomal stability data and abbreviated discovery in vivo pharmacokinetics study data for a set of drug discovery compounds in order to have evidence for how the in vitro assay can be reliably applied by discovery teams for making critical decisions. In this study the relationship between in vitro single time point high throughput microsomal stability and in vivo clearance from abbreviated drug discovery pharmacokinetics studies was examined using 306 real world drug discovery compounds. The results showed that in vitro Phase I microsomal stability t(1/2) is significantly correlated to in vivo clearance with a p-value<0.001. For compounds with low in vitro rat microsomal stability (t(1/2)<15 min), 87% showed high clearance in vivo (CL>25 mL/min/kg). This demonstrates that high throughput microsomal stability data are very effective in identifying compounds with significant clearance liabilities in vivo. For compounds with high in vitro rat microsomal stability (t(1/2)>15 min), no significant differentiation was observed between high and low clearance compounds. This is likely owing to other clearance pathways, in addition to cytochrome P450 metabolism that enhances in vivo clearance. This finding supports the strategy used by medicinal chemists and drug discovery teams of applying the in vitro data to triage compounds for in vivo PK and efficacy studies and guide structural modification to improve metabolic stability. When in vitro and in vivo data are both available for a compound, potential in vivo clearance pathways can be diagnosed to guide further discovery studies.     

In vitro high throughput screening of compounds for favorable metabolic properties in drug discovery

Drug metabolism can have profound effects on the pharmacological and toxicological profile of therapeutic agents. In the pharmaceutical industry, many in vitro techniques are in place or under development to screen and optimize compounds for favorable metabolic properties in the drug discovery phase. These in vitro technologies are meant to address important issues such as: (1) is the compound a potent inhibitor of drug metabolising enzymes (DMEs)? (2) does the compound induce the expression of DMEs? (3) how labile is the compound to metabolic degradation? (4) which specific enzyme(s) is responsible for the compound's biotransformation? and (5) to which metabolites is the compound metabolized? Answers to these questions provide a basis for judging whether a compound is likely to have acceptable pharmacokinetic properties in vivo. To address these issues on the increasing number of compounds inundating the drug discovery programs, high throughput assays are essential. A combination of biochemical advances in the understanding of the function and regulation of DMEs (in particular, cytochromes P450, CYPs) and automated analytical technologies are revolutionizing drug metabolism research. Automated LC-MS based metabolic stability, fluorescence, radiometric and LC-MS based CYP inhibition assays are now in routine use. Automatible models for studying CYP induction based on enzyme activity, quantitative RT-PCR and reporter gene systems are being developed. We will review the utility and limitations of these HTS approaches and highlight on-going developments and emerging technologies to answer metabolism questions at the different stages of the drug discovery process.     

Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction

Quantitative structure–activity relationships (QSAR) methods are urgently needed for predicting ADME/T (absorption, distribution, metabolism, excretion and toxicity) properties to select lead compounds for optimization at the early stage of drug discovery, and to screen drug candidates for clinical trials. Use of suitable QSAR models ultimately results in lesser time-cost and lower attrition rate during drug discovery and development. In the case of ADME/T parameters, drug metabolism is a key determinant of metabolic stability, drug–drug interactions, and drug toxicity. QSAR models for predicting drug metabolism have undergone significant advances recently. However, most of the models used lack sufficient interpretability and offer poor predictability for novel drugs. In this review, we describe some considerations to be taken into account by QSAR for modeling drug metabolism, such as the accuracy/consistency of the entire data set, representation and diversity of the training and test sets, and variable selection. We also describe some novel statistical techniques (ensemble methods, multivariate adaptive regression splines and graph machines), which are not yet used frequently to develop QSAR models for drug metabolism. Subsequently, rational recommendations for developing predictable and interpretable QSAR models are made. Finally, the recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction, including in vivo hepatic clearance, in vitro metabolic stability, inhibitors and substrates of cytochrome P450 families, are briefly summarized.     

Development of QSAR models for microsomal stability: identification of good and bad structural features for rat,human and mouse microsomal stability

High throughput microsomal stability assays have been widely implemented in drug discovery and many companies have accumulated experimental measurements for thousands of compounds. Such datasets have been used to develop in silico models to predict metabolic stability and guide the selection of promising candidates for synthesis. This approach has proven most effective when selecting compounds from proposed virtual libraries prior to synthesis. However, these models are not easily interpretable at the structural level, and thus provide little insight to guide traditional synthetic efforts. We have developed global classification models of rat, mouse and human liver microsomal stability using in-house data. These models were built with FCFP_6 fingerprints using a Naïve Bayesian classifier within Pipeline Pilot. The test sets were correctly classified as stable or unstable with satisfying accuracies of 78, 77 and 75% for rat, human and mouse models, respectively. The prediction confidence was assigned using the Bayesian score to assess the applicability of the models. Using the resulting models, we developed a novel data mining strategy to identify structural features associated with good and bad microsomal stability. We also used this approach to identify structural features which are good for one species but bad for another. With these findings, the structure-metabolism relationships are likely to be understood faster and earlier in drug discovery.     

High-Throughput Metabolic Soft-Spot Identification in Liver Microsomes by LC/UV/MS: Application of a Single Variable Incubation Time Approach

CYP-mediated fast metabolism may lead to poor bioavailability, fast drug clearance and significant drug interaction. Thus, metabolic stability screening in human liver microsomes (HLM) followed by metabolic soft-spot identification (MSSID) is routinely conducted in drug discovery. Liver microsomal incubations of testing compounds with fixed single or multiple incubation time(s) and quantitative and qualitative analysis of metabolites using high-resolution mass spectrometry are routinely employed in MSSID assays. The major objective of this study was to develop and validate a simple, effective, and high-throughput assay for determining metabolic soft-spots of testing compounds in liver microsomes using a single variable incubation time and LC/UV/MS. Model compounds (verapamil, dextromethorphan, buspirone, mirtazapine, saquinavir, midazolam, amodiaquine) were incubated at 3 or 5 µM with HLM for a single variable incubation time between 1 and 60 min based on predetermined metabolic stability data. As a result, disappearances of the parents were around 20–40%, and only one or a few primary metabolites were generated as major metabolite(s) without notable formation of secondary metabolites. The unique metabolite profiles generated from the optimal incubation conditions enabled LC/UV to perform direct quantitative estimation for identifying major metabolites. Consequently, structural characterization by LC/MS focused on one or a few major primary metabolite(s) rather than many metabolites including secondary metabolites. Furthermore, generic data-dependent acquisition methods were utilized to enable Q-TOF and Qtrap to continuously record full MS and MS/MS spectral data of major metabolites for post-acquisition data-mining and interpretation. Results from analyzing metabolic soft-spots of the seven model compounds demonstrated that the novel MSSID assay can substantially simplify metabolic soft-spot identification and is well suited for high-throughput analysis in lead optimization.