Machine Learning Strategies When Transitioning between Biological Assays.

Machine learning is widely used in drug development to predict activity in biological assays based on chemical structure. However, the process of transitioning from one experimental setup to another for the same biological endpoint has not been extensively studied. In a retrospective study, we here explore different modeling strategies of how to combine data from the old and new assays when training conformal prediction models using data from hERG and NaV assays. We suggest to continuously monitor the validity and efficiency of models as more data is accumulated from the new assay and select a modeling strategy based on these metrics. In order to maximize the utility of data from the old assay, we propose a strategy that augments the proper training set of an inductive conformal predictor by adding data from the old assay but only having data from the new assay in the calibration set, which results in valid (well-calibrated) models with improved efficiency compared to other strategies. We study the results for varying sizes of new and old assays, allowing for discussion of different practical scenarios. We also conclude that our proposed assay transition strategy is more beneficial, and the value of data from the new assay is higher, for the harder case of regression compared to classification problems.

In silico approaches in organ toxicity hazard assessment: current status and future needs in predicting liver toxicity.

Hepatotoxicity is one of the most frequently observed adverse effects resulting from exposure to a xenobiotic. For example, in pharmaceutical research and development it is one of the major reasons for drug withdrawals, clinical failures, and discontinuation of drug candidates. The development of faster and cheaper methods to assess hepatotoxicity that are both more sustainable and more informative is critically needed. The biological mechanisms and processes underpinning hepatotoxicity are summarized and experimental approaches to support the prediction of hepatotoxicity are described, including toxicokinetic considerations. The paper describes the increasingly important role of in silico approaches and highlights challenges to the adoption of these methods including the lack of a commonly agreed upon protocol for performing such an assessment and the need for in silico solutions that take dose into consideration. A proposed framework for the integration of in silico and experimental information is provided along with a case study describing how computational methods have been used to successfully respond to a regulatory question concerning non-genotoxic impurities in chemically synthesized pharmaceuticals.

Predicting the Risk of Phospholipidosis with in Silico Models and an Image-Based in Vitro Screen.

The drug-induced accumulation of phospholipids in lysosomes of various tissues is predominantly observed in regular repeat dose studies, often after prolonged exposure, and further investigated in mechanistic studies prior to candidate nomination. The finding can cause delays in the discovery process inflicting high costs to the affected projects. This article presents an in vitro imaging-based method for early detection of phospholipidosis liability and a hybrid approach for early detection and risk mitigation of phospolipidosis utilizing the in vitro readout with in silico model prediction. A set of reference compounds with phospolipidosis annotation was used as an external validation set yielding accuracies between 77.6% and 85.3% for various in vitro and in silico models, respectively. By means of a small set of chemically diverse known drugs with in vivo phospholipidosis annotation, the advantages of combining different prediction methods to reach an overall improved phospholipidosis prediction will be discussed.

Flagging Drugs That Inhibit the Bile Salt Export Pump.

The bile salt export pump (BSEP) is an ABC-transporter expressed at the canalicular membrane of hepatocytes. Its physiological role is to expel bile salts into the canaliculi from where they drain into the bile duct. Inhibition of this transporter may lead to intrahepatic cholestasis. Predictive computational models of BSEP inhibition may allow for fast identification of potentially harmful compounds in large databases. This article presents a predictive in silico model based on physicochemical descriptors that is able to flag compounds as potential BSEP inhibitors. This model was built using a training set of 670 compounds with available BSEP inhibition potencies. It successfully predicted BSEP inhibition for two independent test sets and was in a further step used for a virtual screening experiment. After in vitro testing of selected candidates, a marketed drug, bromocriptin, was identified for the first time as BSEP inhibitor. This demonstrates the usefulness of the model to identify new BSEP inhibitors and therefore potential cholestasis perpetrators.

Ligand-based target prediction with signature fingerprints.

When evaluating a potential drug candidate it is desirable to predict target interactions in silico prior to synthesis in order to assess, e.g., secondary pharmacology. This can be done by looking at known target binding profiles of similar compounds using chemical similarity searching. The purpose of this study was to construct and evaluate the performance of chemical fingerprints based on the molecular signature descriptor for performing target binding predictions. For the comparison we used the area under the receiver operating characteristics curve (AUC) complemented with net reclassification improvement (NRI). We created two open source signature fingerprints, a bit and a count version, and evaluated their performance compared to a set of established fingerprints with regards to predictions of binding targets using Tanimoto-based similarity searching on publicly available data sets extracted from ChEMBL. The results showed that the count version of the signature fingerprint performed on par with well-established fingerprints such as ECFP. The count version outperformed the bit version slightly; however, the count version is more complex and takes more computing time and memory to run so its usage should probably be evaluated on a case-by-case basis. The NRI based tests complemented the AUC based ones and showed signs of higher power.

Design and optimization of pyrazinecarboxamide-based inhibitors of diacylglycerol acyltransferase 1 (DGAT1) leading to a clinical candidate dimethylpyrazinecarboxamide phenylcyclohexylacetic acid (AZD7687).

A new series of pyrazinecarboxamide DGAT1 inhibitors was designed to address the need for a candidate drug with good potency, selectivity, and physical and DMPK properties combined with a low predicted dose in man. Rational design and optimization of this series led to the discovery of compound 30 (AZD7687), which met the project objectives for potency, selectivity, in particular over ACAT1, solubility, and preclinical PK profiles. This compound showed the anticipated excellent pharmacokinetic properties in human volunteers.

Mitigating the inhibition of human bile salt export pump by drugs: opportunities provided by physicochemical property modulation, in silico modeling, and structural modification.

The human bile salt export pump (BSEP) is a membrane protein expressed on the canalicular plasma membrane domain of hepatocytes, which mediates active transport of unconjugated and conjugated bile salts from liver cells into bile. BSEP activity therefore plays an important role in bile flow. In humans, genetically inherited defects in BSEP expression or activity cause cholestatic liver injury, and many drugs that cause cholestatic drug-induced liver injury (DILI) in humans have been shown to inhibit BSEP activity in vitro and in vivo. These findings suggest that inhibition of BSEP activity by drugs could be one of the mechanisms that initiate human DILI. To gain insight into the chemical features responsible for BSEP inhibition, we have used a recently described in vitro membrane vesicle BSEP inhibition assay to quantify transporter inhibition for a set of 624 compounds. The relationship between BSEP inhibition and molecular physicochemical properties was investigated, and our results show that lipophilicity and molecular size are significantly correlated with BSEP inhibition. This data set was further used to build predictive BSEP classification models through multiple quantitative structure-activity relationship modeling approaches. The highest level of predictive accuracy was provided by a support vector machine model (accuracy = 0.87, κ = 0.74). These analyses highlight the potential value that can be gained by combining computational methods with experimental efforts in early stages of drug discovery projects to minimize the propensity of drug candidates to inhibit BSEP.

Design of small molecule inhibitors of acetyl-CoA carboxylase 1 and 2 showing reduction of hepatic malonyl-CoA levels in vivo in obese Zucker rats.

Inhibition of acetyl-CoA carboxylases has the potential for modulating long chain fatty acid biosynthesis and mitochondrial fatty acid oxidation. Hybridization of weak inhibitors of ACC2 provided a novel, moderately potent but lipophilic series. Optimization led to compounds 33 and 37, which exhibit potent inhibition of human ACC2, 10-fold selectivity over inhibition of human ACC1, good physical and in vitro ADME properties and good bioavailability. X-ray crystallography has shown this series binding in the CT-domain of ACC2 and revealed two key hydrogen bonding interactions. Both 33 and 37 lower levels of hepatic malonyl-CoA in vivo in obese Zucker rats.

Synergism of virtual screening and medicinal chemistry: identification and optimization of allosteric antagonists of metabotropic glutamate receptor 1.

We report the identification of novel potent and selective metabotropic glutamate receptor 1 (mGluR1) antagonists by virtual screening and subsequent hit optimization. For ligand-based virtual screening, molecules were represented by a topological pharmacophore descriptor (CATS-2D) and clustered by a self-organizing map (SOM). The most promising compounds were tested in mGluR1 functional and binding assays. We identified a potent chemotype exhibiting selective antagonistic activity at mGluR1 (functional IC(50)=0.74+/-0.29 microM). Hit optimization yielded lead structure 16 with an affinity of K(i)=0.024+/-0.001 microM and greater than 1000-fold selectivity for mGluR1 versus mGluR5. Homology-based receptor modelling suggests a binding site compatible with previously reported mutation studies. Our study demonstrates the usefulness of ligand-based virtual screening for scaffold-hopping and rapid lead structure identification in early drug discovery projects.

Virtual screening for selective allosteric mGluR1 antagonists and structure-activity relationship investigations for coumarine derivatives.

A virtual screening study towards novel noncompetitive antagonists of the metabotropic glutamate receptor 1 (mGluR1) is described. Alignment-free topological pharmacophore descriptors (CATS) were used to encode the screening compounds. All virtual hits were characterized with respect to their allosteric antagonistic effect on mGluR1 in both functional and binding assays. Exceptionally high hit rates of up to 26 % were achieved, confirming the applicability of this virtual screening concept. Most of the compounds were found to be moderately active, however, one potent and subtype selective mGluR1 antagonist, 13 (IC(50): 0.362 microM, SEM +/-0.031; K(i): 0.753 microM, SEM +/-0.048), based on a coumarine scaffold was discovered. In a following activity optimization program a series of coumarine derivatives was synthesized. This led to the discovery of potent (60, IC(50): 0.058 microM, SEM +/-0.008; K(i): 0.293 microM, SEM +/-0.022) and subtype selective (rmGluR5 IC(50): 28.6 microM) mGluR1 antagonists. From our homology model of mGluR1 we derived a potential binding mode within the allosteric transmembrane region. Potential interacting patterns are proposed considering the difference of the binding pockets between rat and human receptors. The study demonstrates the applicability of ligand-based virtual screening for noncompetitive antagonists of a G-protein coupled receptor, resulting in novel, potent, and selective agents.