ABSTRACT: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, ‫؍‬ 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.

The self-organizing map (SOM) principle was introduced by Kohonen in 1982, [1] and has been applied to a variety of tasks in chemistry and chemical biology ever since. [2,3] In this study, we used the SOM algorithm for mapping known ligands according to a topological pharmacophore descriptor (CATS) [4] and predicting potential cross-activities. Our aim was to see whether 1) the descriptor is able to discriminate antagonists of metabotropic glutamate receptors (mGluR) 1 and 5, and 2) the SOM could be used for predicting potential additional binding behaviors of the ligands.First, an mGluR reference collection containing 338 compounds was compiled including published and Merz in-house structures of noncompetitive group I mGluR antagonists. The collection comprises two subsets: allosteric mGlu1 receptor antagonists (213 compounds), and allosteric mGlu5 receptor antagonists (125 compounds).[5] These molecules cover a broad range of binding activities (K i values between 1 nm and % 10 mm) and represent different chemical classes. This mGluR reference library was complemented by the molecules from the COBRA database (v. 3.12; 5376 molecules) containing a broad set of known drugs, leads, and lead candidates affecting a large number of different drug targets. [6] Subsequently, the molecules were converted to a vector representation giving the scaled occurrence frequencies of topological potential pharmacophore point pairs (CATS2D method). [4,7] In this study, intramolecular distances from zero to nine bonds were considered, resulting in a 150-dimensional vector representation of each molecular compound.The complete COBRA database was subjected to clustering and mapping onto a two-dimensional grid by the SOM approach. The SOM provides a nonlinear two-dimensional projection of the 150-dimensional data space ("chemical space"), where local neighborhood is conserved. This means, that molecules that are located close to each other on the map are also close in the original high-dimensional space. For SOM training we applied a slightly modified version of the Kohonen algorithm as described previously. [6,8] As a result, all molecules from COBRA were distributed into 225 (15 15) clusters A C H T U N G T R E N N U N G ("neurons"or "receptive fields"). The distribution of these compounds is shown in Figure 1 a. It is evident that the SOM is devoid of large patches of empty clusters (< 3 %) and pronounced densities, which indicates successful mapping and also reflects the diversity of the COBRA entries. After SOM training we projected the mGluR data onto this map and analyzed the resulting distribution patterns. The two mGluR ligand classes form separate localized distributions, where the distribution of the mGluR5 antagonists (Figure 1 c) appears to be slightly more focused than the mGluR1 data (Figure 1 b). Notably, only 6 % of the two ligand classes were clustered together. The SOM was Figure 1. a) SOM projection of the complete COBRA data, b) the mGluR1 antagonists, and c) mGluR5 antagonists. The distribution of the compounds...