Search

The branched-chain amino acid transaminases (BCATs) are enzymes that catalyze the first reaction of catabolism of the essential branched-chain amino acids to branched-chain keto acids to form glutamate. They are known to play a key role in different cancer types. Here, we report a new structural class of BCAT1/2 inhibitors, (trifluoromethyl)pyrimidinediones, identified by a high-throughput screening campaign and subsequent optimization guided by a series of X-ray crystal structures. Our potent dual BCAT1/2 inhibitor BAY-069 displays high cellular activity and very good selectivity. Along with a negative control (BAY-771), BAY-069 was donated as a chemical probe to the Structural Genomics Consortium.

A short synthetic approach with broad scope to access five- to seven-membered cyclic sulfoximines in only two to three steps from readily available thiophenols is reported. Thus, simple building blocks were converted to complex molecular structures by a sequence of S-alkylation and one-pot sulfoximine formation, followed by intramolecular cyclization. Seventeen structurally diverse cyclic sulfoximines were prepared in high overall yields. In vitro evaluation of these underrepresented, three-dimensional, cyclic sulfoximines with respect to properties relevant to medicinal chemistry did not reveal any intrinsic flaw for application in drug discovery.

An unprecedented set of structurally diverse sulfonimidamides (47 compounds) has been prepared by various N‐functionalization reactions of tertiary =NH sulfonimidamide 2 aa. These N‐functionalization reactions of model compound 2 aa include arylation, alkylation, trifluoromethylation, cyanation, sulfonylation, alkoxycarbonylation (carbamate formation) and aminocarbonylation (urea formation). Small molecule X‐ray analyses of selected N‐functionalized products are reported. To gain further insight into the properties of sulfonimidamides relevant to medicinal chemistry, a variety of structurally diverse reaction products were tested in selected in vitro assays. The described N‐functionalization reactions provide a short and efficient approach to structurally diverse sulfonimidamides which have been the subject of recent, growing interest in the life sciences.

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Many drug failures are due to an unfavorable ADMET profile (Absorption, Distribution, Metabolism, Excretion & Toxicity). Lipophilicity is intimately connected with ADMET and in today’s drug discovery process, the octanol water partition coefficient log P and it’s pH dependant counterpart log D have to be taken into account early on in lead discovery. Commercial tools available for ’in silico’ prediction of ADMET or lipophilicity parameters usually have been trained on relatively small and mostly neutral molecules, therefore their accuracy on industrial in-house data leaves room for considerable improvement (see Bruneau et al. and references therein). Using modern kernel-based machine learning algorithms – so called Gaussian Processes (GP)– this study constructs different log P and log D7 models that exhibit excellent predictions which compare favorably to state-of-the-art tools on both benchmark and in-house data sets.

Unfavorable physicochemical properties often cause drug failures. It is therefore important to take lipophilicity and water solubility into account early on in lead discovery. This study presents log D7 models built using Gaussian Process regression, Support Vector Machines, decision trees and ridge regression algorithms based on 14556 drug discovery compounds of Bayer Schering Pharma. A blind test was conducted using 7013 new measurements from the last months. We also present independent evaluations using public data. Apart from accuracy, we discuss the quality of error bars that can be computed by Gaussian Process models, and ensemble and distance based techniques for the other modelling approaches.

Unfavorable lipophilicity and water solubility cause many drug failures; therefore these properties have to be taken into account early on in lead discovery. Commercial tools for predicting lipophilicity usually have been trained on small and neutral molecules, and are thus often unable to accurately predict in-house data. Using a modern Bayesian machine learning algorithm--a Gaussian process model--this study constructs a log D7 model based on 14,556 drug discovery compounds of Bayer Schering Pharma. Performance is compared with support vector machines, decision trees, ridge regression, and four commercial tools. In a blind test on 7013 new measurements from the last months (including compounds from new projects) 81% were predicted correctly within 1 log unit, compared to only 44% achieved by commercial software. Additional evaluations using public data are presented. We consider error bars for each method (model based error bars, ensemble based, and distance based approaches), and investigate how well they quantify the domain of applicability of each model.

Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.