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.

No abstract

The availability of a chemical probe to study the role of a specific domain of a protein in a concentration- and time-dependent manner is of high value. Herein, we report the identification of a highly potent and selective ERK5 inhibitor BAY-885 by high-throughput screening and subsequent structure-based optimization. ERK5 is a key integrator of cellular signal transduction, and it has been shown to play a role in various cellular processes such as proliferation, differentiation, apoptosis, and cell survival. We could demonstrate that inhibition of ERK5 kinase and transcriptional activity with a small molecule did not translate into antiproliferative activity in different relevant cell models, which is in contrast to the results obtained by RNAi technology.

Molecular orbital calculations (MP4(fc)6-3 1 1 G(3df,3pd)//MP2(full)/6-3 1 lG(3df,3pd) + ZPE(MP2/full)/6-3 1 IG(3df,3pd)) are used to describe the geometries, energies, and vibrational frequencies of the four species S O H + (l'), HSiO+ (2+), SiOH' (I*), and HSiO' (Z'), respectively, and the transition states for the 1,2-hydrogen migrations. It should be recalled that the ionic species formed in reactions 1 and 2 was originally assumed by Turner and Dalgarno (ref 2a) as HSiO+. (4) Fahey, D. W.; Fehsenfeld, F. C.; Ferguson, E. E.; Viehland, L. A. J. Chem. Phys. 1981, 75, 669. (28) (a) Hehre, W. J.; Radom, L.; Schleyer, P. v. R.; Pople, J. A. ob initio Molecular Orbital Theory; Wiley; New York, 1986. (b) For Gaussian 86, see: Frisch, M. J.; Binkley, J. S.; Schlegel, H. B.; Raghavachari, K.; Melius, C. F.; Martin, R. L.; Stewart, J. J. P.; Bobrowicz, F. W.; Rohlfing, C. W.; Kahn, L. R.; DeFrees, D. J.; Seeger, R.; Whitwide, R. A.; Fox, D. J.; nuder, E. M.; Pople, J. A., Carnegie-Mellon Quantum Chemistry Publishing Unit: Pittsburgh, PA, 1984.

No abstract