Progressive cerebral amyloid beta-protein (A beta) deposition is believed to play a central role in the pathogenesis of Alzheimer's disease (AD). Elevated levels of A beta(42) peptide formation have been linked to early-onset familial AD-causing gene mutations in the amyloid beta-protein precursor (A beta PP) and the presenilins. Sequential cleavage of A beta PP by the beta- and gamma-secretases generates the N- and C-termini of the A beta peptide, making both the beta- and gamma-secretase enzymes potential therapeutic targets for AD. The identity of the A beta PP gamma-secretase and the mechanism by which the C-termini of A beta are formed remain uncertain, although it has been suggested that the presenilins themselves are novel intramembrane-cleaving gamma-secretases of the aspartyl protease class [Wolfe, M. S., Xia, W., Ostaszewski, B. L., Diehl, T. S., Kimberly, W. T., and Selkoe, D. J. (1999) Nature 398, 513-517]. In this study we report the identification of L-685,458 as a structurally novel inhibitor of A beta PP gamma-secretase activity, with a similar potency for inhibition of A beta(42) and A beta(40) peptides. This compound contains an hydroxyethylene dipeptide isostere which suggests that it could function as a transition state analogue mimic of an aspartyl protease. The preferred stereochemistry of the hydroxyethylene dipeptide isostere was found to be the opposite to that required for inhibition of the HIV-1 aspartyl protease, a factor which may contribute to the observed specificity of this compound. Specific and potent inhibitors of A beta PP gamma-secretase activity such as L-685,458 will enable important advances toward the identification and elucidation of the mechanism of action of this enigmatic protease.

We describe methods for predicting cytochrome P450 (CYP) metabolism incorporating both pathway-specific reactivity and isoform-specific accessibility considerations. Semiempirical quantum mechanical (QM) simulations, parametrized using experimental data and ab initio calculations, estimate the reactivity of each potential site of metabolism (SOM) in the context of the whole molecule. Ligand-based models, trained using high-quality regioselectivity data, correct for orientation and steric effects of the different CYP isoform binding pockets. The resulting models identify a SOM in the top 2 predictions for between 82% and 91% of compounds in independent test sets across seven CYP isoforms. In addition to predicting the relative proportion of metabolite formation at each site, these methods estimate the activation energy at each site, from which additional information can be derived regarding their lability in absolute terms. We illustrate how this can guide the design of compounds to overcome issues with rapid CYP metabolism.

We describe a novel deep learning neural network method and its application to impute assay pIC 50 values. Unlike conventional machine learning approaches, this method is trained on sparse bioactivity data as input, typical of that found in public and commercial databases, enabling it to learn directly from correlations between activities measured in dierent assays.In two case studies on public domain data sets we show that the neural network method outperforms traditional quantitative structureactivity relationship (QSAR) models and other leading approaches. Furthermore, by focussing on only the most condent predictions the accuracy is increased to R 2 > 0.9 using our method, as compared to R 2 = 0.44 when reporting all predictions.

In the development of novel pharmaceuticals, the knowledge of how many, and which, Cytochrome P450 isoforms are involved in the phase I metabolism of a compound is important. Potential problems can arise if a compound is metabolised predominantly by a single isoform in terms of drug-drug interactions or genetic polymorphisms that would lead to variations in exposure in the general population. Combined with models of regioselectivities of metabolism by each isoform, such a model would also aid in the prediction of the metabolites likely to be formed by P450-mediated metabolism. We describe the generation of a multi-class random forest model to predict which, out of a list of the seven leading Cytochrome P450 isoforms, would be the major metabolising isoforms for a novel compound. The model has a 76% success rate with a top-1 criterion and an 88% success rate for a top-2 criterion and shows significant enrichment over randomised models.

ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 200 leading journals. To access a ChemInform Abstract, please click on HTML or PDF.