With the ongoing rapid growth of publicly available ligand–protein bioactivity data, there is a trove of valuable data that can be used to train a plethora of machine-learning algorithms. However, not all data is equal in terms of size and quality and a significant portion of researchers’ time is needed to adapt the data to their needs. On top of that, finding the right data for a research question can often be a challenge on its own. To meet these challenges, we have constructed the Papyrus dataset. Papyrus is comprised of around 60 million data points. This dataset contains multiple large publicly available datasets such as ChEMBL and ExCAPE-DB combined with several smaller datasets containing high-quality data. The aggregated data has been standardised and normalised in a manner that is suitable for machine learning. We show how data can be filtered in a variety of ways and also perform some examples of quantitative structure–activity relationship analyses and proteochemometric modelling. Our ambition is that this pruned data collection constitutes a benchmark set that can be used for constructing predictive models, while also providing an accessible data source for research. Graphical Abstract

Drug discovery programs of covalent irreversible, mechanism-based enzyme inhibitors often focus on optimization of potency as determined by IC50-values in biochemical assays. These assays do not allow the characterization of the binding activity (Ki) and reactivity (kinact) as individual kinetic parameters of the covalent inhibitors. Here, we report the development of a kinetic substrate assay to study the influence of the acidity (pKa) of heterocyclic leaving group of triazole urea derivatives as diacylglycerol lipase (DAGL)-α inhibitors. Surprisingly, we found that the reactivity of the inhibitors did not correlate with the pKa of the leaving group, whereas the position of the nitrogen atoms in the heterocyclic core determined to a large extent the binding activity of the inhibitor. This finding was confirmed and clarified by molecular dynamics simulations on the covalently bound Michaelis–Menten complex. A deeper understanding of the binding properties of covalent serine hydrolase inhibitors is expected to aid in the discovery and development of more selective covalent inhibitors.

The version presented here may differ from the published version or from the version of the record. Please see the repository URL above for details on accessing the published version and note that access may require a subscription.