Multiple recent studies have focused on unraveling the content of the medicinal chemist's toolbox. Here, we present an investigation of chemical reactions and molecules retrieved from U.S. patents over the past 40 years (1976-2015). We used a sophisticated text-mining pipeline to extract 1.15 million unique whole reaction schemes, including reaction roles and yields, from pharmaceutical patents. The reactions were assigned to well-known reaction types such as Wittig olefination or Buchwald-Hartwig amination using an expert system. Analyzing the evolution of reaction types over time, we observe the previously reported bias toward reaction classes like amide bond formations or Suzuki couplings. Our study also shows a steady increase in the number of different reaction types used in pharmaceutical patents but a trend toward lower median yield for some of the reaction classes. Finally, we found that today's typical product molecule is larger, more hydrophobic, and more rigid than 40 years ago.

Fingerprint methods applied to molecules have proven to be useful for similarity determination and as inputs to machine-learning models. Here, we present the development of a new fingerprint for chemical reactions and validate its usefulness in building machine-learning models and in similarity assessment. Our final fingerprint is constructed as the difference of the atom-pair fingerprints of products and reactants and includes agents via calculated physicochemical properties. We validated the fingerprints on a large data set of reactions text-mined from granted United States patents from the last 40 years that have been classified using a substructure-based expert system. We applied machine learning to build a 50-class predictive model for reaction-type classification that correctly predicts 97% of the reactions in an external test set. Impressive accuracies were also observed when applying the classifier to reactions from an in-house electronic laboratory notebook. The performance of the novel fingerprint for assessing reaction similarity was evaluated by a cluster analysis that recovered 48 out of 50 of the reaction classes with a median F-score of 0.63 for the clusters. The data sets used for training and primary validation as well as all python scripts required to reproduce the analysis are provided in the Supporting Information.

The estimation of free energy of binding is a key problem in structure-based design. We developed the scoring function HYDE based on a consistent description of HYdrogen bond and DEhydration energies in protein-ligand complexes. HYDE is applicable to all types of protein targets since it is not calibrated on experimental binding affinity data or protein-ligand complexes. The comprehensible atom-based score of HYDE is visualized by applying a very intuitive coloring scheme, thereby facilitating the analysis of protein-ligand complexes in the lead optimization process. In this paper, we have revised several aspects of the former version of HYDE which was described in detail previously. The revised HYDE version was already validated in large-scale redocking and screening experiments which were performed in the course of the Docking and Scoring Symposium at 241st ACS National Meeting. In this study, we additionally evaluate the ability of the revised HYDE version to predict binding affinities. On the PDBbind 2007 coreset, HYDE achieves a correlation coefficient of 0.62 between the experimental binding constants and the predicted binding energy, performing second best on this dataset compared to 17 other well-established scoring functions. Further, we show that the performance of HYDE in large-scale redocking and virtual screening experiments on the Astex diverse set and the DUD dataset respectively, is comparable to the best methods in this field.

When analyzing chemical reactions it is essential to know which molecules are actively involved in the reaction and which educts will form the product molecules. Assigning reaction roles, like reactant, reagent, or product, to the molecules of a chemical reaction might be a trivial problem for hand-curated reaction schemes but it is more difficult to automate, an essential step when handling large amounts of reaction data. Here, we describe a new fingerprint-based and data-driven approach to assign reaction roles which is also applicable to rather unbalanced and noisy reaction schemes. Given a set of molecules involved and knowing the product(s) of a reaction we assign the most probable reactants and sort out the remaining reagents. Our approach was validated using two different data sets: one hand-curated data set comprising about 680 diverse reactions extracted from patents which span more than 200 different reaction types and include up to 18 different reactants. A second set consists of 50 000 randomly picked reactions from US patents. The results of the second data set were compared to results obtained using two different atom-to-atom mapping algorithms. For both data sets our method assigns the reaction roles correctly for the vast majority of the reactions, achieving an accuracy of 88% and 97% respectively. The median time needed, about 8 ms, indicates that the algorithm is fast enough to be applied to large collections. The new method is available as part of the RDKit toolkit and the data sets and Jupyter notebooks used for evaluation of the new method are available in the Supporting Information of this publication.

The HYDE scoring function consistently describes hydrogen bonding, the hydrophobic effect and desolvation. It relies on HYdration and DEsolvation terms which are calibrated using octanol/water partition coefficients of small molecules. We do not use affinity data for calibration, therefore HYDE is generally applicable to all protein targets. HYDE reflects the Gibbs free energy of binding while only considering the essential interactions of protein-ligand complexes. The greatest benefit of HYDE is that it yields a very intuitive atom-based score, which can be mapped onto the ligand and protein atoms. This allows the direct visualization of the score and consequently facilitates analysis of protein-ligand complexes during the lead optimization process. In this study, we validated our new scoring function by applying it in large-scale docking experiments. We could successfully predict the correct binding mode in 93% of complexes in redocking calculations on the Astex diverse set, while our performance in virtual screening experiments using the DUD dataset showed significant enrichment values with a mean AUC of 0.77 across all protein targets with little or no structural defects. As part of these studies, we also carried out a very detailed analysis of the data that revealed interesting pitfalls, which we highlight here and which should be addressed in future benchmark datasets.