Silver(I)-Catalyzed Synthesis of Cuneanes from Cubanes and their Investigation as Isosteres.

Bridged or caged polycyclic hydrocarbons have rigid structures that project substituents into precise regions of 3D space, making them attractive as linking groups in materials science and as building blocks for medicinal chemistry. The efficient synthesis of new or underexplored classes of such compounds is, therefore, an important objective. Herein, we describe the silver(I)-catalyzed rearrangement of 1,4-disubstituted cubanes to cuneanes, which are strained hydrocarbons that have not received much attention since they were first described in 1970. The synthesis of 2,6-disubstituted or 1,3-disubstituted cuneanes can be achieved with high regioselectivities, with the regioselectivity being dependent on the electronic character of the cubane substituents. A preliminary assessment of cuneanes as scaffolds for medicinal chemistry suggests cuneanes could serve as isosteric replacements of trans-1,4-disubstituted cyclohexanes and 1,3-disubstituted benzenes. An analogue of the anticancer drug sonidegib was synthesized, in which the 1,2,3-trisubstituted benzene was replaced with a 1,3-disubstituted cuneane.

Transformer Performance for Chemical Reactions: Analysis of Different Predictive and Evaluation Scenarios.

The prediction of chemical reaction pathways has been accelerated by the development of novel machine learning architectures based on the deep learning paradigm. In this context, deep neural networks initially designed for language translation have been used to accurately predict a wide range of chemical reactions. Among models suited for the task of language translation, the recently introduced molecular transformer reached impressive performance in terms of forward-synthesis and retrosynthesis predictions. In this study, we first present an analysis of the performance of transformer models for product, reactant, and reagent prediction tasks under different scenarios of data availability and data augmentation. We find that the impact of data augmentation depends on the prediction task and on the metric used to evaluate the model performance. Second, we probe the contribution of different combinations of input formats, tokenization schemes, and embedding strategies to model performance. We find that less stable input settings generally lead to better performance. Lastly, we validate the superiority of round-trip accuracy over simpler evaluation metrics, such as top-k accuracy, using a committee of human experts and show a strong agreement for predictions that pass the round-trip test. This demonstrates the usefulness of more elaborate metrics in complex predictive scenarios and highlights the limitations of direct comparisons to a predefined database, which may include a limited number of chemical reaction pathways.