Incorporating Synthetic Accessibility in Drug Design: Predicting Reaction Yields of Suzuki Cross-Couplings by Leveraging AbbVie's 15-Year Parallel Library Data Set.

Despite the increased use of computational tools to supplement medicinal chemists' expertise and intuition in drug design, predicting synthetic yields in medicinal chemistry endeavors remains an unsolved challenge. Existing design workflows could profoundly benefit from reaction yield prediction, as precious material waste could be reduced, and a greater number of relevant compounds could be delivered to advance the design, make, test, analyze (DMTA) cycle. In this work, we detail the evaluation of AbbVie's medicinal chemistry library data set to build machine learning models for the prediction of Suzuki coupling reaction yields. The combination of density functional theory (DFT)-derived features and Morgan fingerprints was identified to perform better than one-hot encoded baseline modeling, furnishing encouraging results. Overall, we observe modest generalization to unseen reactant structures within the 15-year retrospective library data set. Additionally, we compare predictions made by the model to those made by expert medicinal chemists, finding that the model can often predict both reaction success and reaction yields with greater accuracy. Finally, we demonstrate the application of this approach to suggest structurally and electronically similar building blocks to replace those predicted or observed to be unsuccessful prior to or after synthesis, respectively. The yield prediction model was used to select similar monomers predicted to have higher yields, resulting in greater synthesis efficiency of relevant drug-like molecules.

Dataset Design for Building Models of Chemical Reactivity.

Models can codify our understanding of chemical reactivity and serve a useful purpose in the development of new synthetic processes via, for example, evaluating hypothetical reaction conditions or in silico substrate tolerance. Perhaps the most determining factor is the composition of the training data and whether it is sufficient to train a model that can make accurate predictions over the full domain of interest. Here, we discuss the design of reaction datasets in ways that are conducive to data-driven modeling, emphasizing the idea that training set diversity and model generalizability rely on the choice of molecular or reaction representation. We additionally discuss the experimental constraints associated with generating common types of chemistry datasets and how these considerations should influence dataset design and model building.

Orientation-independent room temperature optical 13C hyperpolarization in powdered diamond.

Dynamic nuclear polarization via contact with electronic spins has emerged as an attractive route to enhance the sensitivity of nuclear magnetic resonance beyond the traditional limits imposed by magnetic field strength and temperature. Among the various alternative implementations, the use of nitrogen vacancy (NV) centers in diamond-a paramagnetic point defect whose spin can be optically polarized at room temperature-has attracted widespread attention, but applications have been hampered by the need to align the NV axis with the external magnetic field. We overcome this hurdle through the combined use of continuous optical illumination and a microwave sweep over a broad frequency range. As a proof of principle, we demonstrate our approach using powdered diamond with which we attain bulk 13C spin polarization in excess of 0.25% under ambient conditions. Remarkably, our technique acts efficiently on diamond crystals of all orientations and polarizes nuclear spins with a sign that depends exclusively on the direction of the microwave sweep. Our work paves the way toward the use of hyperpolarized diamond particles as imaging contrast agents for biosensing and, ultimately, for the hyperpolarization of nuclear spins in arbitrary liquids brought in contact with their surface.