Synergy Between Expert and Machine-Learning Approaches Allows for Improved Retrosynthetic Planning

When computers plan multistep syntheses, they can rely either on expert knowledge or information machine-extracted from large reaction repositories. Both approaches suffer from imperfect functions evaluating reaction choices: expert functions are heuristics based on chemical intuition, whereas machine learning (ML) relies on neural networks (NNs) that can make meaningful predictions only about popular reaction types. This paper shows that expert and ML approaches can be synergistic—specifically, when NNs are trained on literature data matched onto high-quality, expert-coded reaction rules, they achieve higher synthetic accuracy than either of the methods alone and, importantly, can also handle rare/specialized reaction types.     

Hydrolytic Transformation of Microporous Metal–Organic Frameworks to Hierarchical Micro‐ and Mesoporous MOFs

A new approach to the synthesis of hierarchical micro‐ and mesoporous MOFs from microporous MOFs involves a simple hydrolytic post‐synthetic procedure. As a proof of concept, a new microporous MOF, POST‐66(Y), was synthesized and its transformation into a hierarchical micro‐ and mesoporous MOF by water treatment was studied. This method produced mesopores in the range of 3 to 20 nm in the MOF while maintaining the original microporous structure, at least in part. The degree of micro‐ and mesoporosity can be controlled by adjusting the time and temperature of hydrolysis. The resulting hierarchical porous MOF, POST‐66(Y)‐wt, can be utilized to encapsulate nanometer‐sized guests such as proteins, and the enhanced stability and recyclability of an encapsulated enzyme is demonstrated.     

High Accuracy Protein Structures from Minimal Sparse Paramagnetic Solid‐State NMR Restraints

There is a pressing need for new computational tools to integrate data from diverse experimental approaches in structural biology. We present a strategy that combines sparse paramagnetic solid‐state NMR restraints with physics‐based atomistic simulations. Our approach explicitly accounts for uncertainty in the interpretation of experimental data through the use of a semi‐quantitative mapping between the data and the restraint energy that is calibrated by extensive simulations. We apply our approach to solid‐state NMR data for the model protein GB1 labeled with Cu²⁺‐EDTA at six different sites. We are able to determine the structure to 0.9 Å accuracy within a single day of computation on a GPU cluster. We further show that in some cases, the data from only a single paramagnetic tag are sufficient for accurate folding.