Communications Chemistry最新文献

Reaction optimization plays an essential role in chemical research and industrial production. To explore a large reaction system, a practical issue is how to reduce the heavy experimental load for finding the high-yield conditions. In this paper, we present an efficient machine learning tool called "RS-Coreset", where the key idea is to take advantage of deep representation learning techniques to guide an interactive procedure for representing the full reaction space. Our proposed tool only uses small-scale data, say 2.5% to 5% of the instances, to predict the yields of the reaction space. We validate the performance on three public datasets and achieve state-of-the-art results. Moreover, we apply this tool to assist the realistic exploration of the Lewis base-boryl radicals enabled dechlorinative coupling reactions in our lab. The tool can help us to effectively predict the yields and even discover several feasible reaction combinations that were overlooked in previous articles.

Designing molecules with desirable properties is a critical endeavor in drug discovery. Because of recent advances in deep learning, molecular generative models have been developed. However, the existing compound exploration models often disregard the important issue of ensuring the feasibility of organic synthesis. To address this issue, we propose TRACER, which is a framework that integrates the optimization of molecular property optimization with synthetic pathway generation. The model can predict the product derived from a given reactant via a conditional transformer under the constraints of a reaction type. The molecular optimization results of an activity prediction model targeting DRD2, AKT1, and CXCR4 revealed that TRACER effectively generated compounds with high scores. The transformer model, which recognizes the entire structures, captures the complexity of the organic synthesis and enables its navigation in a vast chemical space while considering real-world reactivity constraints.

Machine learning offers great promise for fast and accurate binding affinity predictions. However, current models lack robust evaluation and fail on tasks encountered in (hit-to-) lead optimisation, such as ranking the binding affinity of a congeneric series of ligands, thereby limiting their application in drug discovery. Here, we address these issues by first introducing a novel attention-based graph neural network model called AEV-PLIG (atomic environment vector-protein ligand interaction graph). Second, we introduce a new and more realistic out-of-distribution test set called the OOD Test. We benchmark our model on this set, CASF-2016, and a test set used for free energy perturbation (FEP) calculations, that not only highlights the competitive performance of AEV-PLIG, but provides a realistic assessment of machine learning models with rigorous physics-based approaches. Moreover, we demonstrate how leveraging augmented data (generated using template-based modelling or molecular docking) can significantly improve binding affinity prediction correlation and ranking on the FEP benchmark (weighted mean PCC and Kendall's τ increases from 0.41 and 0.26 to 0.59 and 0.42). These strategies together are closing the performance gap with FEP calculations (FEP+ achieves weighted mean PCC and Kendall's τ of 0.68 and 0.49 on the FEP benchmark) while being  ~400,000 times faster.

Autoclave reactors are widely used across chemical and biological sciences, including for the synthesis of upconversion nanoparticles (UCNPs) and other nanomaterials. Yet, the details of how autoclave reactors are used in such synthesis are rarely reported in the literature, leaving several key synthesis variables widely unreported and thereby hampering experimental reproducibility. In this perspective, we discuss the safety considerations of autoclave reactors and note that autoclaves should only be used if they are (a) purchased from reputable suppliers/manufacturers and (b) have been certified compliant with relevant safety standards. Ultimately, using unsuitable autoclave equipment can pose a severe physical hazard and may breach legal safety requirements. In addition, we highlight several parameters in autoclave synthesis that should be reported as standard to maximise the reproducibility of autoclave synthesis experiments across materials and chemistry research. We encourage users of autoclave synthesis vessels to: (1) adopt high-safety autoclaves and (2) report the many experimental variables involved to enhance experimental reproducibility.

Gasdermin D and gasdermin A3 belong to the same family of pore-forming proteins and executors of pyroptosis, a form of programmed cell death. To unveil the process of their pore formation, we examine the energy landscapes upon insertion of the gasdermin D and A3 monomers into a lipid bilayer by extensive atomistic molecular dynamics simulations. We reveal a lower free energy barrier of membrane insertion for gasdermin D than for gasdermin A3 and a preference of gasdermin D for the membrane-inserted and of gasdermin A3 for the membrane-adsorbed state, suggesting that gasdermin D first inserts and then oligomerizes while gasdermin A3 oligomerizes and then inserts. Gasdermin D stabilizes itself in the membrane by forming more salt bridges and pulling phosphatidylethanolamine lipids and more water into the membrane. Gasdermin-lipid interactions support the pore formation. Our findings suggest that both the gasdermin species and the lipid composition modulate gasdermin pore formation.

Kinases are attractive drug targets, but the design of highly selective kinase inhibitors remains challenging. Selectivity may be evaluated against a panel of kinases, or - preferred - in a complex proteome. Probes that allow photoaffinity-labeling of their targets can facilitate this process. Here, we report photoaffinity probes based on the imidazopyrazine scaffold, which is found in several kinase inhibitors and drugs or drug candidates. By chemical proteomics experiments, we find a range of off-targets, which vary between the different probes. In silico analysis suggests that differences between probes may be related to the size, spatial arrangement and rigidity of the imidazopyrazine and its substituent at the 1-position.