We present an extension of our Molecular Transformer model combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts for each retrosynthetic step. We introduce four metrics (coverage, class diversity, round-trip accuracy and Jensen-Shannon divergence) to evaluate the single-step retrosynthetic models, using the forward prediction and a reaction classification model always based on the transformer architecture. The hypergraph is constructed on the fly, and the nodes are filtered and further expanded based on a Bayesian-like probability. We critically assessed the end-to-end framework with several retrosynthesis examples from literature and academic exams. Overall, the frameworks have an excellent performance with few weaknesses related to the training data. The use of the introduced metrics opens up the possibility to optimize entire retrosynthetic frameworks by focusing on the performance of the singlestep model only.
Carbohydrates represent a promising option in transitioning from oil-based chemical resources to renewable ones, with the goal of developing chemistries for a sustainable future. Cellulose, hemicellulose, and largely available monosaccharides already provide useful chemical building blocks, so-called platform chemicals, such as levulinic acid and hydroxymethyl furfural, as well as solvents like cyrene or gamma-valerolactone. Therefore, there is great anticipation for novel applications involving materials and chemicals derived from sugars. In the field of ionic liquids (ILs), sugar-based ILs have been overlooked for a long time, mainly on account of their multistep demanding preparation. However, exploring new strategies for accessing sugar-based ILs, their study, and their exploitation, are attracting increasing interest. This is due to the growing concerns about the negative (eco)toxicity profile of most ILs in conjunction with their non-sustainable nature. In the present review, a literature survey concerning the development of sugar-based ILs since 2011 is presented. Their preparation strategies and thermal behavior analyses, sorted by sugar type, make up the first two sections with the intention to provide the reader with a useful guide. A final overview of the potential applications of sugar-based ILs and their future perspectives complement the present analysis.
We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts for each retrosynthetic step. We introduce new metrics (coverage, class diversity, round-trip accuracy and Jensen-Shannon divergence) to evaluate the single-step retrosynthetic models, using the forward prediction and a reaction classification model always based on the transformer architecture. The hypergraph is constructed on the fly, and the nodes are filtered and further expanded based on a Bayesian-like probability. We critically assessed the end-to-end framework with several retrosynthesis examples from literature and academic exams. Overall, the frameworks has a very good performance with few weaknesses due to the bias induced during the training process. The use of the newly introduced metrics opens up the possibility to optimize entire retrosynthetic frameworks through focusing on the performance of the single-step model only.
Organic compounds showing circularly polarized luminescence (CPL) are at the forefront of novel applications and technologies. Here we show the synthesis and chiroptical properties of pyrene and perylene derivatives of inexpensive chiral scaffolds: isomannide and isosorbide. Low‐intensity ECD spectra were obtained, suggesting the absence of chromophore interaction in the ground state, except in the case of isomannide bis‐perylenecarboxylate, whose ECD spectrum showed a positive exciton couplet. All isomannide derivatives, with the only exception of the one containing a pyrenecarboxylate and a perylenecarboxylate, exhibited excimer CPL spectra, whereas isosorbide derivatives did not show any CPL. Isomannide derivatives bearing two pyrenecarboxylate or two pyrenylacetate groups showed positive CPL emission with dissymmetry factors up to 10−2, which depends on the conformational freedom of the appended units. The CPL sign, Stokes shift and order of magnitude of dissymmetry factor were reproduced by excited‐state calculations on a representative compound. Interestingly, the mixed derivative containing pyrenic units with different spacing from the isomannide scaffold showed an oppositely signed excimer band with respect to the homo‐substituted derivatives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.