The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions. In particular, in many cases, the most likely synthesis pathway cannot be applied due to additional constraints, which requires proposing alternative chemical reactions. With this in mind, we present Molecule Edit Graph Attention Network (MEGAN), an end-to-end encoder−decoder neural model. MEGAN is inspired by models that express a chemical reaction as a sequence of graph edits, akin to the arrow pushing formalism. We extend this model to retrosynthesis prediction (predicting substrates given the product of a chemical reaction) and scale it up to large data sets. We argue that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion and achieving state-of-the-art accuracy in standard benchmarks. Code and trained models are made available online at https://github. com/molecule-one/megan.
In the presence of iron(II) chloride (FeCl 2 ; 20 mol%) and potassium tert-butoxide (tBuOK; 4 equiv.) in dimethyl sulfoxide (DMSO), aryl and heteroaryl iodides undergo stereoselective Mizoroki-Heck C À C cross-coupling reactions with styrenes at 60 8C giving the corresponding (E)-alkenes. The best yields are obtained upon adding a ligand (80 mol%) such as proline or picolinic acid. Aryl bromides and pyridinyl bromides are also coupled with styrenes but in lower yields.
A novel, three-step method of trifluoromethylation of azines via oxidative nucleophilic substitution of hydrogen in the heteroaromatic ring by a CF3- carbanion is presented. The key reaction of this process is the addition of the CF3- carbanion, generated by treatment of Me3SiCF3 with KF(s) and Ph3SnF catalyst, to N-alkylazinium salts. The resulting dihydroazines containing a trifluoromethyl group are relatively stable compounds and can be isolated in a pure form. Deprotection of the N-p-methoxybenzyl substituent and aromatization of the heterocyclic ring upon treatment with CAN provides azines with a CF3 group in the ring position originally occupied by hydrogen. The whole process can be thus considered as a nucleophilic oxidative displacement of hydrogen by a CF3- carbanion.
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.