Fast and accurate prediction of the regioselectivity of electrophilic aromatic substitution reactions

Abstract

A fast and user-friendly computational for predicting the regioselectivity of electrophilic aromatic substitution reactions of heteroaromatic systems is presented.

Multitask prediction of site selectivity in aromatic C–H functionalization reactions

“…Previous methodology, namely RegioSQM, 20 achieves high site prediction accuracy based on enumeration and calculation of protonated carbocation intermediates in the EAS pathway. ¶ comparison of the WLN methodology to RegioSQM was limited to bromination reactions for a fair comparison to the intended application of RegioSQM.…”

“…The SQM model predicts selectivity based on estimated energies of carbocations generated from protonation at each site, meant to represent potential intermediates. 20 Any carbocation that is within thresholds of 1 or 3 kcal mol −1 of the lowest energy structure is marked as a possible site for reactivity. The RegioSQM method reaches 90% accuracy within 1 kcal mol −1 and 96% accuracy within 3 kcal mol −1 on their test set of 525 reactions, although this definition of accuracy does not penalize the prediction of multiple reactive sites.…”

Maschinelles Lernen für die organische Synthese: Ersetzen Roboter Chemiker?

“…Die Fähigkeit, Ergebnisse komplizierter chemischer Transformationen vorherzusagen, ist ein seit langem verfolgtes Ziel in der Chemie. Die Entwicklung quantenchemischer Ansätze hat schon einige Möglichkeiten in diese Richtung eröffnet, und in vielen Fällen können die Ergebnisse der Experimente in silico effizient modelliert werden . Die Einführung von Algorithmen der künstlichen Intelligenz (KI), um die Vorhersagen zu automatisieren, zu verbessern und zu verallgemeinern, gewinnt eine zunehmend an Bedeutung in diesem Forschungsgebiet, und mehrere aktuelle Studien wurden in diesem Bereich veröffentlicht.…”

Machine Learning for Organic Synthesis: Are Robots Replacing Chemists?

“…The development of quantum‐chemical approaches has already opened some opportunities in this direction, and in many cases, the outcomes of experiments can be efficiently modeled in silico 1, 2, 3, 4, 5, 6. The advent of artificial intelligence (AI) algorithms to automatize, improve, and generalize predictions is gaining importance in this field, and several recent studies have been published in this area.…”

“…The ability to predict the outcome of complex chemical transformations has been al ong-standing challenge for chemists.The development of quantum-chemical approaches has already opened some opportunities in this direction, and in many cases,the outcomes of experiments can be efficiently modeled in silico. [1][2][3][4][5][6] Theadvent of artificial intelligence (AI) algorithms to automatize,improve,and generalize predictions is gaining importance in this field, and several recent studies have been published in this area. Fore xample,i n2 016, Aspuru-Guzik and co-workers reported their attempt to apply neural networks to basic reactions of alkenes and alkyl halides,a nd they were able to identify the correct reaction type for the majority of aset of textbook problems.…”