However, these methods are trained on a much broader dataset and their a gain in generality could lead to a loss in single reaction type accuracy. Furthermore, ML-based software that predict retrosynthetic pathways are also implicitly trained to predict the regioselectivity of EAS reactions. Several predictive tools have been developed to address this problem based on heuristics, quantum chemical calculations (QM), machine learning (ML) or a combination of QM and ML. Furthermore, EAS is also an important tool in late stage functionalization, which utilizes the C–H bonds of drug leads as points of diversification for generating new analogs, if the regioselectivity can be predicted. Consequently, organic chemists tend to install the halogens early in the synthesis, thereby effectively eliminating a large number of otherwise promising synthetic routes. However, it is often not a priori obvious at which position(s) halogenation will occur for compounds in the late stages of the synthesis that contain multiple (hetero)aromatic rings or in compounds that contain both heteroarene and benzene rings. Halogenated derivatives of heteroaromatics and benzene derivatives are often applied as substrates in carbon-carbon and carbon-heteroatom cross-coupling reactions and are typically prepared by electrophilic aromatic substitution (EAS). The code is freely available under the MIT open source license and will be made available as a webservice () in the near future. The accuracy of the more general IBM RXN approach is somewhat lower: 76.3–85.0%, depending on the data set. RegioSQM20 and WLN offers roughly the same success rates for the entire data sets (without considering tautomers), while WLN is many orders of magnitude faster. (React Chem Eng 5:896, 2020) specifically for regioselectivity predictions of EAS reactions (WLN) and a more generally applicable reactivity predictor (IBM RXN) developed by Schwaller et al. RegioSQM20 is compared to two machine learning based models: one developed by Struble et al. The inclusion of tautomers increases the success rate from 90.7 to 92.7%. Finally, RegioSQM20 offers a qualitative prediction of the reactivity of each tautomer (low, medium, or high) based on the reaction center with the highest proton affinity. Any low energy tautomeric forms of the input molecule are identified and regioselectivity predictions are made for each form. The following improvements have been made: The open source semiempirical tight binding program xtb is used instead of the closed source MOPAC program. We present RegioSQM20, a new version of RegioSQM (Chem Sci 9:660, 2018), which predicts the regioselectivities of electrophilic aromatic substitution (EAS) reactions from the calculation of proton affinities.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |