The synthesis of the desired chemical compound is the main task of synthetic organic chemistry. The predictions of reaction conditions and some important quantitative characteristics of chemical reactions as yield and reaction rate can substantially help in the development of optimal synthetic routes and assessment of synthesis cost. Theoretical assessment of these parameters can be performed with the help of modern machine-learning approaches, which use available experimental data to develop predictive models called quantitative or qualitative structure–reactivity relationship (QSRR) modelling. In the article, we review the state-of-the-art in the QSRR area and give our opinion on emerging trends in this field. 相似文献
This paper proposes a new and systematic approach for optimum design of thermosetting resin systems based on molecular‐dynamics simulations. Specifically, the results of simulations for chemical reaction (cross‐linking) and mechanical properties of epoxy resin are clustered with a self‐organizing map (SOM) that enables to comprehensibly visualize the characteristics of complex structured polymers. Moreover, the scatter‐plot matrix (SPM) is introduced to analyze the specific data. Thus, SOM is used to find common features in a molecular structure, and SPM helps to clarify molecular‐scale mechanism in the clusterization. Through the analysis, the authors find that base resins with multireactive functional groups contribute to superior mechanical properties, and these properties stem from the hydrogen‐bond network distributed throughout the system. The approach, which is thought to be one of chemical informatics, has broad ranges of applications that are not limited to epoxy resin but can be applied to any kind of thermosetting resins.
