Universal Descriptors of 'Quasi Transition States' for Small-Data-Driven Asymmetric Catalysis Prediction in Machine Learning Model

This is the authors' abstract. We don't add key points for this paper.

In contemporary enantioselectivity prediction models, the demand for numerous descriptors and extensive datasets poses a substantial challenge. Descriptor selection, fraught with uncertainty, compounds the issue while amassing requisite data remains a daunting task. The introduction of descriptors derived from quasi-transition-states (qTS) offers a promising avenue to alleviate this burden. However, the challenge of descriptor selection persists. Herein, a novel small-data-driven model based on universal descriptors (UD-qTS) is proposed. Key differentiating properties between diastereomeric qTSs, encompassing energies, frontier orbital energies, Cartesian forces and charges of core atoms, are proposed as UD. The model's efficacy is validated through its application to the asymmetric aldol reaction, utilizing 3 experimental variables and merely 9 UDs, and fewer than 150 training samples. Moreover, a novel method is presented using Cartesian forces to rectify discrepancies between qTS and true TS. This UD-qTS strategy circumvents tedious large-scale descriptor exploration and screening, offering an efficient choice for small-data-driven enantioselectivity prediction.