Many natural substances and drugs are radical scavengers that prevent the oxidative damage to fundamental cell components. This process may occur via different mechanisms, among which, one of the most important, is hydrogen atom transfer. The feasibility of this process can be assessed in silico using quantum mechanics to compute ΔGHAT ○. This approach is accurate, but time consuming. The use of machine learning (ML) allows us to reduce tremendously the computational cost of the assessment of the scavenging properties of a potential antioxidant, almost without affecting the quality of the results. However, in many ML implementations, the description of the relevant features of a molecule in a machine-friendly language is still the most challenging aspect. In this work, we present a newly developed machine-readable molecular representation aimed at the application of automatized ML algorithms. In particular, we show an application on the calculation of ΔGHAT ○.