Mapping Boryl Radical Properties and Reactivity Using Ma-chine Learning: the B-rad and React-B-rad maps

Boryl radicals have become indispensable in modern organic synthesis, yet, translating their complex steric and electronic properties into actionable reactivity insights remains challenging. Herein, we present an updated, publicly accessible database of 100 neutral 7e-4c boryl radicals, each parametrized by a set of electronic and steric features derived from DFT calculations. Unsupervised machine learning (k-means clustering) and dimensionality reduction (PCA / t-SNE) condense this high-dimensional descriptor space into the “B-rad map,” visually capturing trends in steric and electronics among the resulting five clusters. Global electrophilicity (ω) and nucleophilicity (N) indices are overlaid to create a polarity‑annotated guide, while DFT‑computed activation free energies for six benchmark reactions (HAT, radical addition, XAT for two different substrates) yield React‑B‑rad maps that directly link intrinsic properties to specific reaction performance. These maps might be used as a practical guideline to decide on experimental setups for boryl radical mediated transformations. To demonstrate predictive power, supervised machine learning models (random forest) trained on the descriptors are able to forecast activation barriers with reasonable accuracy (3-6 kcal·mol-1), despite the diversity of the reaction space. Overall, this integrated, machine-learning-driven platform can serve as both a practical guide for experimental decision-making and a foundation for data-driven discovery, paving the way towards rational design and virtual screening of boryl-radical reagents for diverse synthetic applications.