Well-defined palladium precatalysts have become increasingly important in cross-coupling chemistry. Despite the wide choice of complexes available today, palladium(0) compounds bearing Buchwald’s biaryl phosphines are still under-represented. We present here an efficient and facile synthesis of biaryl phosphine palladium(0) complexes supported by a divinyltetramethyldisiloxane (dvtms) ligand. Starting from commercially available [Pd­(allyl)­Cl]2, a variety of [Pd­(L)­(dvtms)] complexes can be accessed in high yields under mild reaction conditions. Their catalytic activity was tested in Buchwald–Hartwig couplings and found to be very good for both (hetero)­aryl bromides and chlorides.

A machine learning-based tool that provides conditions and predicted yields for Buchwald-Hartwig couplings from a ChemDraw™ structure input is described. The tool is built on an in-house generated experimental dataset that explores a diverse network of reactant pairings. To minimize the number of experiments necessary to produce models and maximize data value, a workflow based on unsupervised machine leaning tools was created. The workflow enables the construction of models which can successfully generalize—making predictions for reactants which are not represented in the dataset.

A machine learning-based tool that provides conditions and predicted yields for Buchwald-Hartwig couplings from a ChemDraw™ structure input is described. The tool is built on an in-house generated experimental dataset that explores a diverse network of reactant pairings. To minimize the number of experiments necessary to produce models and maximize data value, a workflow based on unsupervised machine leaning tools was created. The workflow enables the construction of models which can successfully generalize—making predictions for reactants which are not represented in the dataset.