Data-driven discovery of active phosphine ligand space for cross-coupling reactions

The design of highly active catalysts is a main theme in organic chemistry, but it still relies heavily on expert experience. Herein, powered by machine-learning global structure exploration, we forge a Metal–Phosphine Catalyst Database (MPCD) with a meticulously designed ligand replacement energy metric, a key descriptor to describe the metal–ligand interactions. It pushes the rational design of organometallic catalysts to a quantitative era, where a ±10 kJ mol−1 window of relative ligand binding strength, a so-called active ligand space (ALS), is identified for highly effective catalyst screening. We highlight the chemistry interpretability and effectiveness of ALS for various C–N, C–C and C–S cross-coupling reactions via a Sabatier-principle-based volcano plot and demonstrate its predictive power in discovering low-cost ligands in catalyzing Suzuki cross-coupling involving aryl chloride. The advent of the MPCD provides a data-driven new route for speeding up organometallic catalysis and other applications.