Prediction of stability constants of metal–ligand complexes by machine learning for the design of ligands with optimal metal ion selectivity

• Published in: The Journal of chemical physics Vol. 160; no. 4
• Main Authors: Zahariev, Federico, Ash, Tamalika, Karunaratne, Erandika, Stender, Erin, Gordon, Mark S., Windus, Theresa L., Pérez García, Marilú
• Format: Journal Article
• Language: English
• Published: United States American Institute of Physics 28.01.2024; American Institute of Physics (AIP)
• Subjects: ab-initio methods; Algorithms; Aqueous solutions; artificial neural networks; CAD; computational models; Computer aided design; INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; ions and properties; Lanthanides; Ligands; Machine learning; Message passing; Neural networks; Root-mean-square errors; Software; Stability constants; thermodynamic cycles; transition metal ion-chelating
• ISSN: 0021-9606; 1089-7690; 1520-9032; 1089-7690
• DOI: 10.1063/5.0176000

The new LOGKPREDICT program integrates HostDesigner molecular design software with the machine learning (ML) program Chemprop. By supplying HostDesigner with predicted log K values, LOGKPREDICT enhances the computer-aided molecular design process by ranking ligands directly by metal–ligand binding strength. Harnessing reliable experimental data from a historic National Institute of Standards and Technology (NIST) database and data from the International Union of Pure and Applied Chemistry (IUPAC), we train message passing neural net algorithms. The multi-metal NIST-based ML model has a root mean square error (RMSE) of 0.629 ± 0.044 (R2 of 0.960 ± 0.006), while two versions of lanthanide-only IUPAC-based ML models have, respectively, RMSE of 0.764 ± 0.073 (R2 of 0.976 ± 0.005) and 0.757 ± 0.071 (R2 of 0.959 ± 0.007). For relative log K predictions on an out-of-sample set of six ligands, demonstrating metal ion selectivity, the RMSE value reaches a commendably low 0.25. We showcase the use of LOGKPREDICT in identifying ligands with high selectivity for lanthanides in aqueous solutions, a finding supported by recent experimental evidence. We also predict new ligands yet to be verified experimentally. Therefore, our ML models implemented through LOGKPREDICT and interfaced with the ligand design software HostDesigner pave the way for designing new ligands with predetermined selectivity for competing metal ions in an aqueous solution.