A Machine Learning-Based Study of Li+ and Na+ Metal Complexation with Phosphoryl-Containing Ligands for the Selective Extraction of Li+ from Brine

The growth of technologies concerned with the high demand in lithium (Li) sources dictates the need for technological solutions garnering Li supplies to preserve the sustainability of the processes. The aim of this study was to use a machine learning-based search for phosphoryl-containing podandic ligands, potentially selective for lithium extraction from brine. Based on the experimental data available on the stability constant values of phosphoryl-containing organic ligands with Li+ and Na+ cations at 4:1 THF:CHCl3, candidate di-podandic ligands were proposed, for which the stability constant values (logK) with Li+ and Na+ as well as the corresponding selectivity values were evaluated using machine learning methods (ML). The modelling showed a reasonable predictive performance with the following statistical parameters: the determination coefficient R2= 0.75, 0.87 and 0.83 and root-mean-square error RMSE = 0.485, 0.449 and 0.32 were obtained for the prediction of the stability constant values with Li+ and Na+ cations and Li+/Na+ selectivity values, respectively. This ML-based analysis was complemented by the preliminary estimation of the host–guest complementarity of metal–ligand 1:1 complexes using the HostDesigner software.

[1]  A. Tsivadze,et al.  Recovery of Uranium, Thorium, and Other Rare Metals from Eudialyte Concentrate by a Binary Extractant Based on 1,5-bis[2-(hydroxyethoxyphosphoryl)-4-ethylphenoxy]-3-oxapentane and Methyl Trioctylammonium Nitrate , 2022, Minerals.

[2]  Kaito Kanahashi,et al.  Machine learning-based analysis of overall stability constants of metal–ligand complexes , 2022, Scientific Reports.

[3]  A. Malysheva,et al.  Comparative Evaluation of the Properties of Aminopolyphosphonates as Chemical Precursors of Samarium-153 Radiopharmaceuticals , 2022, Russian Journal of General Chemistry.

[4]  V. Solov'ev,et al.  Design of phosphoryl containing podands with Li+/Na+ selectivity using machine learning , 2021, SAR and QSAR in environmental research.

[5]  V. Solov'ev,et al.  Synthesis, Complexation Properties, and Evaluation of New Aminodiphosphonic Acids as Vector Molecules for 68Ga Radiopharmaceuticals , 2021, Molecules.

[6]  N. Choudhary,et al.  Phosphonate Chelators for Medicinal Metal Ions. , 2021, Inorganic chemistry.

[7]  A. Tsivadze,et al.  Extraction of REE(III), U(VI), and Th(IV) from Perchloric Acid Solutions with 2,6-Bis(diphenylphosphorylmethyl)pyridine N-Oxide , 2021, Radiochemistry.

[8]  Beena Rai,et al.  Applied machine learning for predicting the lanthanide-ligand binding affinities , 2020, Scientific Reports.

[9]  Damien de Mijolla,et al.  Shapley explainability on the data manifold , 2020, ICLR.

[10]  R. Stolkin,et al.  Recycling lithium-ion batteries from electric vehicles , 2019, Nature.

[11]  A. Ghahreman,et al.  Novel approaches for lithium extraction from salt-lake brines: A review , 2019, Hydrometallurgy.

[12]  A. Varnek,et al.  Classification of Metal Binders by Naïve Bayes Classifier on the Base of Molecular Fragment Descriptors and Ensemble Modeling , 2019, Molecular informatics.

[13]  Z. Ji,et al.  Preparation of titanium-base lithium ionic sieve with sodium persulfate as eluent and its performance , 2017 .

[14]  J. Dufrêche,et al.  Thermodynamic Description of Synergy in Solvent Extraction: II Thermodynamic Balance of Driving Forces Implied in Synergistic Extraction. , 2017, Langmuir : the ACS journal of surfaces and colloids.

[15]  J. Dufrêche,et al.  Thermodynamic Description of Synergy in Solvent Extraction: I. Enthalpy of Mixing at the Origin of Synergistic Aggregation. , 2016, Langmuir : the ACS journal of surfaces and colloids.

[16]  B. Swain.  Separation and purification of lithium by solvent extraction and supported liquid membrane, analysis of their mechanism: a review , 2016 .

[17]  V. Babain,et al.  Recovery of minor actinides from high-level wastes: modern trends , 2016 .

[18]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[19]  V. Solov'ev,et al.  The complexation of metal ions with various organic ligands in water: prediction of stability constants by QSPR ensemble modelling , 2015, Journal of Inclusion Phenomena and Macrocyclic Chemistry.

[20]  Alexandre Varnek,et al.  QSPR ensemble modelling of the 1:1 and 1:2 complexation of Co2+, Ni2+, and Cu2+ with organic ligands: relationships between stability constants , 2014, Journal of Computer-Aided Molecular Design.

[21]  A. Varnek,et al.  QSPR ensemble modelling of alkaline-earth metal complexation , 2013, Journal of Inclusion Phenomena and Macrocyclic Chemistry.

[22]  Chris Morley,et al.  Open Babel: An open chemical toolbox , 2011, J. Cheminformatics.

[23]  H. Zhai,et al.  Prediction of association constants of cesium chelates based on Uniform Design Optimized Support Vector Machine , 2011 .

[24]  A. Varnek,et al.  Computer-aided design of new metal binders , 2008 .

[25]  Jahan B. Ghasemi,et al.  QSPR modeling of stability constants of diverse 15-crown-5 ethers complexes using best multiple linear regression , 2008 .

[26]  A. Yu. Tsivadze,et al.  Structure-property modelling of complex formation of strontium with organic ligands in water , 2006 .

[27]  Igor V. Tetko,et al.  Benchmarking of Linear and Nonlinear Approaches for Quantitative Structure-Property Relationship Studies of Metal Complexation with Ionophores , 2006, J. Chem. Inf. Model..

[28]  J. Uddin,et al.  Search for improved host architectures: application of de novo structure-based design and high-throughput screening methods to identify optimal building blocks for multidentate ethers. , 2005, Journal of the American Chemical Society.

[29]  B. Rapko,et al.  Toward the computer-aided design of metal ion sequestering agents , 2004 .

[30]  A. Varnek,et al.  Structure—property modeling of metal binders using molecular fragments , 2004 .

[31]  B. Hay,et al.  HostDesigner: a program for the de novo structure-based design of molecular receptors with binding sites that complement metal ion guests. , 2002, Inorganic chemistry.

[32]  Alexandre Varnek,et al.  Assessment of the Macrocyclic Effect for the Complexation of Crown-Ethers with Alkali Cations Using the Substructural Molecular Fragments Method , 2002, J. Chem. Inf. Comput. Sci..

[33]  G. Wipff,et al.  Switching Ca2+/Ba2+ to Ba2+/Ca2+ Potentiometric Selectivities of Podands with Phosphoryl-containing Terminal Groups: A Molecular Modelling Study , 2000 .

[34]  Alexandre Varnek,et al.  Modeling of Ion Complexation and Extraction Using Substructural Molecular Fragments , 2000, J. Chem. Inf. Comput. Sci..

[35]  R. M. Izatt,et al.  Thermodynamic and Kinetic Data for Macrocycle Interaction with Cations, Anions, and Neutral Molecules , 1995 .

[36]  Zhong-Guo Shi,et al.  A computer simulation — Statistical procedure for predicting complexation equilibrium constants , 1994 .

[37]  A. Varnek,et al.  Complexation of lithium and sodium cations with β-phosphorylate ethers, modelling terminal groups of organophosphorus podands. An experimental and theoretical study , 1992 .

[38]  A. Gamba,et al.  Molecular modelling of organophosphorus podands and their complexes with alkali metal cations , 1992 .

[39]  Marcel Weil,et al.  Recycling of Traction Batteries as a Challenge and Chance for Future Lithium Availability , 2014 .

[40]  Alexandre Varnek,et al.  New Approach for Accurate QSPR Modeling of Metal Complexation: Application to Stability Constants of Complexes of Lanthanide Ions Ln 3+ , Ag + , Zn 2+ , Cd 2+ and Hg 2+ with Organic Ligands in Water , 2012 .

[41]  Manuela Pavan,et al.  DRAGON SOFTWARE: AN EASY APPROACH TO MOLECULAR DESCRIPTOR CALCULATIONS , 2006 .

[42]  L. Shapley,et al.  A VALUE FOR n-PERSON GAMFB , 2005 .

[43]  H. Imura,et al.  The Synergistic Selective Extraction of Lithium(1) with 2-Thenoyltrifluoroacetone and 1,10-Phenanthroline Derivatives , 2002 .