Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships

Abstract

Machine learning (ML) of quantum mechanical properties shows promise for accelerating chemical discovery. For transition metal chemistry where accurate calculations are computationally costly and available training data sets are small, the molecular representation becomes a critical ingredient in ML model predictive accuracy. We introduce a series of revised autocorrelation functions (RACs) that encode relationships between the heuristic atomic properties (e.g., size, connectivity, and electronegativity) on a molecular graph. We alter the starting point, scope, and nature of the quantities evaluated in standard ACs to make these RACs amenable to inorganic chemistry. On an organic molecule set, we first demonstrate superior standard AC performance to other presently-available topological descriptors for ML model training, with mean unsigned errors (MUEs) for atomization energies on set-aside test molecules as low as 6 kcal/mol. For inorganic chemistry, our RACs yield 1 kcal/mol ML MUEs on set-aside test molecules in spin-state splitting in comparison to 15-20x higher errors from feature sets that encode whole-molecule structural information. Systematic feature selection methods including univariate filtering, recursive feature elimination, and direct optimization (e.g., random forest and LASSO) are compared. Random-forest- or LASSO-selected subsets 4-5x smaller than RAC-155 produce sub- to 1-kcal/mol spin-splitting MUEs, with good transferability to metal-ligand bond length prediction (0.004-5 Å MUE) and redox potential on a smaller data set (0.2-0.3 eV MUE). Evaluation of feature selection results across property sets reveals the relative importance of local, electronic descriptors (e.g., electronegativity, atomic number) in spin-splitting and distal, steric effects in redox potential and bond lengths.

43 double spaced pages, 11 figures, 4 tables

References in corpus (8)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Big Data of Materials Science - Critical Role of the Descriptor
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accelerated materials property predictions and design using motif-based fingerprints
• Quantum Chemistry for Solvated Molecules on Graphical Processing Units (GPUs)using Polarizable Continuum Models
• Towards quantifying the role of exact exchange in predictions of transition metal complex properties
• Where Does the Density Localize? Convergent Behavior for Global Hybrids, Range Separation, and DFT+U
• Constant Size Molecular Descriptors For Use With Machine Learning

Cited by in corpus (2)

• An Atomistic Machine Learning Package for Surface Science and Catalysis
• Prediction of Atomization Energies of Au13+ Clusters through the Machine Learning Approach