Representations and Strategies for Transferable Machine Learning Models in Chemical Discovery

Abstract

Strategies for machine-learning(ML)-accelerated discovery that are general across materials composition spaces are essential, but demonstrations of ML have been primarily limited to narrow composition variations. By addressing the scarcity of data in promising regions of chemical space for challenging targets like open-shell transition-metal complexes, general representations and transferable ML models that leverage known relationships in existing data will accelerate discovery. Over a large set (ca. 1000) of isovalent transition-metal complexes, we quantify evident relationships for different properties (i.e., spin-splitting and ligand dissociation) between rows of the periodic table (i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that incorporates the effective nuclear charge alongside the nuclear charge heuristic that otherwise overestimates dissimilarity of isovalent complexes. To address the common challenge of discovery in a new space where data is limited, we introduce a transfer learning approach in which we seed models trained on a large amount of data from one row of the periodic table with a small number of data points from the additional row. We demonstrate the synergistic value of the eRACs alongside this transfer learning strategy to consistently improve model performance. Analysis of these models highlights how the approach succeeds by reordering the distances between complexes to be more consistent with the periodic table, a property we expect to be broadly useful for other materials domains.

References in corpus (17)

• Scikit-learn: Machine Learning in Python
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Machine Learning Unifies the Modelling of Materials and Molecules
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• A Transferable Machine-Learning Model of the Electron Density
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• Heuristics-Guided Exploration of Reaction Mechanisms
• Direct prediction of phonon density of states with Euclidean neural networks
• Inverse Quantum Chemistry: Concepts and Strategies for Rational Compound Design
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Nonempirical definition of the Mendeleev numbers: Organizing the chemical space