Resolving Transition Metal Chemical Space: Feature Selection for Machine Learning and Structure–Property Relationships
Top Cited Papers
- 15 November 2017
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 121 (46) , 8939-8954
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 of 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 15–20× higher errors for 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 4–5× smaller than the full RAC set 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.Keywords
All Related Versions
Funding Information
- Massachusetts Institute of Technology
- Division of Electrical, Communications and Cyber Systems (ECCS-1449291)
- Division of Chemical, Bioengineering, Environmental and Transport Systems (CBET-1704266)
- Burroughs Wellcome Fund
This publication has 99 references indexed in Scilit:
- Accelerating materials property predictions using machine learningScientific Reports, 2013
- The high-throughput highway to computational materials designNature Materials, 2013
- Reduction of Systematic Uncertainty in DFT Redox Potentials of Transition-Metal ComplexesThe Journal of Physical Chemistry C, 2012
- Variable selection using random forestsPattern Recognition Letters, 2010
- A review of feature selection techniques in bioinformaticsBioinformatics, 2007
- Molecular similarity analysis in virtual screening: foundations, limitations and novel approachesDrug Discovery Today, 2007
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- Chemical spaceNature, 2004
- Development and testing of a general amber force fieldJournal of Computational Chemistry, 2004
- Prediction of Partition Coefficients (LOGPoct) Using Autocorrelation DescriptorsSAR and QSAR in Environmental Research, 1997