Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

2011/09/30 by Matthias Rupp, Alexandre Tkatchenko, Klaus‐Robert Müller +1 · 1 voice · 21 citations
Computer Science · Materials Science · Physics and Astronomy · #Advanced Chemical Physics Studies #Computational Drug Discovery Methods #Machine Learning in Materials Science

paper · doi:10.1103/physrevlett.108.058301

openalex publication_date 2012/01/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

We introduce a machine learning model to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only. The problem of solving the molecular Schrödinger equation is mapped onto a nonlinear statistical regression problem of reduced complexity. Regression models are trained on and compared to atomization energies computed with hybrid density-functional theory. Cross validation over more than seven thousand organic molecules yields a mean absolute error of ∼10 kcal/mol. Applicability is demonstrated for the prediction of molecular atomization potential energy curves.

Citations

• Statistical Mechanics: Theory and Molecular Simulation
• Rationale for mixing exact exchange with density functional approximations
• Density-functional thermochemistry. III. The role of exact exchange
• Self-Consistent Equations Including Exchange and Correlation Effects
• Handbook of Molecular Descriptors

Cited by

• Elucidating atmospheric brown carbon -- Supplanting chemical intuition with exhaustive enumeration and machine learning
• ULaMDyn: enhancing excited-state dynamics analysis through streamlined unsupervised learning
• Discriminative Learning of Similarity and Group Equivariant\n Representations
• The emergence of machine learning force fields in drug design
• Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning
• Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
• Trees and Islands -- Machine learning approach to nuclear physics
• Graph Convolutional Neural Network-Enabled Frontier Molecular Orbital Prediction: A Case Study with Neurotransmitters and Antidepressants
• A framework to evaluate machine learning crystal stability predictions
• Prediction of Atomization Energies of Au13+ Clusters through the Machine Learning Approach
• Generating valid Euclidean distance matrices
• Bosonic Random Walk Networks for Graph Learning
• Reducing the Long Tail Losses in Scientific Emulations with Active\n Learning
• Learning the gravitational force law and other analytic functions
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• BenchMake: Turn any scientific data set into a reproducible benchmark
• Substituting density functional theory in reaction barrier calculations for hydrogen atom transfer in proteins
• GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• Chemical Bond-Based Representation of Materials
• Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks

Discussions

• #descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips Coulomb matrix has been proposed by @profvlilienfeld.bsky.social et al. in "Fast and accurate modeling of molecular..." doi [bsky, 0 points, 0 comments]