Learning Molecular Representations for Thermochemistry Prediction of Cyclic Hydrocarbons and Oxygenates
- 3 June 2021
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 125 (23) , 5166-5179
Abstract
Accurate thermochemistry estimation of polycyclic molecules is crucial for kinetic modeling of chemical processes that use renewable and alternative feedstocks. In kinetic model generators, molecular properties are estimated rapidly with group additivity, but this method is known to have limitations for polycyclic structures. This issue has been resolved in our work by combining a geometry-based molecular representation with a deep neural network trained on ab initio data. Each molecule is transformed into a probabilistic vector from its interatomic distances, bond angles, and dihedral angles. The model is tested on a small experimental dataset (200 molecules) from the literature, a new medium-sized set (4000 molecules) with both open-shell and closed-shell species, calculated at the CBS-QB3 level with empirical corrections, and a large G4MP2-level QM9-based dataset (40 000 molecules). Heat capacities between 298.15 and 2500 K are calculated in the medium set with an average deviation of about 1.5 J mol–1 K–1 and the standard entropy at 298.15 K is predicted with an average error below 4 J mol–1 K–1. The standard enthalpy of formation at 298.15 K has an average out-of-sample error below 4 kJ mol–1 on a QM9 training set size of around 15 000 molecules. By fitting NASA polynomials, the enthalpy of formation at higher temperatures can be calculated with the same accuracy as the standard enthalpy of formation. Uncertainty quantification by means of the ensemble standard deviation is included to indicate when molecules that are on the edge or outside of the application range of the model are evaluated.Keywords
Funding Information
- Fonds Wetenschappelijk Onderzoek (1150817N, 3E013419)
- H2020 European Research Council (818607)
This publication has 75 references indexed in Scilit:
- InChI - the worldwide chemical structure identifier standardJournal of Cheminformatics, 2013
- Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17Journal of Chemical Information and Modeling, 2012
- Towards cleaner combustion engines through groundbreaking detailed chemical kinetic modelsChemical Society Reviews, 2011
- Accurate prediction of heats of formation by a combined method of B3LYP and neural network correctionJournal of Computational Chemistry, 2008
- Assessment of Gaussian-2 and density functional theories for the computation of enthalpies of formationThe Journal of Chemical Physics, 1997
- The expectation-maximization algorithmIEEE Signal Processing Magazine, 1996
- Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94Journal of Computational Chemistry, 1996
- Quantum Mechanical Calculations to Chemical AccuracyScience, 1991
- The theory and practice of distance geometryBulletin of Mathematical Biology, 1983
- Dibenzo[ghi,mno]fluorantheneJournal of the American Chemical Society, 1966