A general QSPR protocol for the prediction of atomic/inter-atomic properties: a fragment based graph convolutional neural network (F-GCN)
- 13 May 2021
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 23 (23), 13242-13249
- https://doi.org/10.1039/d1cp00677k
Abstract
In this study, a general quantitative structure–property relationship (QSPR) protocol, fragment based graph convolutional neural network (F-GCN), was developed for the prediction of atomic/inter-atomic properties. We applied this novel artificial intelligence (AI) tool in predictions of NMR chemical shifts and bond dissociation energies (BDEs). The obtained results were comparable to experimental measurements, while the computational cost was substantially reduced, with respect to pure density functional theory (DFT) calculations. The two important features of F-GCN can be summarised as: first, it could utilise different levels of molecular fragments for atomic/inter-atomic information extraction; second, the designed architecture is also open to include additional descriptors for a more accurate solution of the local environment at atomic level, making itself more efficient for structural solutions. And during our test, the averaged prediction error of 1H NMR chemical shifts is as small as 0.32 ppm, and the error of C–H BDE estimation is 2.7 kcal mol−1. Moreover, we further demonstrated the applicability of this developed F-GCN model via several challenging structural assignments. The success of the F-GCN in atomic and inter-atomic predictions also indicates an essential improvement of computational chemistry with the assistance of AI tools.This publication has 51 references indexed in Scilit:
- Computational Study of Bond Dissociation Enthalpies for a Large Range of Native and Modified LigninsThe Journal of Physical Chemistry Letters, 2011
- A thorough benchmark of density functional methods for general main group thermochemistry, kinetics, and noncovalent interactionsPhysical Chemistry Chemical Physics, 2011
- Efficient and Accurate Double-Hybrid-Meta-GGA Density Functionals—Evaluation with the Extended GMTKN30 Database for General Main Group Thermochemistry, Kinetics, and Noncovalent InteractionsJournal of Chemical Theory and Computation, 2010
- Assessment of Orbital-Optimized, Spin-Component Scaled Second-Order Many-Body Perturbation Theory for Thermochemistry and KineticsJournal of Chemical Theory and Computation, 2009
- Computational Study on the Selectivity of Donor/Acceptor-Substituted Rhodium CarbenoidsThe Journal of Organic Chemistry, 2009
- Long-range corrected hybrid density functionals with damped atom–atom dispersion correctionsPhysical Chemistry Chemical Physics, 2008
- How Well Can New-Generation Density Functionals Describe the Energetics of Bond-Dissociation Reactions Producing Radicals?The Journal of Physical Chemistry A, 2008
- Should Contemporary Density Functional Theory Methods Be Used to Study the Thermodynamics of Radical Reactions?The Journal of Physical Chemistry A, 2007
- Assessment of Experimental Bond Dissociation Energies Using Composite ab Initio Methods and Evaluation of the Performances of Density Functional Methods in the Calculation of Bond Dissociation EnergiesJournal of Chemical Information and Computer Sciences, 2003
- Bond Dissociation Energies of Organic MoleculesAccounts of Chemical Research, 2003