Prediction of Organic Homolytic Bond Dissociation Enthalpies at Near Chemical Accuracy with Sub-Second Computational Cost: Article No. 2328

Peter St. John, Yanfei Guan, Yeonjoon Kim, Seon Ah Kim, Robert Paton

Research output: Contribution to journalArticlepeer-review

137 Scopus Citations

Abstract

Bond dissociation enthalpies (BDEs) of organic molecules play a fundamental role in determining chemical reactivity and selectivity. However, BDE computations at sufficiently high levels of quantum mechanical theory require substantial computing resources. In this paper, we develop a machine learning model capable of accurately predicting BDEs for organic molecules in a fraction of a second. We perform automated density functional theory (DFT) calculations at the M06-2X/def2-TZVP level of theory for 42,577 small organic molecules, resulting in 290,664 BDEs. A graph neural network trained on a subset of these results achieves a mean absolute error of 0.58 kcal mol-1 (vs DFT) for BDEs of unseen molecules. We further demonstrate the model on two applications: first, we rapidly and accurately predict major sites of hydrogen abstraction in the metabolism of drug-like molecules, and second, we determine the dominant molecular fragmentation pathways during soot formation.
Original languageAmerican English
Number of pages12
JournalNature Communications
Volume11
DOIs
StatePublished - 2020

NREL Publication Number

  • NREL/JA-2700-75744

Keywords

  • bond dissociation enthalpies
  • chemical reactivity
  • density functional theory
  • machine learning
  • organic molecules

Fingerprint

Dive into the research topics of 'Prediction of Organic Homolytic Bond Dissociation Enthalpies at Near Chemical Accuracy with Sub-Second Computational Cost: Article No. 2328'. Together they form a unique fingerprint.

Cite this