Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

The Quantum-Mechanical Model of an Atom02:45

The Quantum-Mechanical Model of an Atom

41.7K
Shortly after de Broglie published his ideas that the electron in a hydrogen atom could be better thought of as being a circular standing wave instead of a particle moving in quantized circular orbits, Erwin Schrödinger extended de Broglie’s work by deriving what is now known as the Schrödinger equation. When Schrödinger applied his equation to hydrogen-like atoms, he was able to reproduce Bohr’s...
41.7K
Hybridization of Atomic Orbitals II03:35

Hybridization of Atomic Orbitals II

31.5K
sp3d and sp3d 2 Hybridization
31.5K
Nuclear Binding Energy02:13

Nuclear Binding Energy

12.1K
The difference between the calculated and experimentally measured masses is known as the mass defect of the atom. In the case of helium-4, the mass defect indicates a “loss” in mass of 4.0331 amu – 4.0026 amu = 0.0305 amu. The loss in mass accompanying the formation of an atom from protons, neutrons, and electrons is due to the conversion of that mass into energy that is evolved as the atom forms. The nuclear binding energy is the energy produced when the atoms’ nucleons...
12.1K
VSEPR Theory and the Effect of Lone Pairs04:01

VSEPR Theory and the Effect of Lone Pairs

41.6K
Effect of Lone Pairs of Electrons on Molecule Geometry
41.6K
¹H NMR: Pople Notation01:09

¹H NMR: Pople Notation

1.7K
The Pople nomenclature system classifies spin systems based on the difference between their chemical shifts. Coupled spins are denoted by capital letters with subscripts indicating the number of equivalent nuclei. When the coupled nuclei have well-separated chemical shifts, they are assigned letters that are far apart in the alphabet, such as A and X. When the difference in chemical shifts is small, coupled nuclei are named using adjacent letters of the alphabet (AB, MN, or XY).
A proton...
1.7K
Molecular Orbital Theory II03:51

Molecular Orbital Theory II

18.9K
Molecular Orbital Energy Diagrams
18.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

GW-BSE for molecular excited states in REST: State-of-the-art methods, acceleration strategies, and the LAMB approximation.

The Journal of chemical physics·2026
Same author

Computing Paramagnetic <sup>13</sup>C NMR Chemical Shifts of Cobalt(II) Porphyrins with the eXtended ONIOM Method.

Journal of chemical theory and computation·2026
Same author

In search of density functional approximations for accurate evaluation of NMR shielding constants for main-group nuclei: Analytic derivatives, benchmarking, and insights from density-corrected density functional theory.

The Journal of chemical physics·2026
Same author

Pair-Density Functional Theory Based on Spin-Projected Unrestricted Hartree-Fock Method: A Density-Corrected Version.

Journal of computational chemistry·2026
Same author

Separated Energy Domains in the Sequential Hydration of a Benzonitrile Radical Cation.

Precision chemistry·2026
Same author

Extending the mean-field microkinetics for an accurate and efficient modeling of complex heterogeneous catalyst surfaces.

Nature communications·2026

Related Experiment Video

Updated: May 21, 2025

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
12:11

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

8.1K

X2-PEC: A Neural Network Model Based on Atomic Pair Energy Corrections.

Minghong Jiang1, Zhanfeng Wang1, Yicheng Chen1

  • 1Collaborative Innovation Center of Chemistry for Energy Materials, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, MOE Key Laboratory of Computational Physical Sciences, Department of Chemistry, Fudan University, Shanghai, China.

Journal of Computational Chemistry
|March 18, 2025
PubMed
Summary

The new X2-PEC deep learning method enhances low-rung density functional theory (DFT) calculations to high-rung accuracy. This artificial neural network (ANN) approach improves predictions for molecular properties like atomization energies and enthalpies of formation.

Keywords:
B3LYPBLYPX1XYGJ‐OSdensity functional theoryenthalpy of formationneural network

More Related Videos

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

1.0K
Isotopic Effect in Double Proton Transfer Process of Porphycene Investigated by Enhanced QM/MM Method
05:51

Isotopic Effect in Double Proton Transfer Process of Porphycene Investigated by Enhanced QM/MM Method

Published on: July 19, 2019

6.2K

Related Experiment Videos

Last Updated: May 21, 2025

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
12:11

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

8.1K
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
06:50

Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions

Published on: January 26, 2024

1.0K
Isotopic Effect in Double Proton Transfer Process of Porphycene Investigated by Enhanced QM/MM Method
05:51

Isotopic Effect in Double Proton Transfer Process of Porphycene Investigated by Enhanced QM/MM Method

Published on: July 19, 2019

6.2K

Area of Science:

  • Computational Chemistry
  • Machine Learning in Chemistry
  • Quantum Chemistry

Background:

  • Artificial neural networks (ANNs) are increasingly applied in chemistry for predicting molecular properties.
  • Existing methods often face limitations in accuracy, particularly with lower-rung density functional theory (DFT) approximations.
  • There is a need for methods that can bridge the accuracy gap between low-rung and high-rung DFT calculations.

Purpose of the Study:

  • To introduce the X2-PEC method, an advanced artificial neural network (ANN) model for molecular property prediction.
  • To enhance the accuracy of low-rung DFT calculations to the level of high-rung DFT methods using deep learning.
  • To demonstrate the predictive capabilities of X2-PEC for atomization energies, enthalpies of formation, and reaction barriers.

Main Methods:

  • Developed the X2-PEC method, a generalization of the X1 series of ANN methods incorporating pair energy correction (PEC).
  • Constructed feature vectors using overlap integrals and core Hamiltonian integrals to capture atomic interaction information.
  • Trained the X2-PEC model on the QM9 dataset and evaluated its performance on various standard chemical datasets.

Main Results:

  • X2-PEC accurately predicts atomization energies for isomers like C6H8 and C4H4N2O.
  • The model shows commendable performance on standard enthalpies of formation for multiple datasets (G2-HCNOF, PSH36, ALKANE28, BIGMOL20, HEDM45).
  • X2-PEC also demonstrates good accuracy for reaction barriers on a HCNOF subset of BH9, indicating strong generalization ability.

Conclusions:

  • The X2-PEC method effectively elevates the accuracy of low-rung DFT calculations to high-rung DFT levels through deep learning.
  • The model's feature vector construction successfully incorporates crucial physical and chemical information for atomic interactions.
  • X2-PEC shows significant practical significance and potential for further development in computational chemistry.