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

Competition02:34

Competition

24.9K
When organisms require the same limited resources within an environment, they may have to compete for them. Competition is a net-negative interaction. Even if two competing individuals or populations do not interact directly, the overall fitness of both competitors is lowered as a result of not having full access to the limited resource.
24.9K
Protein Networks02:26

Protein Networks

4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
Network Covalent Solids02:18

Network Covalent Solids

16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Chemistry of Carbohydrates03:25

Chemistry of Carbohydrates

90.8K
Carbohydrates are an essential part of the diet in humans and animals. Grains, fruits, and vegetables are natural sources of carbohydrates that provide energy to the body, particularly through glucose, a simple sugar that is a component of starch and an ingredient in many staple foods. The stoichiometric formula (CH2O)n, where n is the number of carbons in the molecule represents carbohydrates. In other words, the ratio of carbon to hydrogen to oxygen is 1:2:1 in carbohydrate molecules. This...
90.8K
Chemistry of Carbohydrates03:25

Chemistry of Carbohydrates

10.8K
10.8K
What is Organic Chemistry?02:17

What is Organic Chemistry?

92.4K
Organic chemistry is the study of compounds of carbon called organic compounds. Organic compounds either originate from living organisms or are synthesized by chemists. A defining trait of these compounds is the presence of carbon as the principal element, which is bonded to other carbon atoms and other elements such as hydrogen, oxygen, nitrogen, and sulfur. The existence of a wide array of organic molecules is a consequence of carbon atoms’ ability to form up to four strong bonds to...
92.4K

You might also read

Related Articles

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

Sort by
Same author

Software for the frontiers of quantum chemistry: An overview of developments in the Q-Chem 5 package.

The Journal of chemical physics·2021
Same author

Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences.

The Journal of chemical physics·2019
See all related articles

Related Experiment Video

Updated: Feb 8, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Metadynamics for training neural network model chemistries: A competitive assessment.

John E Herr1, Kun Yao1, Ryker McIntyre1

  • 1Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA.

The Journal of Chemical Physics
|July 2, 2018
PubMed
Summary

Metadynamics (MetaMD) sampling improves neural network model chemistries (NNMCs) by efficiently exploring chemical space. Unlike molecular dynamics (MD), MetaMD ensures better generalization for reactive system simulations.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K
Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

5.3K

Related Experiment Videos

Last Updated: Feb 8, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K
Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
07:01

Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment

Published on: September 20, 2020

5.3K

Area of Science:

  • Computational Chemistry
  • Materials Science
  • Machine Learning

Background:

  • Neural network model chemistries (NNMCs) are crucial for exploring chemical space and simulating reactive systems.
  • Improving NNMCs requires incorporating physical details like long-range forces, but short-range accuracy is data-limited.
  • Current data sampling methods may not adequately represent chemical space, leading to poor model generalization.

Purpose of the Study:

  • To competitively evaluate common sampling methods (molecular dynamics and normal-mode sampling) against Metadynamics (MetaMD) for preparing training geometries in NNMCs.
  • To assess the efficiency and effectiveness of different sampling strategies in improving the generality of NNMCs.
  • To identify cost-effective methods for enhancing the predictive power of NNMCs.

Main Methods:

  • Comparison of molecular dynamics (MD) and normal-mode sampling with Metadynamics (MetaMD) for generating training data.
  • Evaluation of sampling method efficiency based on sample quality and generalization improvement.
  • Analysis of the scalability and implementation cost of MetaMD in NNMC software.

Main Results:

  • Molecular dynamics (MD) was found to be an inefficient sampling method, as increased samples did not enhance model generality.
  • Metadynamics (MetaMD) demonstrated effectiveness in exploring new chemical space relevant to chemistry near kbT.
  • MetaMD is easily implementable in NNMC packages with costs scaling linearly with molecule size.

Conclusions:

  • Metadynamics (MetaMD) offers a superior and cost-effective approach for sampling training geometries in neural network model chemistries.
  • MetaMD addresses the critical issue of generalization in NNMCs by ensuring exploration of diverse chemical regions.
  • The findings suggest MetaMD as a valuable tool for advancing the accuracy and applicability of NNMCs in chemical simulations.