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

Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

8.3K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.3K
¹H NMR of Conformationally Flexible Molecules: Temporal Resolution00:52

¹H NMR of Conformationally Flexible Molecules: Temporal Resolution

835
At room temperature, the chair conformer of cyclohexane undergoes rapid ring flipping between two equivalent chair conformers at a rate of approximately 105 times per second. These two chair conformers are in equilibrium. The rapid ring flipping results in the interconversion of the axial proton to an equatorial proton and an equatorial to the axial proton. Such interconversions are too rapid and cannot be detected on the NMR timescale. Hence, the NMR spectrometer cannot distinguish between the...
835
What is Organic Chemistry?02:17

What is Organic Chemistry?

75.4K
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...
75.4K
Chemical Shift: Internal References and Solvent Effects01:17

Chemical Shift: Internal References and Solvent Effects

635
In an NMR sample, precise measurement of the absolute absorption frequencies of nuclei is difficult. A standard internal reference compound is added, and the frequency difference between the reference signal and sample signals is measured.
The internal reference compound generally used in NMR spectroscopy is tetramethylsilane (TMS). TMS is preferred because it is chemically inert, soluble in NMR solvents, and easily removable. Also, the highly shielded methyl protons in TMS yield an intense...
635
Organic Compounds03:02

Organic Compounds

51.4K
All living things are formed mostly of carbon compounds called organic compounds. The category of organic compounds includes both natural and synthetic compounds that contain carbon. Although a single, precise definition has yet to be identified by the chemistry community, most agree that a defining trait of organic molecules is the presence of carbon as the principal element, bonded to hydrogen and other carbon atoms. However, some carbon-containing compounds such as carbonates, cyanides, and...
51.4K
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

34.3K
VSEPR Theory for Determination of Electron Pair Geometries
34.3K

You might also read

Related Articles

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

Sort by
Same author

Steric Hindrance of Proton Donors Modulates Heterogeneous Electrochemical Nitrogen Reduction Reaction Selectivity in Nonaqueous Electrolytes.

Journal of the American Chemical Society·2026
Same author

Enhancing Generalization in Synthesizability Prediction of Structurally Dissimilar Materials.

Journal of chemical information and modeling·2026
Same author

Confinement and Interface Effects on Radiolysis in Liquid-Phase TEM Probed by Palladium Nanocrystal Etching.

Nano letters·2026
Same author

Generative modelling of inorganic materials with explicit electronic structure.

Nature communications·2026
Same author

Machine Learning-Guided Discovery of Sterically Protected High Triplet Exciplex Hosts for Ultra-Bright Green OLEDs.

Journal of the American Chemical Society·2025
Same author

SynTwins: a retrosynthesis-guided framework for synthesizable molecular analog generation.

Chemical science·2025

Related Experiment Video

Updated: Jul 1, 2025

Hand Controlled Manipulation of Single Molecules via a Scanning Probe Microscope with a 3D Virtual Reality Interface
11:00

Hand Controlled Manipulation of Single Molecules via a Scanning Probe Microscope with a 3D Virtual Reality Interface

Published on: October 2, 2016

9.0K

Precise atom-to-atom mapping for organic reactions via human-in-the-loop machine learning.

Shuan Chen1,2, Sunggi An1,2, Ramil Babazade3

  • 1Department of Chemical and Biomolecular Engineering, KAIST, Daejeon, South Korea.

Nature Communications
|March 14, 2024
PubMed
Summary

LocalMapper, a new machine learning model, accurately predicts atom-to-atom mapping (AAM) in chemical reactions by learning from chemists. This approach enhances reaction datasets, improving future AI models for chemical synthesis.

More Related Videos

Molecular Imaging of Human Brain Organoids Using Mass Spectrometry
08:04

Molecular Imaging of Human Brain Organoids Using Mass Spectrometry

Published on: September 27, 2024

693
Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function
05:57

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

381

Related Experiment Videos

Last Updated: Jul 1, 2025

Hand Controlled Manipulation of Single Molecules via a Scanning Probe Microscope with a 3D Virtual Reality Interface
11:00

Hand Controlled Manipulation of Single Molecules via a Scanning Probe Microscope with a 3D Virtual Reality Interface

Published on: October 2, 2016

9.0K
Molecular Imaging of Human Brain Organoids Using Mass Spectrometry
08:04

Molecular Imaging of Human Brain Organoids Using Mass Spectrometry

Published on: September 27, 2024

693
Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function
05:57

Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function

Published on: April 26, 2024

381

Area of Science:

  • Computational Chemistry
  • Machine Learning
  • Chemical Informatics

Background:

  • Atom-to-atom mapping (AAM) is crucial for understanding chemical reaction mechanisms.
  • Current AAM methods rely on substructure alignment, not chemical principles, limiting the accuracy of machine learning models in retrosynthesis and reaction prediction.
  • High-quality AAM data is essential for developing reliable machine learning models for chemical reactions.

Purpose of the Study:

  • To develop a machine learning model, LocalMapper, for accurate atom-to-atom mapping (AAM) in chemical reactions.
  • To leverage human-in-the-loop learning with chemist-labeled data to train the AAM model.
  • To improve the quality of reaction datasets for machine learning applications.

Main Methods:

  • Developed LocalMapper, a machine learning model utilizing human-in-the-loop learning.
  • Trained LocalMapper on a dataset of chemist-labeled chemical reactions.
  • Evaluated LocalMapper's performance on predicting AAM for a large reaction dataset (50K reactions).

Main Results:

  • LocalMapper achieved 98.5% calibrated accuracy in predicting AAM for 50,000 reactions, learning from only 2% of human-labeled data.
  • Confident predictions from LocalMapper covered 97% of reactions with 100% accuracy on a subset.
  • LocalMapper outperformed existing methods in out-of-distribution experiments.

Conclusions:

  • LocalMapper effectively learns accurate atom-to-atom mapping from limited chemist-labeled data.
  • The model demonstrates high accuracy and reliability, outperforming current methods.
  • LocalMapper has the potential to generate precise AAM data, significantly improving machine learning models for chemical reaction prediction.