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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

57
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
57
Response Surface Methodology01:16

Response Surface Methodology

147
Response Surface Methodology (RSM) is a collection of statistical and mathematical techniques used to develop, improve, and optimize processes. It is particularly valuable when many input variables or factors potentially influence a response variable.
The process of RSM involves several key steps:
147
Reaction Quotient02:35

Reaction Quotient

48.6K
The status of a reversible reaction is conveniently assessed by evaluating its reaction quotient (Q). For a reversible reaction described by m A + n B ⇌ x C + y D, the reaction quotient is derived directly from the stoichiometry of the balanced equation as
48.6K
Reactivity of Enols01:18

Reactivity of Enols

3.1K
Enols are a class of compounds where a hydroxyl group is attached to a carbon–carbon double bond, which implies that it is a vinyl alcohol. A carbonyl compound with an α hydrogen undergoes keto–enol tautomerism and remains in equilibrium with its tautomer, the enol form. Usually, the keto tautomer is present in a higher concentration than the enol tautomer due to the higher bond energy of C=O compared to C=C. Moreover, the direction of the keto–enol equilibrium is...
3.1K
Column Efficiency: Rate Theory01:12

Column Efficiency: Rate Theory

356
The rate theory of chromatography provides quantitative insight into the shapes and widths of elution bands. These bands are based on the random-walk mechanism governing molecular migration within a column. The Gaussian profile of chromatographic bands arises from the cumulative effect of random molecular motions as they progress through the column.
During elution, a solute molecule experiences numerous transitions between stationary and mobile phases, exhibiting irregular residence times in...
356
Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

8.5K
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,...
8.5K

You might also read

Related Articles

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

Sort by
Same author

The catalytic enantioselective [1,2]-Wittig rearrangement cascade of allylic ethers.

Nature chemistry·2026
Same author

Correction for "Reformulating Reactivity Design for Data-Efficient Machine Learning".

ACS catalysis·2025
Same author

Electrochemical Deconstructive Methoxylation of Arylalcohols-A Synthetic and Mechanistic Investigation.

Chemistry (Weinheim an der Bergstrasse, Germany)·2024
Same author

Using games to understand the mind.

Nature human behaviour·2024
Same author

Solving large-scale MEG/EEG source localisation and functional connectivity problems simultaneously using state-space models.

NeuroImage·2023
Same author

Photoredox-HAT Catalysis for Primary Amine α-C-H Alkylation: Mechanistic Insight with Transient Absorption Spectroscopy.

ACS catalysis·2023

Related Experiment Video

Updated: Jul 12, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K

Reformulating Reactivity Design for Data-Efficient Machine Learning.

Toby Lewis-Atwell1,2, Daniel Beechey2, Özgür Şimşek2

  • 1Department of Chemistry, University of Bath, Claverton Down, Bath BA2 7AY, U.K.

ACS Catalysis
|October 26, 2023
PubMed
Summary

This study presents a data-efficient machine learning (ML) approach for predicting reaction barriers, significantly reducing computational costs. The new method rapidly identifies reactions with specific activation barriers, aiding in catalyst design and drug discovery.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

599
A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM
13:54

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

4.6K

Related Experiment Videos

Last Updated: Jul 12, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.6K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

599
A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM
13:54

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

4.6K

Area of Science:

  • Computational Chemistry
  • Chemical Informatics
  • Machine Learning

Background:

  • Machine learning (ML) models offer rapid reaction barrier predictions for rational reactivity design.
  • Traditional ML models require extensive datasets (thousands of barriers), which are computationally expensive and lack generalizability across different reaction spaces.
  • Bespoke datasets are necessary for each specific reaction region of interest.

Purpose of the Study:

  • To reformulate the ML barrier prediction problem into a data-efficient process for identifying reactions with desired target values.
  • To enable rapid selection of reactions with purpose-specific activation barriers for applications in synthesis, catalysis, toxicology, and drug discovery.
  • To develop a method requiring only tens of accurately measured barriers, unlike conventional ML approaches.

Main Methods:

  • Developed a reformulated ML approach focused on finding reactions with specific target barrier values from a prespecified set.
  • Applied the method to toxicologically and synthetically relevant datasets, including aza-Michael addition and transition-metal-catalyzed dihydrogen activation.
  • Evaluated performance on incomplete datasets for E2 and SN2 reactions, comparing data requirements with conventional ML methods.

Main Results:

  • The reformulated ML approach requires significantly fewer data points (tens of barriers) compared to conventional methods (thousands).
  • Achieved excellent results on aza-Michael addition and dihydrogen activation datasets, using fewer than 20 density functional theory (DFT) barriers.
  • Demonstrated effectiveness even with incomplete datasets (e.g., 74% missing barriers for E2 reactions).

Conclusions:

  • The reformulated ML approach drastically reduces data requirements for accurate reaction barrier prediction.
  • This data-efficient method facilitates rapid selection of reactions with specific activation barriers, applicable to catalyst optimization and rational chemical design.
  • A case study successfully guided dihydrogen activation catalyst optimization, identifying a target reaction within 1 kcal mol⁻¹ using only 12 DFT calculations.