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

Improving Translational Accuracy02:07

Improving Translational Accuracy

15.2K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.2K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.7K
3.7K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

361
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...
361
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

46.3K
VSEPR Theory for Determination of Electron Pair Geometries
46.3K
Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

1.5K
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
1.5K

You might also read

Related Articles

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

Sort by
Same author

Alchemical diastereomers from antisymmetric alchemical perturbations.

The Journal of chemical physics·2025
Same author

Hammett-Inspired Product Baseline for Data-Efficient Δ-ML in Chemical Space.

Journal of chemical theory and computation·2025
Same author

Antisymmetry rules of response properties in certain chemical spaces.

The Journal of chemical physics·2025
Same author

Crash testing machine learning force fields for molecules, materials, and interfaces: model analysis in the TEA Challenge 2023.

Chemical science·2025
Same author

Crash testing machine learning force fields for molecules, materials, and interfaces: molecular dynamics in the TEA challenge 2023.

Chemical science·2025
Same author

Adapting hybrid density functionals with machine learning.

Science advances·2025

Related Experiment Video

Updated: Feb 22, 2026

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

3.8K

Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.

Felix A Faber1, Luke Hutchison2, Bing Huang1

  • 1Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials, Department of Chemistry, University of Basel , Klingelbergstrasse 80, CH-4056 Basel, Switzerland.

Journal of Chemical Theory and Computation
|September 20, 2017
PubMed
Summary

Choosing the right molecular representations and regressors significantly improves machine learning (ML) models for predicting organic molecule properties. These optimized ML models can achieve accuracy comparable to or exceeding hybrid density functional theory (DFT) calculations.

Related Experiment Videos

Last Updated: Feb 22, 2026

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

3.8K

Area of Science:

  • Computational Chemistry
  • Materials Science
  • Machine Learning

Background:

  • Accurate prediction of molecular properties is crucial for drug discovery and materials design.
  • Traditional quantum mechanical methods, like density functional theory (DFT), can be computationally expensive.
  • Machine learning (ML) offers a faster alternative for predicting molecular properties.

Purpose of the Study:

  • To investigate the impact of different molecular representations and regression models on the accuracy of ML models for 13 electronic ground-state properties of organic molecules.
  • To identify optimal combinations of regressors and representations for specific molecular properties.
  • To compare the accuracy of ML models against DFT calculations and experimental data.

Main Methods:

  • Utilized the QM9 database containing molecular structures and properties calculated at the hybrid DFT level.
  • Evaluated various molecular representations, including Coulomb matrix, bag of bonds, BAML, ECFP4, molecular graphs (MG), and distribution-based variants (HD, HDA/MARAD, HDAD).
  • Assessed multiple regressors: Bayesian ridge regression (BR), elastic net (EN), random forest (RF), kernel ridge regression (KRR), graph convolutions (GC), and gated graph networks (GG).

Main Results:

  • Out-of-sample errors were highly dependent on the chosen representation, regressor, and molecular property.
  • Molecular graphs (MG) with graph convolutions (GC) excelled for electronic properties (HOMO/LUMO, dipole moment, polarizability).
  • Distribution-based representations like HDAD combined with KRR showed superior performance for energetic properties (atomization energies, vibrational energies).

Conclusions:

  • Optimized ML models demonstrated prediction errors comparable to or better than hybrid DFT (B3LYP) and close to chemical accuracy.
  • ML model predictions were found to deviate less from DFT than DFT deviates from experimental values for all properties studied.
  • The findings suggest that ML models, particularly with appropriate representations and regressors, hold significant potential for accurate and efficient molecular property prediction.