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 Molecular Geometry02:27

Predicting Molecular Geometry

34.0K
VSEPR Theory for Determination of Electron Pair Geometries
34.0K
¹H NMR of Conformationally Flexible Molecules: Temporal Resolution00:52

¹H NMR of Conformationally Flexible Molecules: Temporal Resolution

796
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...
796
Atomic Absorption Spectroscopy: Atomization Methods01:25

Atomic Absorption Spectroscopy: Atomization Methods

342
Atomic Absorption Spectroscopy (AAS) atomizes samples through flame atomization or electrothermal atomization. Flame atomization typically involves a nebulizer and spray chamber assembly to combine the sample with a fuel–oxidant mixture, creating a fine aerosol mist that enters a burner. Typically, the fuel and oxidant are combined in an approximately stoichiometric ratio. However, for atoms that are easily oxidized, a fuel-rich mixture may be more advantageous. Only about 5% of the...
342
Hybridization of Atomic Orbitals I03:24

Hybridization of Atomic Orbitals I

46.2K
The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...
46.2K
The Quantum-Mechanical Model of an Atom02:45

The Quantum-Mechanical Model of an Atom

41.8K
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 expression for the energy and, thus, the Rydberg formula governing hydrogen spectra.
41.8K
¹H NMR of Conformationally Flexible Molecules: Variable-Temperature NMR01:15

¹H NMR of Conformationally Flexible Molecules: Variable-Temperature NMR

1.0K
The axial and equatorial protons in cyclohexane can be distinguished by performing a variable-temperature NMR experiment. In this process, except for one proton, the remaining eleven protons are replaced by deuterium. The deuterium substitution avoids the possible peak splitting caused by the spin-spin coupling between the adjacent protons. The remaining proton flips between the axial and equatorial positions.
1.0K

You might also read

Related Articles

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

Sort by
Same author

Accurate density functional theory for noncovalent interactions in charged systems.

Science advances·2026
Same author

Machine-Learned Electrostatic Potentials for Accurate Hydration Free Energy Calculations.

Journal of chemical theory and computation·2026
Same author

aims-PAX: Parallel Active Exploration Enables Expedited Construction of Machine Learning Force Fields for Molecules and Materials.

Journal of chemical information and modeling·2026
Same author

Correction to "Noncovalent Interactions in Density Functional Theory: All the Charge Density We Do Not See".

Journal of the American Chemical Society·2026
Same author

A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data.

Journal of chemical information and modeling·2026
Same author

Improving the Stability and Transferability of Effective ADMET Models by Adding Quantum Mechanical Descriptors.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: May 25, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K

Pretraining graph transformers with atom-in-a-molecule quantum properties for improved ADMET modeling.

Alessio Fallani1,2, Ramil Nugmanov3, Jose Arjona-Medina2

  • 1Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg , Luxembourg.

Journal of Cheminformatics
|February 27, 2025
PubMed
Summary

Pretraining Graph Transformers with atom-level quantum mechanics improves drug ADMET property prediction. This approach offers better molecular representations and performance on large pharmaceutical datasets compared to other pretraining strategies.

More Related Videos

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

308
Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps
09:30

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

1.2K

Related Experiment Videos

Last Updated: May 25, 2025

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.6K
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

308
Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps
09:30

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

1.2K

Area of Science:

  • Computational chemistry and cheminformatics
  • Machine learning for drug discovery
  • Molecular graph representation learning

Background:

  • Accurate prediction of Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties is crucial for drug development.
  • Graph Transformer architectures show promise for molecular property prediction.
  • Effective pretraining strategies are essential for optimizing Graph Transformer performance on complex biological tasks.

Purpose of the Study:

  • To evaluate the impact of different pretraining strategies on Graph Transformer models for ADMET property prediction.
  • To compare pretraining with atom-level quantum-mechanical features, molecular quantum properties (HOMO-LUMO gap), and self-supervised atom masking.
  • To analyze the learned representations and their correlation with predictive performance.

Main Methods:

  • Pretraining Graph Transformer architectures using three distinct feature sets: atom-level quantum mechanics, HOMO-LUMO gap, and atom masking.
  • Fine-tuning pretrained models on Therapeutic Data Commons ADMET datasets.
  • Analyzing latent representations using techniques like Attention Rollout Matrix.
  • Evaluating model performance on public ADMET benchmarks and a large-scale internal dataset for microsomal clearance.

Main Results:

  • Models pretrained with atomic quantum mechanical properties generally yield superior ADMET prediction performance.
  • Supervised pretraining strategies effectively preserve pretraining information after fine-tuning.
  • Atomic quantum mechanical pretraining captures low-frequency Laplacian eigenmodes and enhances atomic environment representations.
  • Performance on large pharmaceutical datasets can differ significantly between models with similar public benchmark performance, particularly for masking and atom-level quantum property pretraining.

Conclusions:

  • Pretraining Graph Transformers with atom-level quantum-mechanical features is a highly effective strategy for modeling drug-like compound ADMET properties.
  • The choice of pretraining significantly influences the learned molecular representations and downstream task performance.
  • Analysis of latent representations and attention mechanisms provides valuable insights for guiding pretraining strategy selection in drug discovery.