Related Experiment Video
Updated: Jun 17, 2025
08:04
Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids
Published on: May 27, 2020
8.4K
When Do Quantum Mechanical Descriptors Help Graph Neural Networks to Predict Chemical Properties?
Shih-Cheng Li1,2, Haoyang Wu1, Angiras Menon1
1Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
Journal of the American Chemical Society
|August 6, 2024
Summary
Quantum mechanical (QM) descriptors enhance deep graph neural networks for molecular property prediction, especially with small datasets. Strategic use improves generalizability and efficiency in drug and material design.
Area of Science:
- Computational chemistry
- Machine learning
- Materials science
Background:
- Deep graph neural networks (GNNs) predict chemical properties but struggle with extrapolation.
- Quantum mechanical (QM) descriptors can improve GNN generalizability.
- QM calculations are computationally intensive.
Purpose of the Study:
- Investigate the impact of QM descriptors on GNN performance for chemical property prediction.
- Determine when QM descriptors benefit GNNs for molecular property prediction.
- Provide guidelines for integrating QM descriptors into GNN workflows.
Main Methods:
- Systematic analysis of atom, bond, and molecular QM descriptors.
- Evaluation of directed message passing neural networks (D-MPNNs).
- Prediction of 16 molecular properties across various tasks and dataset sizes.
Main Results:
- QM descriptors primarily benefit D-MPNNs on small datasets with high target correlation and accurate computation.
- Using QM descriptors can be costly without benefit or introduce noise, degrading performance.
- Strategic integration offers physics-informed, data-efficient modeling.
Conclusions:
- QM descriptors enhance GNNs when used judiciously, particularly for small datasets.
- Guidelines and tools are provided for effective QM descriptor integration.
- This approach streamlines drug and material design through improved chemical property prediction.
More Related Videos
Related Concept Videos
02:27Predicting Molecular Geometry
34.2K
VSEPR Theory for Determination of Electron Pair Geometries
34.2K
01:27Inductive Effects on Chemical Shift: Overview
1.1K
The protons in unsubstituted alkanes are strongly shielded with chemical shifts below 1.8 ppm. Methine, methylene, and methyl protons appear at approximately 1.7, 1.2 and 0.7 ppm, while the proton signal from methane appears at 0.23 ppm. An electronegative substituent, such as chlorine, withdraws the electron density from the protons, increasing their chemical shift. Progressive substitution of the hydrogens in methane by chlorine shifts the proton signals increasingly downfield, to 3.05 ppm in...
1.1K
02:00Molecular Models
38.1K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
38.1K
01:14π Electron Effects on Chemical Shift: Aromatic and Antiaromatic Compounds
1.2K
In aromatic compounds, such as benzene, the circulation of (4n + 2) π-electrons sets up a diamagnetic or diatropic ring current around the perimeter of the molecule. This current induces a magnetic field that opposes the external field inside the ring and reinforces it on the outside. The protons in benzene are deshielded and exhibit high chemical shifts in the range 6.5–8.5 ppm. The shielding effect at the center of the ring is evident in complex aromatic molecules, such as...
1.2K
01:26Physical Properties of Amines
3.0K
Amines with low molecular weight are usually gaseous at room temperature, while those with high molecular weight are liquid or solids in nature. Usually, low molecular weight amines have a rotten fish-like smell. Diamines typically have a pungent smell. For instance, cadaverine and putrescine, depicted in Figure 1, are two molecules responsible for decaying tissue.
3.0K
01:192D NMR: Heteronuclear Single-Quantum Correlation Spectroscopy (HSQC)
674
Heteronuclear single-quantum correlation spectroscopy (HSQC) is a 2D NMR technique that reveals one-bond correlations between hydrogen and a heteronucleus. The HSQC experiment is similar to the heteronuclear correlation experiment (HETCOR) but is more sensitive. In the HSQC spectrum, the proton chemical shift is plotted on the horizontal F2 axis, while the 13C chemical shift is plotted on the vertical F1 axis. The corresponding proton and 13C spectra are also shown. The HSQC contour plot does...
674