Molecular Geometry Prediction using a Deep Generative Graph Neural Network

@article{Mansimov2019MolecularGP,
  title={Molecular Geometry Prediction using a Deep Generative Graph Neural Network},
  author={Elman Mansimov and O. Mahmood and Seokho Kang and Kyunghyun Cho},
  journal={Scientific Reports},
  year={2019},
  volume={9}
}
A molecule’s geometry, also known as conformation, is one of a molecule’s most important properties, determining the reactions it participates in, the bonds it forms, and the interactions it has with other molecules. Conventional conformation generation methods minimize hand-designed molecular force field energy functions that are often not well correlated with the true energy function of a molecule observed in nature. They generate geometrically diverse sets of conformations, some of which are… Expand
22 Citations
3DMolNet: A Generative Network for Molecular Structures
  • 5
  • PDF
Deep Multi-attribute Graph Representation Learning on Protein Structures
  • PDF
Auto-Encoding Molecular Conformations
  • PDF
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
  • 1
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 40 REFERENCES
Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation
  • 101
Neural Message Passing for Quantum Chemistry
  • 1,858
  • PDF
Small-Molecule 3D Structure Prediction Using Open Crystallography Data
  • 13
Benchmarking Commercial Conformer Ensemble Generators.
  • 35
Molecular graph convolutions: moving beyond fingerprints
  • 586
  • PDF
The Graph Neural Network Model
  • 2,023
  • PDF
Freely Available Conformer Generation Methods: How Good Are They?
  • 110
Adam: A Method for Stochastic Optimization
  • 63,253
  • PDF
Quantum chemistry structures and properties of 134 kilo molecules
  • 456
  • PDF
...
1
2
3
4
...