Corpus ID: 224713572

Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models

@article{Ragoza2020LearningAC,
  title={Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models},
  author={Matthew Ragoza and T. Masuda and D. Koes},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.08687}
}
  • Matthew Ragoza, T. Masuda, D. Koes
  • Published 2020
  • Computer Science, Biology
  • ArXiv
  • Machine learning methods in drug discovery have primarily focused on virtual screening of molecular libraries using discriminative models. Generative models are an entirely different approach to drug discovery that learn to represent and optimize molecules in a continuous latent space. These methods have already been applied with increasing success to the generation of two dimensional molecules as SMILES strings and molecular graphs. In this work, we describe deep generative models for three… CONTINUE READING
    2 Citations

    Figures from this paper

    References

    SHOWING 1-10 OF 39 REFERENCES
    Shape-Based Generative Modeling for de Novo Drug Design
    • 37
    • PDF
    Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
    • 863
    • PDF
    MolGAN: An implicit generative model for small molecular graphs
    • 253
    • PDF
    Generating equilibrium molecules with deep neural networks
    • 12
    • PDF
    Junction Tree Variational Autoencoder for Molecular Graph Generation
    • 331
    • PDF
    Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
    • 71
    • PDF
    Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
    • 92
    • PDF
    AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
    • 261
    • PDF
    Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation
    • 11