Shape-Based Generative Modeling for de Novo Drug Design

J Chem Inf Model. 2019 Mar 25;59(3):1205-1214. doi: 10.1021/acs.jcim.8b00706. Epub 2019 Feb 28.


In this work, we propose a machine learning approach to generate novel molecules starting from a seed compound, its three-dimensional (3D) shape, and its pharmacophoric features. The pipeline draws inspiration from generative models used in image analysis and represents a first example of the de novo design of lead-like molecules guided by shape-based features. A variational autoencoder is used to perturb the 3D representation of a compound, followed by a system of convolutional and recurrent neural networks that generate a sequence of SMILES tokens. The generative design of novel scaffolds and functional groups can cover unexplored regions of chemical space that still possess lead-like properties.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Drug Design
  • Hydrogen Bonding
  • Hydrophobic and Hydrophilic Interactions
  • Machine Learning*
  • Models, Molecular
  • Molecular Conformation
  • Molecular Structure
  • Pharmaceutical Preparations / chemistry*
  • Quantitative Structure-Activity Relationship


  • Pharmaceutical Preparations