GEOM, energy-annotated molecular conformations for property prediction and molecular generation

Machine learning (ML) outperforms traditional approaches in many molecular design tasks. ML models usually predict molecular properties from a 2D chemical graph or a single 3D structure, but neither of these representations accounts for the ensemble of 3D conformers that are accessible to a molecule. Property prediction could be improved by using conformer ensembles as input, but there is no large-scale dataset that contains graphs annotated with accurate conformers and experimental data. Here we use advanced sampling and semi-empirical density functional theory (DFT) to generate 37 million molecular conformations for over 450,000 molecules. The Geometric Ensemble Of Molecules (GEOM) dataset contains…

• NA
  National Aeronautics and Space Administration
• NE
  National Energy Research Scientific Computing Center
• DA
  Defense Advanced Research Projects Agency

  Award: HR00111920025
• DO
  Division of Chemistry
• LB
  Lawrence Berkeley National Laboratory
• DO
  Division of Materials Sciences and Engineering