Repository associated with the manuscript “Boosting Graph Neural Networks with Molecular Mechanics: A Case Study of Sigma Profile Prediction”.
Citation:
https://doi.org/10.1021/acs.jctc.3c01003
Dinis O. Abranches, Edward J. Maginn, Yamil J. Colón. "Boosting Graph Neural Networks with Molecular Mechanics: A Case Study of Sigma Profile Prediction." J. Chem. Theory Comput. 2023, 19 (24), 9318– 9328

Repository structure:

• Main
  • Databases: graph and property database files.
  • HyperparameterSearch: hyperparameter tuning results of each GCN model.
  • Models: GCN models, train/val/test splits of final fitting, and CNN-related files.
  • Python: main Python code used throughout the manuscript. Files are numbered in chronological order. Details and instructions included. A Jupyer Notebook is also included, allowing users to predict sigma profiles by providing a SMILES string.