GAME-Net

This is the repository of the framework related to the work "Fast Evaluation of the Adsorption Energy of Organic Molecules on Metals via Graph Neural Networks", preprint here, where we introduce GAME-Net (Graph-based Adsorption on Metal Energy-neural Network), a graph neural network developed for the fast prediction of the DFT ground state energy of the following systems:

• Closed-shell molecules containing C, H, O, N and S.
• Mentioned molecules adsorbed on 14 transition metals: Ag, Au, Cd, Co, Cu, Fe, Ir, Ni, Os, Pd, Pt, Rh, Ru, and Zn.

The framework and related model have been built with PyTorch, PyTorch Geometric and Ray Tune.