Published March 18, 2023 | Version 0.2.0
Software Open

GAME-Net

  • 1. ICIQ

Description

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.

Notes

Includes a minimal version of the FG- and BM-datasets. Added in version 0.2.0: Datasets of Co and Fe; Open Catalyist Benchmark.

Files

Files (45.8 MB)

Name Size Download all
md5:c90306ba5fa700803d83700323fb1a33
45.8 MB Download

Additional details

Related works

Is described by
Preprint: 10.26434/chemrxiv-2022-m719x (DOI)