This directory holds notebooks that illustrate how to use the HydroNet Challenge Data.
See https://exalearn.github.io/hydronet/ for more details.
Install the environment needed for these notebooks with conda env create --file environment.yml --force
The ttm
directory contains code needed to compute the energy of water clusters,
which is needed for Challenge 3.
Download the data from our Globus endpoint to the ./data/output
folder.
The ./get-data.sh
script automates the download process if your computer has Globus Connect installed.
Each of the subdirectories hold notebooks and scripts that give example solutions to some of the challenge problems or tutorial examples for working with HydroNet data.
If you find this work useful, please cite our publication: Sutanay Choudhury, Jenna A. Bilbrey, Logan Ward, Sotiris S. Xantheas, Ian Foster, Joseph P. Heindel, Ben Blaiszik, Marcus E. Schwarting, "HydroNet: Benchmark Tasks for Preserving Intermolecular Interactions and Structural Motifs in Predictive and Generative Models for Molecular Data", 2020, Machine Learning and the Physical Sciences Workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS).
@article{choudhury2020hydronet,
author = {Sutanay Choudhury and
Jenna A. Bilbrey and
Logan T. Ward and
Sotiris S. Xantheas and
Ian T. Foster and
Joseph P. Heindel and
Ben Blaiszik and
Marcus E. Schwarting},
title = {HydroNet: Benchmark Tasks for Preserving Intermolecular Interactions
and Structural Motifs in Predictive and Generative Models for Molecular
Data},
journal = {Machine Learning and the Physical Sciences Workshop at the 34th
Conference on Neural Information Processing Systems (NeurIPS)},
volume = {abs/2012.00131},
year = {2020},
url = {https://arxiv.org/abs/2012.00131},
archivePrefix = {arXiv},
}