COmprehensive Machine-learning Potential (COMP6) Benchmark Suite

This repository contains the COMP6 benchmark for evaluating the extensibility of machine-learning based molecular potentials.

If you use the COMP6 benchmark please cite this paper:

Justin S. Smith, Ben Nebgen, Nicholas Lubbers, Olexandr Isayev, Adrian E. Roitberg. Less is more: sampling chemical space with active learning. arXiv, 2018, DOI: [arXiv:1801.09319] (https://arxiv.org/abs/1801.09319)

Usage

Please read the README.md in the repository linked below for instructions on how to extract the COMP6 HDF5 (extention *.h5) files. https://github.com/isayev/ANI1_dataset

The following paper contains a description of the file format: https://www.nature.com/articles/sdata2017193

##Current Benchmark Results: | Test |

First Header	Second Header
Content Cell	Content Cell
Content Cell	Content Cell