Recommended by

Indexed by

eQM7: a dataset for small molecules with Foster-Boys centers

Maarten Cools-Ceuppens1*, Joni Dambre2, Toon Verstraelen1*

1 Ghent University, Center for Molecular Modeling, Technologiepark-Zwijnaarde 46, Gent, B-9052, Belgium

2 Ghent University - imec, IDLab, Electronics and Information Systems Department, Technologiepark-Zwijnaarde 126, Gent, B-9052, Belgium

* Corresponding authors emails: maarten.coolsceuppens@ugent.be, toon.verstraelen@ugent.be
DOI10.24435/materialscloud:66-9j [version v1]

Publication date: Sep 27, 2021

How to cite this record

Maarten Cools-Ceuppens, Joni Dambre, Toon Verstraelen, eQM7: a dataset for small molecules with Foster-Boys centers, Materials Cloud Archive 2021.154 (2021), doi: 10.24435/materialscloud:66-9j.


The electron QM7 (eQM7) dataset is created with the purpose of training and validating polarizable (machine learning) force fields on non-equilibrium configurations of small molecules. It contains 6868 molecules with hydrogen, carbon, nitrogen and oxygen. For each molecule, 500 perturbations are constructed using normal mode sampling, torsion sampling, dimer sampling and homogeneous electric fields. Energies, forces and Foster-Boys centers are computed using density functional theory (DFT) with the PBE0 functional, Aug-cc-pVTZ basis set in the ab-initio quantum chemistry code Psi4.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
2.7 GiB The eQM7 dataset. For all 6868 molecules, four extended XYZ files are stored, containing all 500 perturbations per molecule. Read the README file for more information.
91.3 MiB An archive containing the hessians and optimized geometries for each of the 6868 molecules in the eQM7 dataset.
5.1 KiB An archive containing the hessians and optimized geometries of the reference molecules for the eMLP.
3.8 KiB Detailed description of the dataset and all the files.


Files and data are licensed under the terms of the following license: Creative Commons Attribution Share Alike 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference
M. Cools-Ceuppens, J. Dambre, T. Verstraelen (in preparation)


machine learning density-functional theory Foster-Boys centers

Version history:

2021.154 (version v1) [This version] Sep 27, 2021 DOI10.24435/materialscloud:66-9j