Recommended by

Indexed by

Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks

Daniel Schwalbe-Koda1, Aik Rui Tan1, Rafael Gómez-Bombarelli1*

1 Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States

* Corresponding authors emails: rafagb@mit.edu
DOI10.24435/materialscloud:2w-6h [version v1]

Publication date: Jul 20, 2021

How to cite this record

Daniel Schwalbe-Koda, Aik Rui Tan, Rafael Gómez-Bombarelli, Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks, Materials Cloud Archive 2021.115 (2021), doi: 10.24435/materialscloud:2w-6h.


Neural network (NN) force fields can predict potential energy surfaces with high accuracy and speed compared to electronic structure methods typically used to generate their training data. However, NN predictions are well-defined only for points close to the training domains, and may exhibit poor results during extrapolation. Uncertainty quantification methods can detect geometries for which predicted errors are high, but sampling regions of high uncertainty requires a thorough exploration of the phase space, often using expensive simulations. Our work uses automatic differentiation to sample atomistic configurations by balancing thermodynamic accessibility and uncertainty quantification without using molecular dynamics simulations. This dataset provides the atomistic data used to train the NN potentials for the ammonia, alanine dipeptide, and zeolite-molecule systems. For all materials, geometries, energies, and forces are provided. The ammonia and zeolite systems were computed using density functional theory calculations, while the alanine dipeptide dataset was generated using molecular dynamics simulations with the OPLS force field.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
268.9 MiB Atomistic data used to train the neural network potentials
3.6 KiB Description of the files, data columns, and units


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

External references

Preprint (Preprint where the data is discussed)
Journal reference (Paper in which the data is discussed)
D. Schwalbe-Koda, A.R. Tan, R. Gómez-Bombarelli. Nat. Commun. (accepted) (2021)


molecular dynamics density functional theory machine learning zeolites

Version history:

2021.115 (version v1) [This version] Jul 20, 2021 DOI10.24435/materialscloud:2w-6h