Skip to content

Releases: rinikerlab/DASH-tree

DASH-Tree_JCIM_published

09 Oct 18:40
1100c80
Compare
Choose a tag to compare

DASH Tree

This release corresponds to the code used to generate the results of the submission of the publication:

DASH: Dynamic Attention-Based Substructure Hierarchy for Partial Charge Assignment

Marc T. Lehner, Paul Katzberger, Niels Maeder, Carl C.G. Schiebroek, Jakob Teetz, Gregory A. Landrum, and Sereina Riniker
Journal of Chemical Information and Modeling 2023 63 (19), 6014-6028
DOI: 10.1021/acs.jcim.3c00800

Abstract

We present a robust and computationally efficient approach for assigning partial charges of atoms in
molecules. The method is based on a hierarchical tree constructed from attention values extracted
from a graph neural network (GNN), which was trained to predict atomic partial charges from accurate
quantum-mechanical (QM) calculations. The resulting dynamic attention-based substructure hierarchy
(DASH) approach provides fast assignment of partial charges with the same accuracy as the GNN itself,
is software-independent, and can easily be integrated in existing parametrization pipelines as shown for
the Open force field (OpenFF). The implementation of the DASH workflow, the final DASH tree, and
the training set are available as open source / open data from public repositories.

DASH-Tree arXiv submission

26 May 14:38
fa02269
Compare
Choose a tag to compare

DASH Tree

This release corresponds to the code used to generate the results of the submission of the publication:

DASH: Dynamic Attention-Based Substructure Hierarchy for Partial Charge Assignment

Marc T. Lehner, Paul Katzberger, Niels Maeder, Carl C. G. Schiebroek, Jakob Teetz, Gregory A. Landrum and Sereina Riniker
https://doi.org/10.48550/arXiv.2305.15981

Abstract

We present a robust and computationally efficient approach for assigning partial charges of atoms in
molecules. The method is based on a hierarchical tree constructed from attention values extracted
from a graph neural network (GNN), which was trained to predict atomic partial charges from accurate
quantum-mechanical (QM) calculations. The resulting dynamic attention-based substructure hierarchy
(DASH) approach provides fast assignment of partial charges with the same accuracy as the GNN itself,
is software-independent, and can easily be integrated in existing parametrization pipelines as shown for
the Open force field (OpenFF). The implementation of the DASH workflow, the final DASH tree, and
the training set are available as open source / open data from public repositories.