3DReact: geometric deep learning for chemical reactions
JSON Export
{
"id": "2403",
"updated": "2024-10-15T15:51:42.635997+00:00",
"metadata": {
"version": 1,
"contributors": [
{
"givennames": "Puck",
"affiliations": [
"Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "puck.vangerwen@epfl.ch",
"familyname": "van Gerwen"
},
{
"givennames": "Ksenia",
"affiliations": [
"Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland",
"National Centre for Computational Design and Discovery of Novel Materials (MARVEL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "ksenia.briling@epfl.ch",
"familyname": "Briling"
},
{
"givennames": "Charlotte",
"affiliations": [
"Learning & Adaptive Systems Group, Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "Charlotte.Bunne@epfl.ch",
"familyname": "Bunne"
},
{
"givennames": "Vignesh Ram",
"affiliations": [
"Learning & Adaptive Systems Group, Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "vsomnath@inf.ethz.ch",
"familyname": "Somnath"
},
{
"givennames": "Ruben",
"affiliations": [
"Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "ruben.laplazasolanas@epfl.ch",
"familyname": "Laplaza"
},
{
"givennames": "Andreas",
"affiliations": [
"Learning & Adaptive Systems Group, Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "krausea@ethz.ch",
"familyname": "Krause"
},
{
"givennames": "Clemence",
"affiliations": [
"Laboratory for Computational Molecular Design, Institute of Chemical Sciences and Engineering, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland",
"National Centre for Competence in Research \u2212 Catalysis (NCCR-Catalysis), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland",
"National Centre for Computational Design and Discovery of Novel Materials (MARVEL), \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, 1015 Lausanne, Switzerland"
],
"email": "clemence.corminboeuf@epfl.ch",
"familyname": "Corminboeuf"
}
],
"title": "3DReact: geometric deep learning for chemical reactions",
"_oai": {
"id": "oai:materialscloud.org:2403"
},
"keywords": [
"reaction barriers",
"geometric deep learning",
"equivariant neural networks"
],
"publication_date": "Oct 15, 2024, 17:51:42",
"_files": [
{
"key": "3DReact.tar.gz",
"description": "See README",
"checksum": "md5:b3f1d58d62efcedeb8aebaab749a7c36",
"size": 418646342
},
{
"key": "README.md",
"description": "README.md",
"checksum": "md5:28d4cf559ff4074788b36a7e09b17ba8",
"size": 1769
},
{
"key": "README.txt",
"description": "README.txt",
"checksum": "md5:28d4cf559ff4074788b36a7e09b17ba8",
"size": 1769
}
],
"references": [
{
"comment": "Paper that uses the data",
"doi": "10.1021/acs.jcim.4c00104",
"citation": "P. van Gerwen, K. R. Briling, C. Bunne, V. R. Somnath, R. Laplaza, A. Krause, C. Corminboeuf, J. Chem. Inf. Model. 64, 5771-5785 (2024)",
"type": "Journal reference"
},
{
"comment": "Code and results that use the data",
"doi": "https://doi.org/10.5281/zenodo.12744941",
"citation": "K. Briling, P. van Gerwen, lcmd-epfl/EquiReact: v1.0.0 (2024)",
"url": "https://github.com/lcmd-epfl/EquiReact",
"type": "Software"
}
],
"description": "Geometric deep learning models, which incorporate the relevant molecular symmetries within the neural network architecture, have considerably improved the accuracy and data efficiency of predictions of molecular properties. Building on this success, we introduce 3DREACT, a geometric deep learning model to predict reaction properties from three-dimensional structures of reactants and products. We demonstrate that the invariant version of the model is sufficient for existing reaction data sets. We illustrate its competitive performance on the prediction of activation barriers on the GDB7-22-TS, Cyclo-23-TS, and Proparg-21-TS data sets in different atom-mapping regimes. We show that, compared to existing models for reaction property prediction, 3DREACT offers a flexible framework that exploits atom- mapping information, if available, as well as geometries of reactants and products (in an invariant or equivariant fashion). Accordingly, it performs systematically well across different data sets, atom-mapping regimes, as well as both interpolation and extrapolation tasks.",
"status": "published",
"license": "Materials Cloud non-exclusive license to distribute v1.0",
"conceptrecid": "2402",
"is_last": true,
"mcid": "2024.161",
"edited_by": 576,
"id": "2403",
"owner": 1011,
"license_addendum": null,
"doi": "10.24435/materialscloud:xd-ef"
},
"revision": 3,
"created": "2024-10-15T08:07:16.392506+00:00"
}