Saved in:
Bibliographic Details
Main Authors: Gabellini, Cristian, Shenoy, Nikhil, Thaler, Stephan, Canturk, Semih, McNeela, Daniel, Beaini, Dominique, Bronstein, Michael, Tossou, Prudencio
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.19629
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913591151558656
author Gabellini, Cristian
Shenoy, Nikhil
Thaler, Stephan
Canturk, Semih
McNeela, Daniel
Beaini, Dominique
Bronstein, Michael
Tossou, Prudencio
author_facet Gabellini, Cristian
Shenoy, Nikhil
Thaler, Stephan
Canturk, Semih
McNeela, Daniel
Beaini, Dominique
Bronstein, Michael
Tossou, Prudencio
contents Machine Learning Interatomic Potentials (MLIPs) are a highly promising alternative to force-fields for molecular dynamics (MD) simulations, offering precise and rapid energy and force calculations. However, Quantum-Mechanical (QM) datasets, crucial for MLIPs, are fragmented across various repositories, hindering accessibility and model development. We introduce the openQDC package, consolidating 37 QM datasets from over 250 quantum methods and 400 million geometries into a single, accessible resource. These datasets are meticulously preprocessed, and standardized for MLIP training, covering a wide range of chemical elements and interactions relevant in organic chemistry. OpenQDC includes tools for normalization and integration, easily accessible via Python. Experiments with well-known architectures like SchNet, TorchMD-Net, and DimeNet reveal challenges for those architectures and constitute a leaderboard to accelerate benchmarking and guide novel algorithms development. Continuously adding datasets to OpenQDC will democratize QM dataset access, foster more collaboration and innovation, enhance MLIP development, and support their adoption in the MD field.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OpenQDC: Open Quantum Data Commons
Gabellini, Cristian
Shenoy, Nikhil
Thaler, Stephan
Canturk, Semih
McNeela, Daniel
Beaini, Dominique
Bronstein, Michael
Tossou, Prudencio
Chemical Physics
Machine Learning
Machine Learning Interatomic Potentials (MLIPs) are a highly promising alternative to force-fields for molecular dynamics (MD) simulations, offering precise and rapid energy and force calculations. However, Quantum-Mechanical (QM) datasets, crucial for MLIPs, are fragmented across various repositories, hindering accessibility and model development. We introduce the openQDC package, consolidating 37 QM datasets from over 250 quantum methods and 400 million geometries into a single, accessible resource. These datasets are meticulously preprocessed, and standardized for MLIP training, covering a wide range of chemical elements and interactions relevant in organic chemistry. OpenQDC includes tools for normalization and integration, easily accessible via Python. Experiments with well-known architectures like SchNet, TorchMD-Net, and DimeNet reveal challenges for those architectures and constitute a leaderboard to accelerate benchmarking and guide novel algorithms development. Continuously adding datasets to OpenQDC will democratize QM dataset access, foster more collaboration and innovation, enhance MLIP development, and support their adoption in the MD field.
title OpenQDC: Open Quantum Data Commons
topic Chemical Physics
Machine Learning
url https://arxiv.org/abs/2411.19629