Inorganic–organic domain dataset

The integrated inorganic–organic domain dataset used to train the MACE-Osaka24 models—composed of the inorganic MPtrj dataset and the organic SPICE, QMug, water clusters, and Tripeptides (OFF23) datasets was generated using via the Total Energy Alignment (TEA) method. If you use any of these datasets, please cite the following papers.@article{deng2023chgnet, title={CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling}, author={Bowen Deng and Peichen Zhong and KyuJung Jun and Janosh Riebesell and Kevin Han and Christopher J. Bartel and Gerbrand Ceder}, year={2023}, eprint={2302.14231}, archivePrefix={arXiv}, primaryClass={cond-mat.mtrl-sci}}<br>@misc{kovacs2023maceoff23, title={MACE-OFF23: Transferable Machine Learning Force Fields for Organic Molecules}, author={Dávid Péter Kovács and J. Harry Moore and Nicholas J. Browning and Ilyes Batatia and Joshua T. Horton and Venkat Kapil and William C. Witt and Ioan-Bogdan Magdău and Daniel J. Cole and Gábor Csányi}, year={2023}, eprint={2312.15211}, archivePrefix={arXiv},}<br>@article{eastman2023spice, title={Spice, a dataset of drug-like molecules and peptides for training machine learning potentials}, author={Eastman, Peter and Behara, Pavan Kumar and Dotson, David L and Galvelis, Raimondas and Herr, John E and Horton, Josh T and Mao, Yuezhi and Chodera, John D and Pritchard, Benjamin P and Wang, Yuanqing and others}, journal={Scientific Data}, volume={10}, number={1}, pages={11}, year={2023}, publisher={Nature Publishing Group UK London}}<br>@article{donchev2021quantum, title={Quantum chemical benchmark databases of gold-standard dimer interaction energies}, author={Donchev, Alexander G and Taube, Andrew G and Decolvenaere, Elizabeth and Hargus, Cory and McGibbon, Robert T and Law, Ka-Hei and Gregersen, Brent A and Li, Je-Luen and Palmo, Kim and Siva, Karthik and others}, journal={Scientific data}, volume={8}, number={1}, pages={55}, year={2021}, publisher={Nature Publishing Group UK London}}<br>@article{isert2022qmugs, title={QMugs, quantum mechanical properties of drug-like molecules}, author={Isert, Clemens and Atz, Kenneth and Jim{\'e}nez-Luna, Jos{\'e} and Schneider, Gisbert}, journal={Scientific Data}, volume={9}, number={1}, pages={273}, year={2022}, publisher={Nature Publishing Group UK London}}<br>@misc{shiota2024taming, title={Taming Multi-Domain, -Fidelity Data: Towards Foundation Models for Atomistic Scale Simulations}, author={Tomoya Shiota and Kenji Ishihara and Tuan Minh Do and Toshio Mori and Wataru Mizukami}, year={2024}, eprint={2412.13088}, archivePrefix={arXiv}, primaryClass={physics.chem-ph}}用于训练MACE-Osaka24模型的无机-有机集成域数据集，由无机域的MPtrj数据集，以及有机域的SPICE、QMug、水团簇和三肽（OFF23）数据集组成，通过总能量对齐（Total Energy Alignment，TEA）方法生成。若您使用本数据集包含的任意子数据集，请引用以下论文： @article{deng2023chgnet, title={CHGNet: 用于电荷感知原子建模的预训练通用神经网络势}, author={Bowen Deng and Peichen Zhong and KyuJung Jun and Janosh Riebesell and Kevin Han and Christopher J. Bartel and Gerbrand Ceder}, year={2023}, eprint={2302.14231}, archivePrefix={arXiv}, primaryClass={cond-mat.mtrl-sci}} @misc{kovacs2023maceoff23, title={MACE-OFF23: 适用于有机分子的可迁移机器学习力场}, author={Dávid Péter Kovács and J. Harry Moore and Nicholas J. Browning and Ilyes Batatia and Joshua T. Horton and Venkat Kapil and William C. Witt and Ioan-Bogdan Magdău and Daniel J. Cole and Gábor Csányi}, year={2023}, eprint={2312.15211}, archivePrefix={arXiv}} @article{eastman2023spice, title={SPICE: 用于训练机器学习势函数的类药物分子与肽数据集}, author={Eastman, Peter and Behara, Pavan Kumar and Dotson, David L and Galvelis, Raimondas and Herr, John E and Horton, Josh T and Mao, Yuezhi and Chodera, John D and Pritchard, Benjamin P and Wang, Yuanqing and others}, journal={Scientific Data}, volume={10}, number={1}, pages={11}, year={2023}, publisher={Nature Publishing Group UK London}} @article{donchev2021quantum, title={量子化学基准数据库：金标准二聚体相互作用能数据集}, author={Donchev, Alexander G and Taube, Andrew G and Decolvenaere, Elizabeth and Hargus, Cory and McGibbon, Robert T and Law, Ka-Hei and Gregersen, Brent A and Li, Je-Luen and Palmo, Kim and Siva, Karthik and others}, journal={Scientific Data}, volume={8}, number={1}, pages={55}, year={2021}, publisher={Nature Publishing Group UK London}} @article{isert2022qmugs, title={QMugs: 类药物分子的量子力学性质数据集}, author={Isert, Clemens and Atz, Kenneth and Jiménez-Luna, José and Schneider, Gisbert}, journal={Scientific Data}, volume={9}, number={1}, pages={273}, year={2022}, publisher={Nature Publishing Group UK London}} @misc{shiota2024taming, title={驾驭多域多保真度数据：迈向原子尺度模拟的基础模型}, author={Tomoya Shiota and Kenji Ishihara and Tuan Minh Do and Toshio Mori and Wataru Mizukami}, year={2024}, eprint={2412.13088}, archivePrefix={arXiv}, primaryClass={physics.chem-ph}}