Zeng Jinzhe, Giese Timothy J, Zhang Duo, Wang Han, York Darrin M
Laboratory for Biomolecular Simulation Research, Institute for Quantitative Biomedicine and Department of Chemistry and Chemical Biology, Rutgers University, Piscataway, New Jersey 08854, United States.
AI for Science Institute, Beijing 100080, P. R. China.
J Chem Inf Model. 2025 Apr 14;65(7):3154-3160. doi: 10.1021/acs.jcim.4c02441. Epub 2025 Mar 27.
Machine learning potentials (MLPs) have revolutionized molecular simulation by providing efficient and accurate models for predicting atomic interactions. MLPs continue to advance and have had profound impact in applications that include drug discovery, enzyme catalysis, and materials design. The current landscape of MLP software presents challenges due to the limited interoperability between packages, which can lead to inconsistent benchmarking practices and necessitates separate interfaces with molecular dynamics (MD) software. To address these issues, we present DeePMD-GNN, a plugin for the DeePMD-kit framework that extends its capabilities to support external graph neural network (GNN) potentials.DeePMD-GNN enables the seamless integration of popular GNN-based models, such as NequIP and MACE, within the DeePMD-kit ecosystem. Furthermore, the new software infrastructure allows GNN models to be used within combined quantum mechanical/molecular mechanical (QM/MM) applications using the range corrected ΔMLP formalism.We demonstrate the application of DeePMD-GNN by performing benchmark calculations of NequIP, MACE, and DPA-2 models developed under consistent training conditions to ensure fair comparison.
机器学习势（MLP）通过提供用于预测原子相互作用的高效且准确的模型，彻底改变了分子模拟。MLP不断发展，并在包括药物发现、酶催化和材料设计在内的应用中产生了深远影响。由于软件包之间的互操作性有限，MLP软件的当前格局带来了挑战，这可能导致基准测试实践不一致，并且需要与分子动力学（MD）软件有单独的接口。为了解决这些问题，我们提出了DeePMD-GNN，这是DeePMD-kit框架的一个插件，它扩展了其功能以支持外部图神经网络（GNN）势。DeePMD-GNN能够在DeePMD-kit生态系统中无缝集成基于GNN的流行模型，如NequIP和MACE。此外，新的软件基础设施允许使用范围校正的ΔMLP形式主义在组合量子力学/分子力学（QM/MM）应用中使用GNN模型。我们通过对在一致训练条件下开发的NequIP、MACE和DPA-2模型进行基准计算来展示DeePMD-GNN的应用，以确保公平比较。
