OpenREACT-CHON-EFH — Open REaction Dataset of Atomic ConfiguraTions comprising C, H, O, N with Energies, Forces, and Hessians

Name: OpenREACT-CHON-EFH — O pen RE action Dataset of A tomic C onfigura T ions comprising C , H , O , N with E nergies, F orces, and H essians
Creator: Mendoza-Cortes, Jose L.; Smith, Justin S.; Rodriguez, Austin
Published: 2025-05-29T00:00:00+08:00

Figshare2025-05-29 更新2026-04-08 收录

原子间势机器学习

化学反应势能面建模

数据链接：

https://figshare.com/articles/dataset/_b_OpenREACT-CHON-FH_b_i_Open_Reaction_Dataset_of_Atomic_Configurations_with_Energies_Forces_and_Hessians_i_/29189858/4 数据链接链接失效反馈

官方服务：

资源简介：

These datasets were used in the training and testing of Machine Learning Interatomic Potentials (MLIPs) as part of the work represented in the article titled Does Hessian Data Improve the Performance of Machine Learning Potentials?.RTP Dataset (Reactant–Transition State–Product Dataset):The RTP dataset forms the core training and evaluation set and consists of 35,087 molecular geometries sampled from 11,961 unique elementary reactions. For each reaction, three critical geometries are included: the optimized reactant, transition state (TS), and product. Each geometry is labeled with its corresponding DFT-computed potential energy, atomic forces, and Hessian matrix, calculated at the wb97xd/6-31g(d) level of theory. This dataset represents stationary points (critical points) on the potential energy surface and serves as the foundation for training the MLIPs to reproduce energies, gradients, and curvatures.IRC Dataset (Intrinsic Reaction Coordinate Dataset):To assess the extrapolation performance of the trained MLIPs along continuous reaction pathways, a dataset of 34,248 geometries was compiled from 600 Intrinsic Reaction Coordinate (IRC) paths, each corresponding to a distinct elementary reaction in the RTP dataset. These geometries were obtained by following the minimum energy path (MEP) from the transition state to both reactant and product wells using quantum chemistry calculations at the wb97xd/6-31g(d) level of theory. While these geometries are not explicitly used in training, they provide a rigorous benchmark for evaluating the ability of MLIPs to generalize beyond training data and accurately model transition state connectivity and reaction dynamics.NMS Dataset (Normal Mode Sampling Dataset):To evaluate MLIP robustness on off-equilibrium, perturbed structures, 62,527 geometries were generated via Normal Mode Sampling (NMS). These structures are derived by displacing intermediate IRC geometries along their vibrational modes with random amplitudes, simulating thermal fluctuations and non-equilibrium distortions. The properties of these perturbed structures were calculated at the wb97xd/6-31g(d) level of theory. This dataset allows for testing the model's stability and accuracy in more realistic, noisy molecular environments as encountered in molecular dynamics simulations or under experimental conditions.

本数据集用于机器学习原子间势（Machine Learning Interatomic Potentials, MLIPs）的训练与测试，相关工作对应发表于题为《Hessian数据是否能提升机器学习势函数性能？》的学术论文。 **RTP数据集（反应物-过渡态-产物数据集）**：该数据集为核心训练与评估集，包含从11961个独特基元反应中采样得到的35087个分子几何构型。每个反应包含三类关键几何构型：优化后的**反应物**、**过渡态（Transition State, TS）**与**产物**。每个构型均标注有基于wb97xd/6-31g(d)理论级别，通过密度泛函理论（Density Functional Theory, DFT）计算得到的对应**势能**、**原子受力**与**海森矩阵（Hessian matrix）**。该数据集涵盖势能面上的驻点（临界点），可作为训练MLIPs以复现势能、梯度与曲率的基础。 **IRC数据集（内禀反应坐标数据集）**：为评估训练后的MLIPs在连续反应路径上的外推性能，我们从RTP数据集中对应不同基元反应的600条**内禀反应坐标（Intrinsic Reaction Coordinate, IRC）路径**中构建了包含34248个几何构型的数据集。这些构型通过基于wb97xd/6-31g(d)理论级别的量子化学计算，沿最小能量路径（Minimum Energy Path, MEP）从过渡态向反应物与产物势阱延伸得到。尽管此类构型未直接用于模型训练，但可为评估MLIPs泛化至训练数据外场景的能力，以及准确建模过渡态连接性与反应动力学的性能提供严谨的基准测试集。 **NMS数据集（简正模式采样数据集）**：为评估MLIPs在**非平衡扰动构型**下的鲁棒性，我们通过**简正模式采样（Normal Mode Sampling, NMS）**生成了62527个几何构型。此类构型通过沿IRC中间构型的振动模式施加随机振幅位移得到，用以模拟热涨落与非平衡畸变。扰动构型的各项性质基于wb97xd/6-31g(d)理论级别计算得到。该数据集可用于测试模型在分子动力学模拟或实验条件下遇到的更贴近真实、带有噪声的分子环境中的稳定性与准确性。

提供机构：

Mendoza-Cortes, Jose L.; Smith, Justin S.; Rodriguez, Austin

创建时间：

2025-05-29

资源简介：

相关数据集