colabfit/Chig-AIMD_scaffold_train

Chig-AIMD支架训练数据集包含了使用DFT级精度的Chig-AIMD中scaffold部分的训练配置。通过对10个氨基酸蛋白质Chignolin进行复制交换分子动力学（REMD）、传统MD和从头MD（AIMD）模拟，最终收集了200万个生物分子结构，并记录了量子级别的能量和力。该数据集包含约1592662个独特的分子配置和264381892个原子，涵盖了C、H、N、O四种元素，并包括了能量、原子力和柯西应力等属性。

The Chig-AIMD scaffold train dataset includes training configurations from the scaffold split of Chig-AIMD with DFT-level precision. By performing replica exchange molecular dynamics (REMD), conventional MD, and ab initio MD (AIMD) simulations on a 10 amino acid protein, Chignolin, approximately 2 million biomolecule structures with quantum level energy and force records were collected. The dataset contains about 1,592,662 unique molecular configurations and 264,381,892 atoms, covering the elements C, H, N, O, and includes properties such as energy, atomic forces, and Cauchy stress.