OXtal-CSP/OXtal_train_data

OXtal是一个用于分子晶体结构预测（CSP）的全原子扩散模型。OXtal在先前基于从头计算的机器学习CSP方法上实现了数量级的改进，同时比传统的量子化学方法便宜得多。具体来说，OXtal能够恢复刚性和柔性分子以及共晶的实验晶体结构，其构象RMSD1 < 0.5 Å，并达到超过80%的堆积相似率，展示了其模拟分子结晶的热力学和动力学规律的能力。该数据集包含用于训练OXtal的CCDC ids列表，并指引用户参考官方CCDC CSD数据库以获取实际的晶体结构。

OXtal is an all-atom diffusion model for molecular crystal structure prediction (CSP). OXtal achieves orders-of-magnitude improvements over prior ab initio machine learning CSP methods, while remaining orders of magnitude cheaper than traditional quantum-chemical approaches. Specifically, OXtal recovers experimental crystal structures for both rigid and flexible molecules as well as co-crystals with conformer RMSD1 < 0.5 Å and attains over 80% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization. This dataset contains the list of CCDC ids used to train OXtal and defer to the official CCDC CSD database for actual crystal structure retreival.