MolCrystalFlow:通过流匹配进行分子晶体结构预测
MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching
AI总结:
MolCrystalFlow通过流匹配方法实现分子晶体结构预测,优于现有生成模型并具有竞争力的性能,结合通用机器学习势能加速预测。
摘要:
分子晶体结构预测是计算化学中的重大挑战,由于构成分子的尺寸较大且存在复杂的分子内和分子间相互作用。尽管生成式建模已革新了分子、无机固体和金属有机框架的结构发现,但将其扩展到完全周期性的分子晶体仍难以实现。本文提出了MolCrystalFlow,一种基于流的生成模型,用于分子晶体结构预测。该框架通过将分子作为刚体嵌入,将分子内复杂性与分子间堆积分离,并共同学习晶格矩阵、分子取向和质心位置。质心和取向在其原生的黎曼流形上进行表示,允许构造测地流并执行图神经网络操作,以尊重几何对称性。我们对最先进的生成模型(MOFFlow)和基于规则的结构生成方法(Genarris)在两个开源分子晶体数据集上进行了基准测试。MolCrystalFlow在MOFFlow上表现更优,同时在Genarris上取得具有竞争力的性能。我们还展示了将MolCrystalFlow模型与通用机器学习势能相结合,以加速分子晶体结构预测,为数据驱动的分子晶体生成发现铺平了道路。
英文摘要:
Molecular crystal structure prediction represents a grand challenge in computational chemistry due to large sizes of constituent molecules and complex intra- and intermolecular interactions. While generative modeling has revolutionized structure discovery for molecules, inorganic solids, and metal-organic frameworks, extending such approaches to fully periodic molecular crystals is still elusive. Here, we present MolCrystalFlow, a flow-based generative model for molecular crystal structure prediction. The framework disentangles intramolecular complexity from intermolecular packing by embedding molecules as rigid bodies and jointly learning the lattice matrix, molecular orientations, and centroid positions. Centroids and orientations are represented on their native Riemannian manifolds, allowing geodesic flow construction and graph neural network operations that respects geometric symmetries. We benchmark our model against a state-of-the-art generative model (MOFFlow) for large-size periodic crystals and a rule-based structure generation method (Genarris) on two open-source molecular crystal datasets. MolCrystalFlow outperforms MOFFlow while achieving competitive performance against Genarris. We also demonstrate an integration of MolCrystalFlow model with universal machine learning potential to accelerate molecular crystal structure prediction, paving the way for data-driven generative discovery of molecular crystals.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。