arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.00102physics.chem-phphysics.comp-ph
收藏

多分辨率三维DenseNet模型在NMR晶体学化学位移预测中的应用

A Multi-Resolution 3D-DenseNet for Chemical Shift Prediction in NMR Crystallography

Shuai Liu, Jie Li, Kochise C. Bennett, Brad Ganoe, Tim Stauch, Martin Head-Gordon, Alexander Hexemer, Daniela Ushizima, Teresa Head-Gordon

摘要:

我们开发了一种用于分子晶体中原子化学位移预测的深度学习算法,该算法利用原子中心高斯密度模型来表示分子的3D数据。我们定义了多个通道,这些通道描述了每种原子类型的不同空间分辨率,这些原子类型利用裁剪、合并和级联来创建多分辨率3D-DenseNet架构(MR-3D-DenseNet)。由于训练和测试时间与样本数量呈线性关系,MR-3D-DenseNet可以利用考虑化学位移旋转不变性的数据增强,从而将训练数据集的大小增加一个数量级,而无需额外成本。我们获得了非常好的协议,13 C,15 N,和17 O化学位移,与最高的准确度为1H化学位移,相当于最好的预测,使用从头算量子化学方法。

英文摘要:

We have developed a deep learning algorithm for chemical shift prediction for atoms in molecular crystals that utilizes an atom-centered Gaussian density model for the 3D data representation of a molecule. We define multiple channels that describe different spatial resolutions for each atom type that utilizes cropping, pooling, and concatenation to create a multi-resolution 3D-DenseNet architecture (MR-3D-DenseNet). Because the training and testing time scale linearly with the number of samples, the MR-3D-DenseNet can exploit data augmentation that takes into account the property of rotational invariance of the chemical shifts, thereby also increasing the size of the training dataset by an order of magnitude without additional cost. We obtain very good agreement for 13C, 15N, and 17O chemical shifts, with the highest accuracy found for 1H chemical shifts that is equivalent to the best predictions using ab initio quantum chemistry methods.

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。

↑