arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.07558cs.LG
收藏

二十面体球形化学对象(ICOs)支持化学数据增强,并保持旋转、平移和置换不变性

Icospherical Chemical Objects (ICOs) allow for chemical data augmentation and maintain rotational, translation and permutation invariance

Ella Gale

AI总结:

本文提出二十面体球形化学对象(ICOs),以旋转不变方式编码三维分子结构并支持数据增强,在分子性质预测、溶解度预测和蛋白质结合任务上验证了其与球形神经网络的有效性。

摘要:

数据集增强是应对小数据集问题的常用方法,而化学数据集往往规模较小。球形卷积神经网络(SphNNs)和二十面体神经网络(IcoNNs)是一类保持旋转对称性的几何机器学习算法。分子结构具有旋转不变性且本质上是三维的,因此我们需要三维编码方法将分子结构输入机器学习模型。在本文中,我提出了二十面体球形化学对象(ICOs),它能够以旋转不变的方式编码三维数据,可与球形或二十面体神经网络配合使用,并支持数据集增强。我在以下任务上展示了ICO特征化方法:预测一般分子性质、预测类药分子的溶解度以及蛋白质结合问题,并发现ICO和SphNNs在所有问题上均表现良好。

英文摘要:

Dataset augmentation is a common way to deal with small datasets; Chemistry datasets are often small. Spherical convolutional neural networks (SphNNs) and Icosahedral neural networks (IcoNNs) are a type of geometric machine learning algorithm that maintains rotational symmetry. Molecular structure has rotational invariance and is inherently 3-D, and thus we need 3-D encoding methods to input molecular structure into machine learning. In this paper I present Icospherical Chemical Objects (ICOs) that enable the encoding of 3-D data in a rotationally invariant way which works with spherical or icosahedral neural networks and allows for dataset augmentation. I demonstrate the ICO featurisation method on the following tasks: predicting general molecular properties, predicting solubility of drug like molecules and the protein binding problem and find that ICO and SphNNs perform well on all problems.

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。

↑