arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.16205physics.chem-phcs.LG
收藏

化学基团的自动识别

Automatic Identification of Chemical Moieties

Berlin Institute of Technology (TU Berlin)(柏林工业大学(TU Berlin));BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD——柏林学习与数据基础研究所);UiT The Arctic University of Norway(挪威UiT北极大学);Google Research(谷歌研究院);Korea University(高丽大学);Max Planck Institut für Informatik(马克斯·普朗克信息学研究所)

Jonas Lederer, Michael Gastegger, Kristof T. Schütt, Michael Kampffmeyer, Klaus-Robert Müller, Oliver T. Unke

AI总结:

本文提出一种从 MPNN 原子表示中自动识别化学基团的方法,可用于分子指纹设计、数据库代表条目选择、粗粒化力场构建和反应坐标识别。

摘要:

近年来,利用机器学习方法预测量子力学可观测量变得越来越流行。消息传递神经网络(MPNN)通过构建原子表示来解决这一任务,并据此预测所关注的性质。在这里,我们提出一种从此类表示中自动识别化学基团(分子构建块)的方法,从而支持性质预测之外的多种应用,而这些应用原本依赖专家知识。所需表示既可以由预训练的 MPNN 提供,也可以仅使用结构信息从头学习。除了以数据驱动方式设计分子指纹外,我们方法的多功能性还通过以下方面得到证明:支持在化学数据库中选择代表性条目、自动构建粗粒化力场,以及识别反应坐标。

英文摘要:

In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.

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。

↑