Automatic Identification of Chemical Moieties

2022/03/30 by Jonas Lederer, Lederer, Jonas, Michael Gastegger +9
Materials Science · Computer Science · Chemistry · #Machine Learning in Materials Science #Computational Drug Discovery Methods #Various Chemistry Research Topics

paper · pdf · doi:10.48550/arxiv.2203.16205

Abstract

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.

Related

• Neural Message Passing for Quantum Chemistry
• Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Universal neural network potentials as descriptors: Towards scalable chemical property prediction using quantum and classical computers
• Machine Learning, Quantum Mechanics, and Chemical Compound Space