Automatic Identification of Chemical Moieties
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 97 references that are in the map. First posted on arXiv 30 Mar 2022.
Builds on
32 of 97 references.
References · 32
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
- 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
- 2020Directional Message Passing for Molecular Graphscited by 556
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
- 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
- 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
- 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
20 more
- 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
- 2020Machine Learning Force Fieldscited by 204
- 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
- 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
- 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
- 2019Machine learning for molecular simulationcited by 109
- 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
- 2021Inverse design of 3d molecular structures with conditional generative neural networkscited by 93
- 2019Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctionscited by 73
- 2018Machine Learning of coarse-grained Molecular Dynamics Force Fieldscited by 68
- 2017Time-lagged autoencoders: Deep learning of slow collective variables for molecular kineticscited by 64
- 2020Memory-Based Graph Networkscited by 56
- 2020Coarse Graining Molecular Dynamics with Graph Neural Networkscited by 56
- 2020TorchMD: A deep learning framework for molecular simulationscited by 55
- 2018Coarse-Graining Auto-Encoders for Molecular Dynamicscited by 30
- 2021Toward Explainable AI for Regression Modelscited by 30
- 2018Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistrycited by 25
- 2019Spectral Clustering with Graph Neural Networks for Graph Poolingcited by 16
- 2020Machine learning of solvent effects on molecular spectra and reactionscited by 14
- 2020Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approachcited by 4
Built on by
Citing papers per year: 2022: 2.
2 papers.