Energy-motivated equivariant pretraining for 3d molecular graphs
… 3D tasks. In this work, we tackle 3D molecular pretraining in a complete and novel sense. In
particular, we first propose to adopt an equivariant energy-based model as the backbone for …
particular, we first propose to adopt an equivariant energy-based model as the backbone for …
Pre-training molecular graph representation with 3d geometry
… by 3D geometry due to its encoded energy knowledge, we aim to make use of the 3D
geometry of molecules in pre-training. … Unite: Unitary n-body tensor equivariant network with …
geometry of molecules in pre-training. … Unite: Unitary n-body tensor equivariant network with …
Automated 3D pre-training for molecular property prediction
… stage, we can potentially encode more accurate molecular geometry information on the 2D
molecular graph, … Equivariant message passing for the prediction of tensorial properties and …
molecular graph, … Equivariant message passing for the prediction of tensorial properties and …
Equivariant Pretrained Transformer for Unified Geometric Learning on Multi-Domain 3D Molecules
… In contrast to previous methods, this paper proposes one pretrained model for multiple
domains (see Figure 1), to enable unified geometric learning on 3D molecules. We claim several …
domains (see Figure 1), to enable unified geometric learning on 3D molecules. We claim several …
Equivariant graph neural networks for 3d macromolecular structure
… most broadly applicable to molecular structure—on these … pretrained equivariant
representations can boost performance on downstream tasks. These results suggest that equivariant …
representations can boost performance on downstream tasks. These results suggest that equivariant …
Unified 2d and 3d pre-training of molecular representations
… [30] introduce equivariant networks to ensure the … only leverage the 2D molecular graphs for
pre-training, our method … This shows the effectiveness of using 3D information in pre-training…
pre-training, our method … This shows the effectiveness of using 3D information in pre-training…
Equivariant graph attention networks for molecular property prediction
… and Clebsch-Gordan decomposition to build equivariant functions, but we explicitly design
functions that are equivariant and operate on 3D-Cartesian coordinates for faster and more …
functions that are equivariant and operate on 3D-Cartesian coordinates for faster and more …
Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding
… (3)-EGMN [ 27 ] as the molecule encoder network for the ProtMD … features and 3D coordinates,
while the pre-training stage … the 3D coordinates is used in the self-supervised pre-training …
while the pre-training stage … the 3D coordinates is used in the self-supervised pre-training …
Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
… To leverage this advantage better, we incorporate an equivariant graph neural network (GNN)
block into the architecture, inspired by [38, 39], to efficiently encode crucial information …
block into the architecture, inspired by [38, 39], to efficiently encode crucial information …
Equiformer: Equivariant graph attention transformer for 3d atomistic graphs
YL Liao, T Smidt - arXiv preprint arXiv:2206.11990, 2022 - arxiv.org
… domain of 3D atomistic graphs such as molecules even when 3D-… well to 3D atomistic graphs
and present Equiformer, a graph … ing SE(3)/E(3)-equivariant features based on irreducible …
and present Equiformer, a graph … ing SE(3)/E(3)-equivariant features based on irreducible …
Related searches
- perceptron networks molecular graphs
- equivariant graph neural networks
- equivariant graph matching networks
- molecular pretraining cross-modal distillation
- molecular representation learning graph similarities
- graph attention networks molecular property prediction
- graph contrastive learning molecular property prediction
- graph transformer molecular property prediction
- relation graphs molecular property prediction
- graph neural networks molecular property prediction
- multiplex graph neural networks small molecules
- 3d equivariant molecule graph pretraining
- 3d equivariant molecular graph transformer
- 3d equivariant molecular graph embedding
- 3d equivariant molecular graph representation
- 3d equivariant molecular graph attention