2021
DOI: 10.48550/arxiv.2106.03843
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Bowen Jing,
Stephan Eismann,
Pratham N. Soni
et al.

Abstract: Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on 4 out of 8 tasks in the ATOM3D benchmark and broadly improves over rotation-invariant graph neural networks. We also demonstrate that transfer learning can improve performance in learni… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
48
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 27 publications
(50 citation statements)
references
References 10 publications
2
48
0
Order By: Relevance
“…Each edge also encodes both the scalar and the vector features. We then apply the geometric vector perceptrons (GVP) [Jing et al 2020, 2021] to embed the protein and arrive at feature h p ∈ ℝ n × s after graph propagation, where n is the number of nodes and s is the embedding size.…”
Section: Tankbind Modelmentioning
confidence: 99%
See 2 more Smart Citations
“…Each edge also encodes both the scalar and the vector features. We then apply the geometric vector perceptrons (GVP) [Jing et al 2020, 2021] to embed the protein and arrive at feature h p ∈ ℝ n × s after graph propagation, where n is the number of nodes and s is the embedding size.…”
Section: Tankbind Modelmentioning
confidence: 99%
“…There has been a surge of interest in integrating geometric priors for representation learning in the domain of drug discovery Jumper et al [2021], Baek et al [2021], Jing et al [2021], Ganea et al [2021], Jin et al [2021], Ingraham et al [2019], AlQuraishi 2019], [Schütt et al [2017], Somnath et al [2021]. Recent researches have incorporated geometric information and symmetry properties of the input signals to improve the spatial perception of the learned representations.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…We also compare GNN variants such as GCN (Kipf & Welling, 2016), GIN (Xu et al, 2018) and GAT (Veličković et al, 2017) with our DW-GCN, DW-GIN and DW-GAT models. In addition, we include GVP-GNN (Jing et al, 2021) discussed above as well.…”
Section: Residue Identificationmentioning
confidence: 99%
“…However, none of those DL approaches consider a temporal perspective and take advantage of molecular dynamics simulations to describe the joint flexibility of proteins and ligands. [65]…”
Section: Protein-ligand Modelingmentioning
confidence: 99%