# Distance-Geometric Graph Attention Network (DG-GAT) for 3D Molecular Geometry

arXiv: https://arxiv.org/abs/2207.08023 · HTML: https://mlsanity.com/paper/2207.08023/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 16 Jul 2022.

## Builds on (most cited first, 10 of 10)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Tiered Graph Autoencoders with PyTorch Geometric for Molecular Graphs](https://mlsanity.com/paper/1908.08612/) (2019)
- [Spatial Graph Convolutional Networks](https://mlsanity.com/paper/1909.05310/) (2019)
- [Distance Geometry and Data Science](https://mlsanity.com/paper/1909.08544/) (2019)
- [Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs](https://mlsanity.com/paper/2006.01785/) (2020)
- [Distance-Geometric Graph Convolutional Network (DG-GCN) for Three-Dimensional (3D) Graphs](https://mlsanity.com/paper/2007.03513/) (2020)
- [A Bird's-Eye Tutorial of Graph Attention Architectures](https://mlsanity.com/paper/2206.02849/) (2022)

## Built on by (most cited first, 1 of 1)

- [Hypergraph: A Unified and Uniform Definition with Application to Chemical Hypergraph and More](https://mlsanity.com/paper/2405.12235/) (2024)

## Abstract (arXiv)

Deep learning for molecular science has so far mainly focused on 2D molecular graphs. Recently, however, there has been work to extend it to 3D molecular geometry, due to its scientific significance and critical importance in real-world applications. The 3D distance-geometric graph representation (DG-GR) adopts a unified scheme (distance) for representing the geometry of 3D graphs. It is invariant to rotation and translation of the graph, and it reflects pair-wise node interactions and their generally local nature, particularly relevant for 3D molecular geometry. To facilitate the incorporation of 3D molecular geometry in deep learning for molecular science, we adopt the new graph attention network with dynamic attention (GATv2) for use with DG-GR and propose the 3D distance-geometric graph attention network (DG-GAT). GATv2 is a great fit for DG-GR since the attention can vary by node and by distance between nodes. Experimental results of DG-GAT for the ESOL and FreeSolv datasets show major improvement (31% and 38%, respectively) over those of the standard graph convolution network based on 2D molecular graphs. The same is true for the QM9 dataset. Our work demonstrates the utility and value of DG-GAT for deep learning based on 3D molecular geometry.