Pre-training Molecular Graph Representation with 3D Geometry

• URL: http://arxiv.org/abs/2110.07728v1
• Date: Thu, 7 Oct 2021 17:48:57 GMT
• Title: Pre-training Molecular Graph Representation with 3D Geometry
• Authors: Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang
• Abstract summary: Molecular graphs are typically modeled by their 2D topological structures. Lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation. We propose the Graph Multi-View Pre-training (GraphMVP) framework where self-supervised learning is performed by leveraging the correspondence and consistency between 2D topological structures and 3D geometric views.
• Score: 39.35244035710228
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Molecular graph representation learning is a fundamental problem in modern drug and material discovery. Molecular graphs are typically modeled by their 2D topological structures, but it has been recently discovered that 3D geometric information plays a more vital role in predicting molecular functionalities. However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation. To cope with this challenge, we propose the Graph Multi-View Pre-training (GraphMVP) framework where self-supervised learning (SSL) is performed by leveraging the correspondence and consistency between 2D topological structures and 3D geometric views. GraphMVP effectively learns a 2D molecular graph encoder that is enhanced by richer and more discriminative 3D geometry. We further provide theoretical insights to justify the effectiveness of GraphMVP. Finally, comprehensive experiments show that GraphMVP can consistently outperform existing graph SSL methods.

Related papers

• Automated 3D Pre-Training for Molecular Property Prediction [54.15788181794094]
  We propose a novel 3D pre-training framework (dubbed 3D PGT) It pre-trains a model on 3D molecular graphs, and then fine-tunes it on molecular graphs without 3D structures. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT.
  arXiv  Detail & Related papers  (2023-06-13T14:43:13Z)
• 3D Molecular Geometry Analysis with 2D Graphs [79.47097907673877]
  Ground-state 3D geometries of molecules are essential for many molecular analysis tasks. Modern quantum mechanical methods can compute accurate 3D geometries but are computationally prohibitive. We propose a novel deep learning framework to predict 3D geometries from molecular graphs.
  arXiv  Detail & Related papers  (2023-05-01T19:00:46Z)
• Graph Generation with Diffusion Mixture [57.78958552860948]
  Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures. We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
  arXiv  Detail & Related papers  (2023-02-07T17:07:46Z)
• Distance-Geometric Graph Attention Network (DG-GAT) for 3D Molecular Geometry [0.8722210937404288]
  3D distance-geometric graph representation (DG-GR) adopts a unified scheme (distance) for representing the geometry of 3D graphs. We propose the 3D distance-geometric graph attention network (DG-GAT) for use with DG-GR. Experimental results show major improvement over those of the standard graph convolution network based on 2D molecular graphs.
  arXiv  Detail & Related papers  (2022-07-16T21:39:31Z)
• GraphHD: Efficient graph classification using hyperdimensional computing [58.720142291102135]
  We present a baseline approach for graph classification with HDC. We evaluate GraphHD on real-world graph classification problems. Our results show that when compared to the state-of-the-art Graph Neural Networks (GNNs) the proposed model achieves comparable accuracy.
  arXiv  Detail & Related papers  (2022-05-16T17:32:58Z)
• Hierarchical Graph Networks for 3D Human Pose Estimation [50.600944798627786]
  Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. We argue that this skeletal topology is too sparse to reflect the body structure and suffer from serious 2D-to-3D ambiguity problem. We propose a novel graph convolution network architecture, Hierarchical Graph Networks, to overcome these weaknesses.
  arXiv  Detail & Related papers  (2021-11-23T15:09:03Z)
• Joint 3D Human Shape Recovery from A Single Imag with Bilayer-Graph [35.375489948345404]
  We propose a dual-scale graph approach to estimate the 3D human shape and pose from images. We use a coarse graph, derived from a dense graph, to estimate the human's 3D pose, and the dense graph to estimate the 3D shape. We train our model end-to-end and show that we can achieve state-of-the-art results for several evaluation datasets.
  arXiv  Detail & Related papers  (2021-10-16T05:04:02Z)
• GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction [47.70253904390288]
  We propose a novel graph contrastive learning method utilizing the geometry of a molecule across 2D and 3D views. Specifically, we first devise a dual-view geometric message passing network (GeomMPNN) to adaptively leverage the rich information of both 2D and 3D graphs of a molecule.
  arXiv  Detail & Related papers  (2021-09-24T03:55:27Z)
• Distance-Geometric Graph Convolutional Network (DG-GCN) for Three-Dimensional (3D) Graphs [0.8722210937404288]
  We propose a message-passing graph convolutional network based on the distance-geometric graph representation: DG-GCN. It enables learning of filter weights from distances, thereby incorporating the geometry of 3D graphs in graph convolutions. Our work demonstrates the utility and value of DG-GCN for end-to-end deep learning on 3D graphs, particularly molecular graphs.
  arXiv  Detail & Related papers  (2020-07-06T15:20:52Z)
• Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs [0.8722210937404288]
  The geometry of three-dimensional (3D) graphs, consisting of nodes and edges, plays a crucial role in many important applications. We define three types of geometric graph representations: positional, angle-geometric and distance-geometric. For proof of concept, we use the distance-geometric graph representation for geometric graph convolutions. The results of geometric graph convolutions, for the ESOL and Freesol datasets, show significant improvement over those of standard graph convolutions.
  arXiv  Detail & Related papers  (2020-06-02T17:08:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.