Geometry-enhanced molecular representation learning for property prediction

By Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, Haifeng Wang. Nature Machine Intelligence, 2021

648 citations recorded by the source corpus.

Effective molecular representation learning is of great importance to facilitate molecular property prediction. Recent advances for molecular representation learning have shown great promise in applying graph neural networks to model molecules. Moreover, a few recent studies design self-supervised learning methods for molecular representation to address insufficient labelled molecules; however, these self-supervised frameworks treat the molecules as topological graphs without fully utilizing the molecular geometry information. The molecular geometry, also known as the three-dimensional spatial structure of a molecule, is critical for determining molecular properties. To this end, we propose a novel geometry-enhanced molecular representation learning method (GEM). The proposed GEM has a specially designed geometry-based graph neural network architecture as well as several dedicated geometry-level self-supervised learning strategies to learn the molecular geometry knowledge. We compare GEM with various state-of-the-art baselines on different benchmarks and show that it can considerably outperform them all, demonstrating the superiority of the proposed method. Molecules are often represented as topological graphs while their true three-dimensional geometry contains a lot of valuable information. Xiaomin Fang and colleagues present a self-supervised molecule representation method that uses this geometric data in graph neural networks to predict a range of molecular properties.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/2a47759c48bf8d14d2caa54bcc4bd03c1eee6135

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Payel Das
2. Zhifeng Gao
3. Hang Zheng
4. Youssef Mroueh
5. Brian M. Belgodere
6. Guolin Ke
7. Jerret Ross
8. Inkit Padhi

In Materials Chemistry

1. Payel Das
2. Hang Zheng
3. Youssef Mroueh
4. Brian M. Belgodere
5. Guolin Ke
6. Jerret Ross
7. Inkit Padhi

In Molecular Biology

1. Zhewei Wei
2. Payel Das
3. Gengmo Zhou
4. Hongteng Xu
5. Linfeng Zhang
6. Zhifeng Gao
7. Hang Zheng
8. Youssef Mroueh

Citations in the corpus

• Do Deep Learning Models Really Outperform Traditional Approaches in Molecular Docking? (2023, methodology): “Recently, deep learning has been widely used in drug design applications, such as molecular property prediction [5, 6, 7, 8] and protein structure predition [9].”
• Large-scale chemical language representations capture molecular structure and properties (2021, methodology): “We have considered three other geometry-aware GNN baselines, one supervised (DimeNet 37 ), and two self-supervised (GeomGCL 36 and GEM 38 ).”
• Uni-Mol: A Universal 3D Molecular Representation Learning Framework (2023, methodology): “N-gram [53], PretrainGNN [22], GROVER [11], GraphMVP [26], MolCLR [12], and GEM [13] are pretraining methods.”