ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction

@article{Fang2022ChemRLGEMGE,
  title={ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction},
  author={Xiaomin Fang and Lihang Liu and Jieqiong Lei and Donglong He and Shanzhuo Zhang and Jingbo Zhou and Fan Wang and Hua Wu and Haifeng Wang},
  journal={Nat. Mach. Intell.},
  year={2022},
  volume={4},
  pages={127-134}
}
Effective molecular representation learning is of great importance to facilitate molecular property prediction, which is a fundamental task for the drug and material industry. Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning. Moreover, a few recent studies have also demonstrated successful applications of self-supervised learning methods to pre-train the GNNs to overcome the problem of insufficient labeled… 

ReLMole: Molecular Representation Learning Based on Two-Level Graph Similarities.

This paper proposes a representation learning method for molecular graphs, called ReLMole, which is featured by a hierarchical graph modeling of molecules and a contrastive learning scheme based on two-level graph similarities.

GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction

This work proposes a novel graph contrastive learning method utilizing the geometry of the molecule across 2D and 3D views, which is named GeomGCL, and devise a dual-view geometric message passing network (GeomMPNN) to adaptively leverage the rich information of both 3D and 2D graphs of a molecule.

ComABAN: refining molecular representation with the graph attention mechanism to accelerate drug discovery

An unsolved challenge in developing molecular representation is determining an optimal method to characterize the molecular structure. Comprehension of intramolecular interactions is paramount toward

Substructure-Atom Cross Attention for Molecular Representation Learning

This work pretrain the network to learn a general representation of molecules with minimal supervision, and shows that the pretrained network achieves competitive performance on 11 downstream tasks for molecular property prediction.

Molecular Structure-Property Co-Trained Foundation Model for In Silico Chemistry

A novel multimodal foundation model that can be used in silico for various downstream tasks in chemistry, based on the dual-stream transformer with X-shape attention, which can simultaneously perform chemical property prediction from given structure-describing strings and allows the generation of molecular structures for given chemical properties, which was previously not possible with a single architecture.

FunQG: Molecular Representation Learning Via Quotient Graphs

A novel molecular graph coarsening framework named FunQG utilizing Fun ctional groups, as inential building blocks of a molecule to determine its properties, based on a graph-theoretic concept called Q uotient G raph is proposed and shown that the resulting informative graphs are much smaller than the molecular graphs and thus are good candidates for training GNNs.

3D Graph Contrastive Learning for Molecular Property Prediction

A novel contrastive learning framework, small-scale 3D Graph Contrastive Learning (3DGCL) for molecular property prediction, to solve a few issues of self-supervised learning, including 3D structural information based on chemical knowledge is essential to molecular representation learning for property prediction.

Graph Neural Networks for Molecules

This review introduces GNNs and their various applications for small organic molecules and summarizes the recent development of self-supervised learning for molecules withGNNs.

Pre-training Graph Neural Networks for Molecular Representations: Retrospect and Prospect

  • Computer Science
  • 2022
A comprehensive survey of pre-trained GMs for molecular representations based on a taxonomy from four different perspectives including model architectures, pre-training strategies, tuning strategies, and applications is provided.

Pre-training Transformers for Molecular Property Prediction Using Reaction Prediction

A pre-training proce-dure for molecular representation learning using reaction data and use it to pre-train a SMILES Transformer and show a statistically significant positive effect on 5 of the 12 tasks compared to a non-pre-trained base-line model.

References

SHOWING 1-10 OF 65 REFERENCES

Gated Graph Recursive Neural Networks for Molecular Property Prediction

This work proposes a simple and powerful graph neural networks for molecular property prediction as a directed complete graph in which each atom has a spatial position, and introduces a recursive neural network with simple gating function.

Learn molecular representations from large-scale unlabeled molecules for drug discovery

This work proposed a novel Molecular Pre-training Graph-based deep learning framework, named MPG, that leans molecular representations from large-scale unlabeled molecules and reveals that MolGNet can capture valuable chemistry insights to produce interpretable representation.

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction.

A convolutional neural network is employed for the embedding task of learning an expressive molecular representation by treating molecules as undirected graphs with attributed nodes and edges, and preserves molecule-level spatial information that significantly enhances model performance.

Self-Supervised Graph Transformer on Large-Scale Molecular Data

A novel framework, GROVER, which stands for Graph Representation frOm self-supervised mEssage passing tRansformer, which allows it to be trained efficiently on large-scale molecular dataset without requiring any supervision, thus being immunized to the two issues mentioned above.

Analyzing Learned Molecular Representations for Property Prediction

A graph convolutional model is introduced that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets.

Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties

  • Zeren ShuiG. Karypis
  • Computer Science, Chemistry
    2020 IEEE International Conference on Data Mining (ICDM)
  • 2020
A novel graph representation of molecules, heterogeneous molecular graph (HMG) in which nodes and edges are of various types, to model many-body interactions and achieves state-of-the-art performance in 9 out of 12 tasks on the QM9 dataset.

N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

The N-gram graph is introduced, a simple unsupervised representation for molecules that is equivalent to a simple graph neural network that needs no training and is complemented by theoretical analysis showing its strong representation and prediction power.

MoleculeNet: A Benchmark for Molecular Machine Learning

MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance, however, this result comes with caveats.

Neural Message Passing for Quantum Chemistry

Using MPNNs, state of the art results on an important molecular property prediction benchmark are demonstrated and it is believed future work should focus on datasets with larger molecules or more accurate ground truth labels.

Pushing the boundaries of molecular representation for drug discovery with graph attention mechanism.

A new graph neural network architecture called Attentive FP for molecular representation that uses a graph attention mechanism to learn from relevant drug discovery datasets and achieves state-of-the-art predictive performances on a variety of datasets and that what it learns is interpretable.
...