jiachengxiong / Literature

Recent application of graph neural network in drug discovery

GNN in Drug Discovery

This is a collection of recent parpers of graph neural network applied in drug discovery

Contents

• Review
• Articles
  • Self-supervised Learning
  • Property Prediction
    • Small Molecular
    • Protien
  • Chemical Reaction Prediction
    • Prediction of General Chemical Reaction
    • Prediction of Specific Types of Chemical Reactions
    • Prediction of Retrosynthesis
  • Molecule Generation
    • Based on GAN
    • Based on VAE
    • Based on Autoregression
    • Based on Invertible Flow
    • Based on Chemical Reaction
  • Interaction & Association Prediction
    • Drug-Target Interaction
    • Drug-Drug Interaction
    • Protien-Protein Interaction
    • Solute-Solvent Interaction
    • RNA-Protein Interaction
    • Disease-lncRNA Association
    • Drug-miRNA Association
    • Disease-Gene Association

Review

1. Graph convolutional networks for computational drug development and discovery. BRIEF BIOINFORM. 2019. Link

Articles

Self-supervised Learning

1. Strategies For Pre-training Graph Neural Networks. ICLR. 2020. Link

Prediction of Molecular Properties

Small Molecular

1. Convolutional networks on graphs for learning molecular fingerprints. NIPS. 2015. Link

2. Molecular graph convolutions: moving beyond fingerprints. J. Comput.-Aided Mol. Des. 2016. Link

3. Neural message passing for quantum chemistry. JMLR. 2017. Link

4. Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network. arXiv. 2018. Link

5. Edge attention-based multi-relational graph convolutional networks. arXiv. 2018. Link

6. Graph warp module an auxiliary module for boosting the power of graph neural networks in molecular graph analysis. arXiv. 2019. Link

7. Analyzing Learned Molecular Representations for Property Prediction. J CHEM INF MODEL 2019. Link

8. Graph networks as a universal machine learning framework for molecules and crystals. CHEM MATER. 2019. Link

9. Molecular activity prediction using graph convolutional deep neural network considering distance on a molecular graph. aRxiv. 2019. Link

10. Multitask learning on graph neural networks applied to molecular property predictions. aRxiv. 2019. Link

11. Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism. J MED CHEM. 2019. Link

12. Molecular geometry prediction using a deep generative graph neural network. Sci Rep. 2019. Link

13. Practical high-quality electrostatic potential surfaces for drug. J MED CHEM. 2019. Link

14. Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction. J CHEMINFORMATICS. 2020. Link

15. A deep learning approach to antibiotic discovery. CELL. 2020 Link

Protien

1. Structural learning of proteins using graph convolutional neural networks. bioRxiv. 2019. Link

Chemical Reaction Prediction

Prediction of General Chemical Reaction

1. Predicting organic reaction outcomes with weisfeiler-lehman network. NIPS. 2017. Link

2. A graph-convolutional neural network model for the prediction of chemical reactivity. CHEM SCI. 2019. Link

3. Graph transformation policy network for chemical reaction prediction. KDD. 2019. Link

4. Integrating deep neural networks and symbolic inference for organic reactivity prediction. chemArix. 2020. Link

Prediction of Specific Types of Chemical Reactions

1. Rapid and accurate prediction of pka values of C–H acids using graph convolutional neural networks. JACS. 2019. Link

Prediction of Retrosynthesis

1. Interpretable retrosynthesis prediction in two steps. ChemRxiv. 2020. Link

Molecule Generation

Based on GAN

1. MolGAN: An implicit generative model for small molecular graphs. aRxiv. 2018. Link

Based on VAE

1. Graphvae: Towards generation of small graphs using variational autoencoders. ICANN. 2018. Link

2. Junction tree variational autoencoder for molecular graph generation. PMLR. 2018. Link

3. Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation. J CHEMINFORMATICS. 2019. Link

4. Hierarchical graph-to-graph translation for molecules. aRxiv. 2019. Link

5. Learning Multimodal Graph-to-graph Translation For Molecular Optimization. ICLR. 2019. Link

6. Core: Automatic molecule optimization using copy & refine strategy. AAAI. 2020. Link

Based on Autoregression

1. Graph convolutional policy network for goal-directed molecular graph generation. NIPS. 2018. Link

2. Multi-objective de novo drug design with conditional graph generative model. J CHEMINFORMATICS. 2018. Link

3. MolecularRNN: Generating realistic molecular graphs with optimized properties. aRxiv. 2019. Link

Based on Invertible Flow

1. GraphNVP:An invertible flow model for generating molecular graphs. aRxiv. 2019. Link

Based on Chemical Reaction

1. A model to search for synthesizable molecules. NIPS. 2019. Link

Interaction & Association Prediction

Drug-Target Interaction

1. Atomic convolutional networks for predicting protein-ligand binding affinity. aRxiv. 2017. Link

2. PotentialNet for molecular property prediction. ACS CENTRAL SCI. 2018. Link

3. Interpretable drug target prediction using deep neural representation. IJCAI. 2018. Link

4. Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. BIOINFORMATICS. 2019. Link

5. GraphDTA: Prediction of drug target binding affinity using graph neural networks. bioRxiv . 2019. Link

6. Graph convolutional neural networks for predicting drug-target interactions. J CHEM INF MODEL. 2019. Link

7. Predicting drug−target interaction using a novel graph neural network with 3d structure-embedded graph representation. J CHEM INF MODEL. 2019. Link

8. AGL-Score: Algebraic graph learning score for protein−ligand binding scoring, ranking, docking, and screening. J CHEM INF MODEL. 2019. Link

9. Target identification among known drugs by deep learning from heterogeneous networks. CHEM SCI. 2020. Link

Drug-Drug Interaction

1. Enhancing drug-drug interaction extraction from texts by molecular structure information. aRxiv. 2018. Link

2. MR-GNN: Multi-resolution and dual graph neural network for predicting structured entity interactions. aRxiv. 2018. Link

3. Drug similarity integration through attentive multi-view graph auto-encoders. aRxiv. 2018. Link

4. Modeling polypharmacy side effects with graph convolutional networks. BIOINFORMATICS. 2018. Link

5. GENN: Predicting correlated drug-drug interactions with graph energy neural networks. aRxiv. 2019. Link

6. Tri-graph information propagation for polypharmacy side effect prediction. aRxiv. 2019. Link

Protien-Protein Interaction

1. Protein interface prediction using graph convolutional networks. NIPS. 2017. Link

Solute-Solvent Interaction

1. Chemically interpretable graph interaction network for prediction of pharmacokinetic properties of drug-like molecules. chemRxiv. 2020. Link

RNA-Protein Interaction

1. Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions. bioRxiv. 2020. Link

Disease-lncRNA Association

1. Graph convolutional network and convolutional neural network based method for predicting lncRNA-disease associations. Cells. 2019. Link

Drug-miRNA Association

1. Graph convolution for predicting associations between miRNA and drug resistance. BIOINFORMATICS. 2020. Link

Disease-Gene Association

1. GCN-MF: Disease-gene association identification by graph convolutional networks and matrix factorization. KDD. 2019. Link