Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Molecular contrastive learning of representations via graph neural networks

Nature Machine Intelligence volume 4, pages 279–287 (2022)Cite this article

Subjects

A preprint version of the article is available at arXiv.

Abstract

Molecular machine learning bears promise for efficient molecular property prediction and drug discovery. However, labelled molecule data can be expensive and time consuming to acquire. Due to the limited labelled data, it is a great challenge for supervised-learning machine learning models to generalize to the giant chemical space. Here we present MolCLR (Molecular Contrastive Learning of Representations via Graph Neural Networks), a self-supervised learning framework that leverages large unlabelled data (~10 million unique molecules). In MolCLR pre-training, we build molecule graphs and develop graph-neural-network encoders to learn differentiable representations. Three molecule graph augmentations are proposed: atom masking, bond deletion and subgraph removal. A contrastive estimator maximizes the agreement of augmentations from the same molecule while minimizing the agreement of different molecules. Experiments show that our contrastive learning framework significantly improves the performance of graph-neural-network encoders on various molecular property benchmarks including both classification and regression tasks. Benefiting from pre-training on the large unlabelled database, MolCLR even achieves state of the art on several challenging benchmarks after fine-tuning. In addition, further investigations demonstrate that MolCLR learns to embed molecules into representations that can distinguish chemically reasonable molecular similarities.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of MolCLR.
Fig. 2: Investigation of molecule graph augmentations on classification benchmarks.
Fig. 3: Visualization of molecular representations learned by MolCLR via t-SNE.
Fig. 4: Comparison of MolCLR-learned representations and conventional FPs using the query molecule (PubChem ID 42953211).

Similar content being viewed by others

Data availability

The pre-training data and molecular property prediction benchmarks used in this work are available in the both the CodeOcean capsule at https://doi.org/10.24433/CO.8582800.v149 and the GitHub repository at https://github.com/yuyangw/MolCLR.

Code availability

The code accompanying this work is available in both the CodeOcean capsule at https://doi.org/10.24433/CO.8582800.v149 and the GitHub repository at https://github.com/yuyangw/MolCLR.

References

  1. Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).

    Article  Google Scholar 

  2. Huang, B. & Von Lilienfeld, O. A. Communication: Understanding molecular representations in machine learning: the role of uniqueness and target similarity. J. Chem. Phys. 145, 161102 (2016).

    Article  Google Scholar 

  3. David, L., Thakkar, A., Mercado, R. & Engkvist, O. Molecular representations in AI-driven drug discovery: a review and practical guide. J. Cheminform. 12, 56 (2020).

    Article  Google Scholar 

  4. Oprea, T. I. & Gottfries, J. Chemography: the art of navigating in chemical space. J. Comb. Chem. 3, 157–166 (2001).

    Article  Google Scholar 

  5. Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010).

    Article  Google Scholar 

  6. Duvenaud, D. et al. Convolutional networks on graphs for learning molecular fingerprints. In Proc. 28th International Conference on Neural Information Processing Systems 2224–2232 (MIT Press, 2015).

  7. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In International Conference on Machine Learning 1263–1272 (PMLR, 2017).

  8. Karamad, M. et al. Orbital graph convolutional neural network for material property prediction. Phys. Rev. Mater. 4, 093801 (2020).

    Article  Google Scholar 

  9. Chmiela, S., Sauceda, H. E., Müller, K.-R. & Tkatchenko, A. Towards exact molecular dynamics simulations with machine-learned force fields. Nat. Commun. 9, 3887 (2018).

  10. Deringer, V. L. et al. Realistic atomistic structure of amorphous silicon from machine-learning-driven molecular dynamics. J. Phys. Chem. Lett. 9, 2879–2885 (2018).

    Article  Google Scholar 

  11. Wang, W. & Gómez-Bombarelli, R. Coarse-graining auto-encoders for molecular dynamics. npj Comput. Mater. 5, 125 (2019).

    Article  Google Scholar 

  12. Altae-Tran, H., Ramsundar, B., Pappu, A. S. & Pande, V. Low data drug discovery with one-shot learning. ACS Cent. Sci. 3, 283–293 (2017).

    Article  Google Scholar 

  13. Magar, R., Yadav, P. & Farimani, A. B. Potential neutralizing antibodies discovered for novel corona virus using machine learning. Sci. Rep. 11, 5261 (2021).

    Article  Google Scholar 

  14. Wang, Y., Cao, Z. & Farimani, A. B. Efficient water desalination with graphene nanopores obtained using artificial intelligence. npj 2D Mater. Appl. 5, 66 (2021).

    Article  Google Scholar 

  15. Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comp. Sci. 28, 31–36 (1988).

    Article  Google Scholar 

  16. Krenn, M., Häse, F., Nigam, A., Friederich, P. & Aspuru-Guzik, A. Self-referencing embedded strings (selfies): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1, 045024 (2020).

    Article  Google Scholar 

  17. Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (2017).

  18. Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In International Conference on Learning Representations (2019).

  19. Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A. & Müller, K.-R. SchNet—a deep learning architecture for molecules and materials. J. Chem. Phys. 148, 241722 (2018).

    Article  Google Scholar 

  20. Yang, K. et al. Analyzing learned molecular representations for property prediction. J. Chem. Inf. Model. 59, 3370–3388 (2019).

    Article  Google Scholar 

  21. Kirkpatrick, P. & Ellis, C. Chemical space. Nature 432, 823 (2004).

  22. Bohacek, R. S., McMartin, C. & Guida, W. C. The art and practice of structure-based drug design: a molecular modeling perspective. Med. Res. Rev. 16, 3–50 (1996).

    Article  Google Scholar 

  23. Brown, N., Fiscato, M., Segler, M. H. & Vaucher, A. C. GuacaMol: benchmarking models for de novo molecular design. J. Chem. Inf. Model. 59, 1096–1108 (2019).

    Article  Google Scholar 

  24. Wu, Z. et al. Moleculenet: a benchmark for molecular machine learning. Chem. Sci. 9, 513–530 (2018).

    Article  Google Scholar 

  25. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  Google Scholar 

  26. Vamathevan, J. et al. Applications of machine learning in drug discovery and development. Nat. Rev. Drug Discov. 18, 463–477 (2019).

    Article  Google Scholar 

  27. Unterthiner, T. et al. Deep learning as an opportunity in virtual screening. In Proc. Deep Learning Workshop at NIPS Vol. 27 (2014).

  28. Ma, J., Sheridan, R. P., Liaw, A., Dahl, G. E. & Svetnik, V. Deep neural nets as a method for quantitative structure–activity relationships. J. Chem. Inf. Model. 55, 263–274 (2015).

    Article  Google Scholar 

  29. Ramsundar, B. et al. Massively multitask networks for drug discovery. Preprint at https://arxiv.org/abs/1502.02072 (2015).

  30. Kusner, M. J., Paige, B. & Hernández-Lobato, J. M. Grammar variational autoencoder. In International Conference on Machine Learning 1945–1954 (PMLR, 2017).

  31. Gupta, A. et al. Generative recurrent networks for de novo drug design. Mol. Inf. 37, 1700111 (2018).

    Article  Google Scholar 

  32. Xu, Z., Wang, S., Zhu, F. & Huang, J. Seq2seq fingerprint: an unsupervised deep molecular embedding for drug discovery. In Proc. 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics 285–294 (ACM, 2017).

  33. Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268–276 (2018).

    Article  Google Scholar 

  34. Schwaller, P. et al. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Cent. Sci. 5, 1572–1583 (2019).

    Article  Google Scholar 

  35. Maziarka, Ł. et al. Molecule attention transformer. Preprint at https://arxiv.org/abs/2002.08264 (2020).

  36. Feinberg, E. N. et al. PotentialNet for molecular property prediction. ACS Cent. Sci. 4, 1520–1530 (2018).

    Article  Google Scholar 

  37. Klicpera, J., Groß, J. & Günnemann, S. Directional message passing for molecular graphs. Preprint at https://arxiv.org/abs/2003.03123 (2020).

  38. Gaulton, A. et al. ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res. 40, D1100–D1107 (2012).

    Article  Google Scholar 

  39. Sterling, T. & Irwin, J. J. Zinc 15–ligand discovery for everyone. J. Chem. Inf. Model. 55, 2324–2337 (2015).

    Article  Google Scholar 

  40. Kim, S. et al. Pubchem 2019 update: improved access to chemical data. Nucleic Acids Res. 47, D1102–D1109 (2019).

    Article  Google Scholar 

  41. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. Preprint at https://arxiv.org/abs/1810.04805 (2018).

  42. Chithrananda, S., Grand, G. & Ramsundar, B. ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. Preprint at https://arxiv.org/abs/2010.09885 (2020).

  43. Wang, S., Guo, Y., Wang, Y., Sun, H. & Huang, J. SMILES-BERT: large scale unsupervised pre-training for molecular property prediction. In Proc. 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics 429–436 (ACM, 2019).

  44. Liu, S., Demirel, M. F. & Liang, Y. N-gram graph: simple unsupervised representation for graphs, with applications to molecules. In Thirty-third Conference on Neural Information Processing Systems (NeurIPS, 2019).

  45. Hu, W. et al. Strategies for pre-training graph neural networks. In International Conference on Learning Representations (2020).

  46. You, Y. et al. Graph contrastive learning with augmentations. Adv. Neural Inf. Process. Syst. 33, 5812–5823 (2020).

    Google Scholar 

  47. van den Oord, A., Li, Y. & Vinyals, O. Representation learning with contrastive predictive coding. Preprint at https://arxiv.org/abs/1807.03748 (2018).

  48. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning 1597–1607 (PMLR, 2020).

  49. Wang, Y., Wang, J., Cao, Z. & Farimani, A. B. MolCLR: molecular contrastive learning of representations via graph neural networks. CodeOcean https://doi.org/10.24433/CO.8582800.v1 (2021).

  50. Chen, T., Kornblith, S., Swersky, K., Norouzi, M. & Hinton, G. Big self-supervised models are strong semi-supervised learners. Preprint at https://arxiv.org/abs/2006.10029 (2020).

  51. Do, K., Tran, T. & Venkatesh, S. Graph transformation policy network for chemical reaction prediction. In Proc. 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 750–760 (ACM, 2019).

  52. Jin, W., Barzilay, R. & Jaakkola, T. Hierarchical generation of molecular graphs using structural motifs. In International Conference on Machine Learning 4839–4848 (PMLR, 2020).

  53. Lu, C. et al. Molecular property prediction: a multilevel quantum interactions modeling perspective. In Proc. AAAI Conference on Artificial Intelligence Vol. 33, 1052–1060 (AAAI, 2019).

  54. Van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).

    MATH  Google Scholar 

  55. Yun, S., Jeong, M., Kim, R., Kang, J. & Kim, H. J. Graph transformer networks. In Advances in Neural Information Processing Systems Vol. 32 (eds. Wallach, H. et al.) (Curran Associates, 2019).

  56. Pope, P. E., Kolouri, S., Rostami, M., Martin, C. E. & Hoffmann, H. Explainability methods for graph convolutional neural networks. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 10772–10781 (IEEE, 2019).

  57. Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A. & Vandergheynst, P. Geometric deep learning: going beyond Euclidean data. IEEE Signal Process. Mag. 34, 18–42 (2017).

    Article  Google Scholar 

  58. He, K., Fan, H., Wu, Y., Xie, S. & Girshick, R. Momentum contrast for unsupervised visual representation learning. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 9729–9738 (IEEE, 2020).

  59. Gao, T., Yao, X. & Chen, D. SimCSE: simple contrastive learning of sentence embeddings. Preprint at https://arxiv.org/abs/2104.08821 (2021).

  60. Wang, J., Lu, Y. & Zhao, H. CLOUD: contrastive learning of unsupervised dynamics. Preprint at https://arxiv.org/abs/2010.12488 (2020).

  61. Landrum, G. RDKit: open-source cheminformatics (2006); https://www.rdkit.org/

  62. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).

  63. Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds (2019).

  64. Ho, T. K. Random decision forests. In Proc. 3rd International Conference on Document Analysis and Recognition Vol. 1, 278–282 (IEEE, 1995).

  65. Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273–297 (1995).

    MATH  Google Scholar 

Download references

Acknowledgements

We thank the start-up fund provided by the Department of Mechanical Engineering at Carnegie Mellon University. The work is also funded in part by the Advanced Research Projects Agency-Energy (ARPA-E), US Department of Energy, under award no. DE-AR0001221.

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

    Yuyang Wang, Zhonglin Cao & Amir Barati Farimani

  2. Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA

    Yuyang Wang & Amir Barati Farimani

  3. Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA

    Jianren Wang

  4. Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

    Amir Barati Farimani

Authors
  1. Yuyang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianren Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhonglin Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Amir Barati Farimani
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Y.W., J.W. and A.B.F. designed the research study. Y.W., J.W. and Z.C. developed the method, wrote the code and performed the analysis. All authors wrote and approved the manuscript.

Corresponding author

Correspondence to Amir Barati Farimani.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Alán Aspuru-Guzik and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–3, Discussion and Tables 1–5.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Wang, J., Cao, Z. et al. Molecular contrastive learning of representations via graph neural networks. Nat Mach Intell 4, 279–287 (2022). https://doi.org/10.1038/s42256-022-00447-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-022-00447-x

This article is cited by

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research