Molecular graph convolutions: moving beyond fingerprints

Abstract

Molecular “fingerprints” encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph—atoms, bonds, distances, etc.—which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

References

  1. 1.

    Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software. http://tensorflow.org

  2. 2.

    Ballester PJ, Richards WG (2007) Ultrafast shape recognition to search compound databases for similar molecular shapes. J Comput Chem 28(10):1711–1723

    CAS  Article  Google Scholar 

  3. 3.

    Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. arXiv:1312.6203

  4. 4.

    Carhart RE, Smith DH, Venkataraghavan R (1985) Atom pairs as molecular features in structure-activity studies: definition and applications. J Chem Inf Comput Sci 25(2):64–73

    CAS  Article  Google Scholar 

  5. 5.

    Dahl G (2012) Deep learning how I did it: Merck 1st place interview.http://blog.kaggle.com/2012/11/01/deep-learning-how-i-did-it-merck-1st-place-interview

  6. 6.

    Dahl GE, Jaitly N, Salakhutdinov R (2014) Multi-task neural networks for QSAR predictions. arXiv:1406.1231

  7. 7.

    Dieleman S (2015) Classifying plankton with deep neural networks. 17 Mar 2015. http://benanne.github.io/2015/03/17/plankton.html

  8. 8.

    Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159

    Google Scholar 

  9. 9.

    Duvenaud DK, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T, Aspuru-Guzik A, Adams RP (2015) Convolutional networks on graphs for learning molecular fingerprints. In: Advances in neural information processing systems, pp 2224–2232

  10. 10.

    Gasteiger J, Marsili M (1980) Iterative partial equalization of orbital electronegativity–a rapid access to atomic charges. Tetrahedron 36(22):3219–3228

    CAS  Article  Google Scholar 

  11. 11.

    Hawkins PCD, Skillman AG, Nicholls A (2007) Comparison of shape-matching and docking as virtual screening tools. J Med Chem 50(1):74–82

    CAS  Article  Google Scholar 

  12. 12.

    Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167

  13. 13.

    Jain AN, Nicholls A (2008) Recommendations for evaluation of computational methods. J Comput Aided Mol Des 22(3–4):133–139

    CAS  Article  Google Scholar 

  14. 14.

    Landrum G (2014) RDKit: open-source cheminformatics. http://www.rdkit.org

  15. 15.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    CAS  Article  Google Scholar 

  16. 16.

    Lusci A, Pollastri G, Baldi P (2013) Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. J Chem Inf Model 53(7):1563–1575

    CAS  Article  Google Scholar 

  17. 17.

    Ma J, Sheridan RP, Liaw A, Dahl GE, Svetnik V (2015) Deep neural nets as a method for quantitative structure–activity relationships. J Chem Inf Model 55(2):263–274

    CAS  Article  Google Scholar 

  18. 18.

    Masci J, Boscaini D, Bronstein M, Vandergheynst P (2015) Geodesic convolutional neural networks on riemannian manifolds. In: Proceedings of the IEEE international conference on computer vision workshops, pp 37–45

  19. 19.

    Mayr A, Klambauer G, Unterthiner T, Hochreiter S (2015) Deeptox: toxicity prediction using deep learning. Front Environ Sci 3:80

    Google Scholar 

  20. 20.

    McGill R, Tukey JW, Larsen WA (1978) Variations of box plots. Am Stat 32(1):12–16

    Google Scholar 

  21. 21.

    Merkwirth C, Lengauer T (2005) Automatic generation of complementary descriptors with molecular graph networks. J Chem Inf Model 45(5):1159–1168

    CAS  Article  Google Scholar 

  22. 22.

    Micheli A (2009) Neural network for graphs: a contextual constructive approach. IEEE Trans Neural Netw 20(3):498–511

    Article  Google Scholar 

  23. 23.

    Muchmore SW, Souers AJ, Akritopoulou-Zanze I (2006) The use of three-dimensional shape and electrostatic similarity searching in the identification of a melanin-concentrating hormone receptor 1 antagonist. Chem Biol Drug Des 67(2):174–176

    CAS  Article  Google Scholar 

  24. 24.

    Mysinger MM, Carchia M, Irwin JJ, Shoichet BK (2012) Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J Med Chem 55(14):6582–6594

    CAS  Article  Google Scholar 

  25. 25.

    Nicholls A, McGaughey GB, Sheridan RP, Good AC, Warren G, Mathieu M, Muchmore SW, Brown SP, Grant JA, Haigh JA et al (2010) Molecular shape and medicinal chemistry: a perspective. J Med Chem 53(10):3862–3886

    CAS  Article  Google Scholar 

  26. 26.

    OpenEye GraphSim Toolkit. OpenEye Scientific Software, Santa Fe, NM. http://www.eyesopen.com

  27. 27.

    Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830

    Google Scholar 

  28. 28.

    Petrone PM, Simms B, Nigsch F, Lounkine E, Kutchukian P, Cornett A, Deng Z, Davies JW, Jenkins JL, Glick M (2012) Rethinking molecular similarity: comparing compounds on the basis of biological activity. ACS Chem Biol 7(8):1399–1409

    CAS  Article  Google Scholar 

  29. 29.

    Ramsundar B, Kearnes S, Riley P, Webster D, Konerding D, Pande V (2015) Massively multitask networks for drug discovery. arXiv:1502.02072

  30. 30.

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

    CAS  Article  Google Scholar 

  31. 31.

    Rohrer SG, Baumann K (2009) Maximum unbiased validation (MUV) data sets for virtual screening based on pubchem bioactivity data. J Chem Inf Model 49(2):169–184

    CAS  Article  Google Scholar 

  32. 32.

    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  33. 33.

    Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80

    Article  Google Scholar 

  34. 34.

    Seabold S, Perktold J (2010) Statsmodels: econometric and statistical modeling with python. In: Proceedings of the 9th Python in science conference, pp 57–61

  35. 35.

    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    Google Scholar 

  36. 36.

    Swamidass JS, Azencott C-A, Lin T-W, Gramajo H, Tsai S-C, Baldi P (2009) Influence relevance voting: an accurate and interpretable virtual high throughput screening method. J Chem Inf Model 49(4):756–766

    CAS  Article  Google Scholar 

  37. 37.

    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: CVPR 2015. arxiv.org/abs/1409.4842

  38. 38.

    Todeschini R, Consonni V (2009) Molecular descriptors for chemoinformatics, volume 41 (2 volume set), vol 41. Wiley, New York

    Google Scholar 

  39. 39.

    Truchon J-F, Bayly CI (2007) Evaluating virtual screening methods: good and bad metrics metrics for the âĂIJearly recognitionâĂİ problem. J Chem Inf Model 47(2):488–508

    CAS  Article  Google Scholar 

  40. 40.

    Wallach I, Dzamba M, Heifets A (2015) AtomNet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery. arXiv:1510.02855

  41. 41.

    Yanli W, Xiao J, Suzek TO, Zhang J, Wang J, Zhou Z, Han L, Karapetyan K, Dracheva S, Shoemaker BA et al (2012) PubChem’s BioAssay database. Nucl Acids Res 40(D1):D400–D412

    Article  Google Scholar 

  42. 42.

    Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353

    Article  Google Scholar 

Download references

Acknowledgments

We thank Bharath Ramsundar, Brian Goldman, and Robert McGibbon for helpful discussion. We also acknowledge Manjunath Kudlur, Derek Murray, and Rajat Monga for assistance with TensorFlow. S.K. was supported by internships at Google Inc. and Vertex Pharmaceuticals Inc. Additionally, we acknowledge use of the Stanford BioX3 cluster supported by NIH S10 Shared Instrumentation Grant 1S10RR02664701. S.K. and V.P. also acknowledge support from from NIH 5U19AI109662-02.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Steven Kearnes.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1207 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kearnes, S., McCloskey, K., Berndl, M. et al. Molecular graph convolutions: moving beyond fingerprints. J Comput Aided Mol Des 30, 595–608 (2016). https://doi.org/10.1007/s10822-016-9938-8

Download citation

Keywords

  • Machine learning
  • Virtual screening
  • Deep learning
  • Artificial neural networks
  • Molecular descriptors