Application of Generative Autoencoder in De Novo Molecular Design

Abstract

A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate the potential use of autoencoder, a deep learning methodology, for de novo molecular design. Various generative autoencoders were used to map molecule structures into a continuous latent space and vice versa and their performance as structure generator was assessed. Our results show that the latent space preserves chemical similarity principle and thus can be used for the generation of analogue structures. Furthermore, the latent space created by autoencoders were searched systematically to generate novel compounds with predicted activity against dopamine receptor type 2 and compounds similar to known active compounds not included in the trainings set were identified.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 38

1. 1.

   J. Ma, R. P. Sheridan, A. Liaw, G. E. Dahl, V. Svetnik, J. Chem. Inf. Model. 2015, 55, 263–274.

   Not in our library10.1021/ci500747n

2. 2.

   M. H. S. Segler, T. Kogej, C. Tyrchan, M. P. Waller, ArXiv:1701.01329 Phys. Stat 2017.

   Not in our library

3. 3.

   W. Yuan, D. Jiang, D. K. Nambiar, L. P. Liew, M. P. Hay, J. Bloomstein, P. Lu, B. Turner, Q.-T. Le, R. Tibshirani, et al., J. Chem. Inf. Model. 2017, 57, 875–882.

   Not in our library10.1021/acs.jcim.6b00754

4. 4.

   N. Jaques, S. Gu, D. Bahdanau, J. M. H. Lobato, R. E. Turner, D. Eck, ArXiv:1611.02796 Cs 2016.

   Not in our library

5. 5.

   G. R. Bickerton, G. V. Paolini, J. Besnard, S. Muresan, A. L. Hopkins, Nat. Chem. 2012, 4, 90–98.

   Not in our library10.1038/nchem.1243

6. 6.
   Molecular de-novo design through deep reinforcement learning · 2017

   No notice
7. 7.

   C. J. Churchwell, M. D. Rintoul, S. Martin, D. P. Visco, A. Kotu, R. S. Larson, L. O. Sillerud, D. C. Brown, J.-L. Faulon, J. Mol. Graphics 2004, 22, 263–273.

   Not in our library10.1016/j.jmgm.2003.10.002

8. 8.

   W. W. Wong, F. J. Burkowski, J. Cheminf. 2009, 1, 4.

   Not in our library10.1186/1758-2946-1-4

9. 9.

   T. Miyao, H. Kaneko, K. Funatsu, J. Chem. Inf. Model. 2016, 56, 286–299.

   Not in our library10.1021/acs.jcim.5b00628

10. 10.

    L. Douali, D. Villemin, D. Cherqaoui, J. Chem. Inf. Comput. Sci. 2003, 43, 1200–1207.

    Not in our library10.1021/ci034047q

11. 11.

    T. Miyao, K. Funatsu, J. Bajorath, F1000Research 2017, 6, 1285.

    Not in our library10.12688/f1000research.12228.1

12. 12.

    R. Gómez-Bombarelli, D. Duvenaud, J. M. Hernández-Lobato, J. Aguilera-Iparraguirre, T. D. Hirzel, R. P. Adams, A. Aspuru-Guzik, ArXiv:1610.02415 Phys. 2016.

    Not in our library

13. 13.

    A. Kadurin, S. Nikolenko, K. Khrabrov, A. Aliper, A. Zhavoronkov, Mol. Pharm. 2017.

    Not in our library10.1021/acs.molpharmaceut.7b00346

14. 14.

    I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, ArXiv:1406.2661 Cs Stat 2014.

    Not in our library

15. 15.

    H. Abdi, L. J. Williams, Wiley Interdiscip. Rev. Comput. Stat. 2010, 2, 433–459.

    Not in our library

16. 16.

    M. Scholz, M. Fraunholz, J. Selbig, SpringerLink 2008, 44–67.

    Not in our library

17. 17.

    D. Duvenaud, D. Maclaurin, J. Aguilera-Iparraguirre, R. Gómez-Bombarelli, T. Hirzel, A. Aspuru-Guzik, R. P. Adams, ArXiv:1509.09292 Cs Stat 2015.

    Not in our library

18. 18.

    I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016.

    Not in our library

19. 19.

    S. Hochreiter, J. Schmidhuber, Neural Comput 1997, 9, 1735–1780.

    Not in our library10.1162/neco.1997.9.8.1735

20. 20.

    J. Chung, C. Gulcehre, K. Cho, Y. Bengio, ArXiv:1412.3555 Cs 2014.

    Not in our library

21. 21.

    T. Lei, R. Barzilay, T. Jaakkola, ArXiv:1508.04112 Cs 2015.

    Not in our library

22. 22.

    P. Y. Simard, D. Steinkraus, J. C. Platt, in Proc. Seventh Int. Conf. Doc. Anal. Recognit. – Vol. 2, IEEE Computer Society, Washington, DC, USA, 2003, 958.

    Not in our library

23. 23.

    G. Klambauer, T. Unterthiner, A. Mayr, S. Hochreiter, ArXiv:1706.02515 Cs Stat 2017.

    Not in our library

24. 24.

    D. P. Kingma, M. Welling, ArXiv:1312.6114 Cs Stat 2013.

    Not in our library

25. 25.

    “PyTorch,” can be found under http://pytorch.org/, 2017.

    Not in our library

26. 26.

    R. J. Williams, D. Zipser, Neural Comput. 1989, 1, 270–280.

    Not in our library

27. 27.

    H. Jaeger, A Tutorial on Training Recurrent Neural Networks, Covering BPPT, RTRL, EKF and the “Echo State Network” Approach, German National Research Center For Information Technology, GMD Report 159, 2002.

    Not in our library

28. 28.

    A. Makhzani, J. Shlens, N. Jaitly, I. Goodfellow, B. Frey, ArXiv:1511.05644 Cs 2015.

    Not in our library

29. 29.

    The GPyOpt authors, GPyOpt: A Bayesian Optimization Framework in Python, 2016.

    Not in our library

30. 30.

    C. E. Rasmussen, C. K. I. Williams, Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning), The MIT Press, 2005.

    Not in our library

31. 31.

    D. R. Jones, M. Schonlau, W. J. Welch, J. Glob. Optim. 1998, 13, 455–492.

    Not in our library

32. 32.

    “Daylight Theory: SMILES,” can be found under http://www.daylight.com/dayhtml/doc/theory/theory.smiles.html, 2017.

    Not in our library

33. 33.

    “RDKit,” can be found under http://www.rdkit.org/, 2017.

    Not in our library

34. 34.

    A. Gaulton, L. J. Bellis, A. P. Bento, J. Chambers, M. Davies, A. Hersey, Y. Light, S. McGlinchey, D. Michalovich, B. Al-Lazikani, et al., Nucleic Acids Res. 2012, 40, D1100–D1107.

    Not in our library10.1093/nar/gkr777

35. 35.

    D. P. Kingma, J. Ba, ArXiv:1412.6980 Cs 2014.

    Not in our library

36. 36.
    ExCAPE-DB: an integrated large scale dataset facilitating Big Data analysis in chemogenomics · 2017

    Corrected
37. 37.

    “scikit-learn” can be found under http://scikit-learn.org/stable/index.html, 2017.

    Not in our library

38. 38.

    D. Rogers, M. Hahn, J. Chem. Inf. Model. 2010, 50, 742–754.

    Not in our library10.1021/ci100050t

Cited by papers we hold 10

• SMILES-based deep generative scaffold decorator for de-novo drug design · 2020
  No notice
• Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models · 2020
  No notice
• Constrained Bayesian optimization for automatic chemical design using variational autoencoders · 2020
  No notice
• A de novo molecular generation method using latent vector based generative adversarial network · 2019
  No notice
• Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations · 2019
  No notice
• Randomized SMILES strings improve the quality of molecular generative models · 2019
  No notice
• Optimization of Molecules via Deep Reinforcement Learning · 2019
  Corrected
• Artificial Intelligence in Drug Design · 2018
  No notice
• Multi-objective de novo drug design with conditional graph generative model · 2018
  No notice
• Molecular generative model based on conditional variational autoencoder for de novo molecular design · 2018
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.