Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 401

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Optimization of Molecules via Deep Reinforcement Learning

Open access
Zhou, Zhenpeng, Kearnes, Steven, Li, Li, Zare, Richard N., Riley, Patrick·2019·Scientific Reports
DOI 10.1038/s41598-019-47148-x
Open this paper in CoChat — free account

Abstract

We present a framework, which we call Molecule Deep Q-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double Q-learning and randomized value functions). We directly define modifications on molecules, thereby ensuring 100% chemical validity. Further, we operate without pre-training on any dataset to avoid possible bias from the choice of that set. MolDQN achieves comparable or better performance against several other recently published algorithms for benchmark molecular optimization tasks. However, we also argue that many of these tasks are not representative of real optimization problems in drug discovery. Inspired by problems faced during medicinal chemistry lead optimization, we extend our model with multi-objective reinforcement learning, which maximizes drug-likeness while maintaining similarity to the original molecule. We further show the path through chemical space to achieve optimization for a molecule to understand how the model works.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-019-47148-x

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 30

  1. Blaschke, T., Olivecrona, M., Engkvist, O., Bajorath, J. & Chen, H. Application of generative autoencoder in de novo molecular design. Mol. Inform. 37, 1700123 (2018). · DOI · Paper page
  2. Segler, M. H., Kogej, T., Tyrchan, C. & Waller, M. P. Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent. Sci. 4, 120–131 (2017). · DOI · Paper page
  3. Putin, E. et al. Adversarial threshold neural computer for molecular de novo design. Mol. Pharm. 15, 4386–4397 (2018). · DOI
  4. Weininger, D. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988). · DOI · Paper page
  5. Kusner, M. J., Paige, B. & Hernández-Lobato, J. M. Grammar variational autoencoder. arXiv preprint arXiv:1703.01925 (2017). · arXiv
  6. Dai, H., Tian, Y., Dai, B., Skiena, S. & Song, L. Syntax-directed variational autoencoder for structured data. arXiv preprint arXiv:1802.08786 (2018). · arXiv
  7. Li, Y., Vinyals, O., Dyer, C., Pascanu, R. & Battaglia, P. Learning deep generative models of graphs. arXiv preprint arXiv:1803.03324 (2018). · arXiv
  8. Li, Y., Zhang, L. & Liu, Z. Multi-objective de novo drug design with conditional graph generative model. J. Cheminformatics 10, 33 (2018). · DOI · Paper page
  9. Cao, N. De & Kipf, T. Molgan: An implicit generative model for small molecular graphs. arXiv preprint arXiv:1805.11973 (2018). · arXiv
  10. Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. arXiv preprint arXiv:1802.04364 (2018). · arXiv
  11. Olivecrona, M., Blaschke, T., Engkvist, O. & Chen, H. Molecular de-novo design through deep reinforcement learning. J. Cheminformatics 9, 48 (2017). · DOI · Paper page
  12. Guimaraes, G. L., Sanchez-Lengeling, B., Outeiral, C., Farias, P. L. C. & Aspuru-Guzik, A. Objective-reinforced generative adversarial networks (organ) for sequence generation models. arXiv preprint arXiv:1705.10843 (2017). · arXiv
  13. Putin, E. et al. Reinforced adversarial neural computer for de novo molecular design. J. Chem. Inf. Model. (2018). · DOI · Paper page
  14. Popova, M., Isayev, O. & Tropsha, A. Deep reinforcement learning for de novo drug design. Sci. Adv. 4, eaap7885 (2018). · DOI · Paper page
  15. You, J., Liu, B., Ying, R., Pande, V. & Leskovec, J. Graph convolutional policy network for goal-directed molecular graph generation. arXiv preprint arXiv:1806.02473 (2018). · arXiv
  16. Bellman, R. A markovian decision process. J. Math. Mech. 679–684 (1957). · DOI · Paper page
  17. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529 (2015). · DOI · Paper page
  18. Gu, S., Lillicrap, T., Ghahramani, Z., Turner, R. E. & Levine, S. Q-prop: Sample-efficient policy gradient with an off-policy critic. arXiv preprint arXiv:1611.02247 (2016). · arXiv
  19. Osband, I., Blundell, C., Pritzel, A. & Van Roy, B. Deep exploration via bootstrapped DQN in Adv. Neural Inf. Process. Syst. 4026–4034 (2016).
  20. Van Hasselt, H., Guez, A. & Silver, D. Deep reinforcement learning with double Q-Learning. In AAAI 2, 5 (2016). · DOI · Paper page
  21. Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010). · DOI · Paper page
  22. Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
  23. Bickerton, G. R., Paolini, G. V., Besnard, J., Muresan, S. & Hopkins, A. L. Quantifying the chemical beauty of drugs. Nat. Chem. 4, 90 (2012). · DOI · Paper page
  24. Irwin, J. J., Sterling, T., Mysinger, M. M., Bolstad, E. S. & Coleman, R. G. Zinc: a free tool to discover chemistry for biology. J. Chem. Inf. Model. 52, 1757–1768 (2012). · DOI · Paper page
  25. Welch, B. L. The generalization ofstudent’s’ problem when several different population variances are involved. Biometrika 34, 28–35 (1947).
  26. Garg, T., Singh, O., Arora, S. & Murthy, R. Scaffold: a novel carrier for cell and drug delivery, Crit. Rev. Ther. Drug. Carrier. Syst. 29 (2012). · DOI · Paper page
  27. Gaulton, A. et al. The chembl database in 2017. Nucleic Acids Res. 45, D945–D954 (2016). · DOI · Paper page
  28. Haarnoja, T., Tang, H., Abbeel, P. & Levine, S. Reinforcement learning with deep energy-based policies. arXiv preprint arXiv:1702.08165 (2017). · arXiv
  29. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. arXiv preprint arXiv:1704.01212 (2017). · arXiv
  30. Benhenda, M. Chemgan challenge for drug discovery: can ai reproduce natural chemical diversity? arXiv preprint arXiv:1708.08227 (2017). · DOI

Cited by

Metadata

Authors
Zhou, Z., Kearnes, S., Li, L., Zare, R. N., & Riley, P.
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2019-07-24
Volume
9
Issue
1
Pages
10752-10752
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-019-47148-x
OpenAlex
W2962764565
Cited by
401
References
5
FWCI
25.05
Type
journal article
Language
en
Update notices
correction (2020-06-23)
Open access
gold
Licence
Funders
National Science Foundation (CHE-1734082)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.