Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 385

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Randomized SMILES strings improve the quality of molecular generative models

Open access
Arús-Pous, Josep, Johansson, Simon Viet, Prykhodko, Oleksii, Bjerrum, Esben Jannik, Tyrchan, Christian, Reymond, Jean-Louis, Chen, Hongming, Engkvist, Ola·2019·Journal of Cheminformatics
DOI 10.1186/s13321-019-0393-0

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million, 10,000 and 1000), with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations. To guide the benchmarks new metrics were developed that define how well a model has generalized the training set. The generated chemical space is evaluated with respect to its uniformity, closedness and completeness. Results show that models that use LSTM cells trained with 1 million randomized SMILES, a non-unique molecular string representation, are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space. Specifically, a model was trained with randomized SMILES that was able to generate almost all molecules from GDB-13 with a quasi-uniform probability. Models trained with smaller samples show an even bigger improvement when trained with randomized SMILES models. Additionally, models were trained on molecules obtained from ChEMBL and illustrate again that training with randomized SMILES lead to models having a better representation of the drug-like chemical space. Namely, the model trained with randomized SMILES was able to generate at least double the amount of unique molecules with the same distribution of properties comparing to one trained with canonical SMILES.

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 · 10.1186/s13321-019-0393-0

Cites

6 of 6 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 6 references

Research works printed but not linked: 38

  1. Bohacek RS, McMartin C, Guida WC (2010) ChemInform abstract: the art and practice of structure-based drug design: a molecular modeling perspective. ChemInform. https://doi.org/10.1002/chin.199617316 · doi:10.1002/chin.199617316
  2. Blum LC, Reymond JL (2009) 970 Million druglike small molecules for virtual screening in the chemical universe database GDB-13. J Am Chem Soc 131:8732–8733. https://doi.org/10.1021/ja902302h · DOI · Paper page
  3. Visini R, Arús-Pous J, Awale M, Reymond JL (2017) Virtual exploration of the ring systems chemical universe. J Chem Inf Model 57:2707–2718. https://doi.org/10.1021/acs.jcim.7b00457 · DOI
  4. Ruddigkeit L, Blum LC, Reymond JL (2013) Visualization and virtual screening of the chemical universe database GDB-17. J Chem Inf Model 53:56–65. https://doi.org/10.1021/ci300535x · DOI
  5. Segler MHS, Kogej T, Tyrchan C, Waller MP (2018) Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci 4:120–131. https://doi.org/10.1021/acscentsci.7b00512 · DOI · Paper page
  6. Olivecrona M, Blaschke T, Engkvist O, Chen H (2017) Molecular de-novo design through deep reinforcement learning. J Cheminform. https://doi.org/10.1186/s13321-017-0235-x · DOI · Paper page
  7. Gaulton A, Hersey A, Nowotka ML et al (2017) The ChEMBL database in 2017. Nucleic Acids Res 45:D945–D954. https://doi.org/10.1093/nar/gkw1074 · DOI · Paper page
  8. Awale M, Sirockin F, Stiefl N, Reymond JL (2019) Drug analogs from fragment-based long short-term memory generative neural networks. J Chem Inf Model 59:1347–1356. https://doi.org/10.1021/acs.jcim.8b00902 · DOI
  9. Blaschke T, Olivecrona M, Engkvist O et al (2018) Application of generative autoencoder in de novo molecular design. Mol Inform. https://doi.org/10.1002/minf.201700123 · DOI · Paper page
  10. Guimaraes GL, Sanchez-Lengeling B, Outeiral C, et al (2017) Objective-reinforced generative adversarial networks (organ) for sequence generation models. https://arxiv.org/abs/1705.10843 · arXiv
  11. Prykhodko O, Johansson S, Kotsias P-C, et al (2019) A de novo molecular generation method using latent vector based generative adversarial network. https://doi.org/10.26434/chemrxiv.8299544.v1 · doi:10.26434/chemrxiv.8299544.v1
  12. Chen H, Engkvist O, Wang Y et al (2018) The rise of deep learning in drug discovery. Drug Discov Today 23:1241–1250. https://doi.org/10.1016/j.drudis.2018.01.039 · DOI · Paper page
  13. Weininger D (1988) SMILES, a chemical language and information system: 1: introduction to methodology and encoding rules. J Chem Inf Comput Sci 28:31–36. https://doi.org/10.1021/ci00057a005 · DOI · Paper page
  14. Li Y, Zhang L, Liu Z (2018) Multi-objective de novo drug design with conditional graph generative model. J Cheminform 10:1–24. https://doi.org/10.1186/s13321-018-0287-6 · DOI · Paper page
  15. Jin W, Barzilay R, Jaakkola T (2018) Junction tree variational autoencoder for molecular graph generation. https://arxiv.org/abs/1802.04364 · arXiv
  16. Arús-Pous J, Blaschke T, Ulander S et al (2019) Exploring the GDB-13 chemical space using deep generative models. J Cheminform 11:20. https://doi.org/10.1186/s13321-019-0341-z · DOI
  17. Bjerrum EJ, Sattarov B (2018) Improving chemical autoencoder latent space and molecular de novo generation diversity with heteroencoders. Biomolecules 8:1–17. https://doi.org/10.3390/biom8040131 · DOI
  18. Bjerrum EJ (2017) SMILES enumeration as data augmentation for neural network modeling of molecules. https://arxiv.org/abs/1703.07076 · arXiv
  19. Kimber TB, Engelke S, Tetko I V, et al (2018) Synergy effect between convolutional neural networks and the multiplicity of smiles for improvement of molecular prediction. https://arxiv.org/abs/1812.04439 · arXiv
  20. O’Boyle N, Dalke A (2018) DeepSMILES: an adaptation of SMILES for use in machine-learning of chemical structures. ChemRxiv. https://doi.org/10.26434/chemrxiv.7097960.v1 · DOI
  21. Cho K, van Merrienboer B, Gulcehre C, et al (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. https://doi.org/10.3115/v1/D14-1179 · DOI · Paper page
  22. Weiss G, Goldberg Y, Yahav E (2018) On the practical computational power of finite precision RNNs for language recognition. https://arxiv.org/abs/1805.04908 · DOI · Paper page
  23. Morgan HL (1965) The generation of a unique machine description for chemical structures—a technique developed at chemical abstracts service. J Chem Doc 5:107–113. https://doi.org/10.1021/c160017a018 · DOI · Paper page
  24. Weininger D, Weininger A, Weininger JL (1989) SMILES. 2. Algorithm for generation of unique SMILES notation. J Chem Inf Comput Sci 29:97–101. https://doi.org/10.1021/ci00062a008 · DOI · Paper page
  25. Williams RJ, Zipser D (2008) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280. https://doi.org/10.1162/neco.1989.1.2.270 · DOI · Paper page
  26. Lin J (1991) Divergence measures based on the Shannon entropy. IEEE Trans Inf Theory 37:47–51 · DOI · Paper page
  27. Paszke A, Chanan G, Lin Z et al (2017) Automatic differentiation in PyTorch. Adv Neural Inf Process Syst 30:1–4
  28. Zaharia M, Franklin MJ, Ghodsi A et al (2016) Apache Spark. Commun ACM 59:56–65. https://doi.org/10.1145/2934664 · DOI · Paper page
  29. Preuer K, Renz P, Unterthiner T et al (2018) Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery. J Chem Inf Model 58:1736–1741. https://doi.org/10.1021/acs.jcim.8b00234 · DOI · Paper page
  30. Polykovskiy D, Zhebrak A, Sanchez-Lengeling B, et al (2018) Molecular sets (MOSES): a benchmarking platform for molecular generation models. https://arxiv.org/abs/1811.12823 · arXiv
  31. Ertl P, Schuffenhauer A (2009) Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J Cheminform 1:8. https://doi.org/10.1186/1758-2946-1-8 · DOI · Paper page
  32. Bickerton GR, Paolini GV, Besnard J et al (2012) Quantifying the chemical beauty of drugs. Nat Chem 4:90–98. https://doi.org/10.1038/nchem.1243 · DOI · Paper page
  33. Ertl P, Roggo S, Schuffenhauer A (2008) Natural product-likeness score and its application for prioritization of compound libraries. J Chem Inf Model 48:68–74. https://doi.org/10.1021/ci700286x · DOI · Paper page
  34. Metz L, Poole B, Pfau D, Sohl-Dickstein J (2016) Unrolled generative adversarial networks. https://arxiv.org/abs/1611.02163 · arXiv
  35. Johansson S, Ptykhodko O, Arús-Pous J, et al (2019) Comparison between SMILES-based differential neural computer and recurrent neural network architectures for de novo molecule design. https://doi.org/10.26434/chemrxiv.9758600.v1 · DOI
  36. Ertl P (2003) Cheminformatics analysis of organic substituents: identification of the most common substituents, calculation of substituent properties, and automatic identification of drug-like bioisosteric groups. J Chem Inf Comput Sci 43:374–380. https://doi.org/10.1021/ci0255782 · DOI · Paper page
  37. Jozefowicz R, Vinyals O, Schuster M, et al (2016) Exploring the limits of language modeling. https://arxiv.org/abs/1602.02410 · arXiv
  38. Li Y, Vinyals O, Dyer C et al (2018) Learning deep generative models of graphs. Iclr. https://doi.org/10.1146/annurev-statistics-010814-020120 · DOI · Paper page

Cited by

Metadata

Authors
Arús-Pous, J., Johansson, S. V., Prykhodko, O., Bjerrum, E. J., Tyrchan, C., Reymond, J.-L., Chen, H., & Engkvist, O.
Venue
Journal of Cheminformatics
Publisher
Springer Science and Business Media LLC
Published
2019-11-21
Volume
11
Issue
1
Pages
71-71
ISSN
1758-2946 (ISSN-L)
DOI
10.1186/s13321-019-0393-0
OpenAlex
W2989615256
Cited by
385
References
6
FWCI
26.19
Type
journal article
Language
en
Open access
gold
Licence
Funders
H2020 Marie Skłodowska-Curie Actions (676434)

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.