CoChat
Sign Up
Cited by 421Computational Drug Discovery MethodsMachine Learning in Materials ScienceGenerative Adversarial Networks and Image Synthesis

The DOI matches its Crossref record; 19 of the 23 references it cites were found in a registry or an index.

Molecular generative model based on conditional variational autoencoder for de novo molecular design

Open access
Lim, Jaechang, Ryu, Seongok, Kim, Jin Woo, Kim, Woo Youn·2018·Journal of Cheminformatics
DOI 10.1186/s13321-018-0286-7PMC PMC6041224
Open this paper in CoChat — free accountOpen PDF

Abstract

We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules with five target properties. We were also able to adjust a single property without changing the others and to manipulate it beyond the range of the dataset.

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/s13321-018-0286-7

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Schematic representation of conditional variational autoencoder for molecular design
Fig. 1 Schematic representation of conditional variational autoencoder for molecular designCC BY · PubMed Central
Fig. 2 Distribution of molecular weight, LogP, HBD, HBA, and TPSA in the total dataset (500,000)
Fig. 2 Distribution of molecular weight, LogP, HBD, HBA, and TPSA in the total dataset (500,000)CC BY · PubMed Central
Fig. 3 Molecules generated by the CVAE with the condition vector made of the five target properties of a Aspirin and b Tamiflu
Fig. 3 Molecules generated by the CVAE with the condition vector made of the five target properties of a Aspirin and b TamifluCC BY · PubMed Central
Fig. 4 Molecules generated by the CVAE with the condition vector made of the five target properties of Aspirin and the latent vector slightly modified from that of Aspirin
Fig. 4 Molecules generated by the CVAE with the condition vector made of the five target properties of Aspirin and the latent vector slightly modified from that of AspirinCC BY · PubMed Central
Fig. 5 Molecules generated by the CVAE with the condition vector made of MW, HBD, HBA, and TPSA of Tamiflu and continuously changing LogP
Fig. 5 Molecules generated by the CVAE with the condition vector made of MW, HBD, HBA, and TPSA of Tamiflu and continuously changing LogPCC BY · PubMed Central
Fig. 6 a Molecules with LogP larger than 5.5. b Molecules with TPSA larger than 165
Fig. 6 a Molecules with LogP larger than 5.5. b Molecules with TPSA larger than 165CC BY · PubMed Central
Fig. 7 Distribution of a LogP and b TPSA for 1000 randomly selected molecules in training set and 1000 generated molecules with LogP and TPSA outside of the range of the dataset, respectively
Fig. 7 Distribution of a LogP and b TPSA for 1000 randomly selected molecules in training set and 1000 generated molecules with LogP and TPSA outside of the range of the dataset, respectivelyCC BY · PubMed Central
Fig. 8 The latent space of 1000 randomly selected molecules with MW, LogP and TPSA values
Fig. 8 The latent space of 1000 randomly selected molecules with MW, LogP and TPSA valuesCC BY · PubMed Central

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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 23 references

Research works printed but not linked: 10

  1. Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2015) Adversarial autoencoders. arXiv:1511.05644 · arXiv
  2. Blaschke T, Olivecrona M, Engkvist O, Bajorath J, Chen H (2017) Application of generative autoencoder in de novo molecular design. arXiv:1711.07839 · arXiv
  3. Bjerrum EJ, Threlfall R (2017) Molecular generation with recurrent neural networks (RNNs). arXiv:1705.04612 · arXiv
  4. Guimaraes GL, Sanchez-Lengeling B, Outeiral C, Farias PLC, Aspuru-Guzik A (2017) Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models. arXiv:1705.10843 · arXiv
  5. Jaques N, Gu S, Bahdanau D, Hernández-Lobato JM, Turner RE, Eck D (2016) Sequence tutor: conservative fine-tuning of sequence generation models with KL-control. arXiv:1611.02796 · arXiv
  6. D.P Kingma, D.J Rezende, S Mohamed, M Welling, (2014) Semi-supervised learning with deep generative models, pp 1–9. arXiv:1406.5298 · arXiv
  7. Kusner MJ, Paige B, Hernández-Lobato JM (2017) Grammar variational autoencoder. arXiv:1703.01925 · arXiv
  8. Wang H, Wang J, Wang J, Zhao M, Zhang W, Zhang F, Xie X, Guo M (2017) GraphGAN: graph representation learning with generative adversarial nets. arXiv:1711.08267 · arXiv
  9. You J, Ying R, Ren X, Hamilton WL, Leskovec J (2018) GraphRNN: a deep generative model for graphs. arXiv:1802.08773 · arXiv
  10. W Jin, R Barzilay, T Jaakkola (2018) Junction tree variational autoencoder for molecular graph generation. arXiv:1802.04364 · arXiv

Cited by

Sorted by citations

Items 301–400 of 420

Related

See all

Metadata

Authors
Lim, J., Ryu, S., Kim, J. W., & Kim, W. Y.
Affiliations
Korea Advanced Institute of Science and Technology (KR)
Corresponding author
  • Kim, Jin Woo
  • Kim, Woo Youn
ORCID
Venue
Journal of Cheminformatics
Publisher
Springer Science and Business Media LLC
Published
2018-07-11
Volume
10
Issue
1
Pages
31-31
ISSN
1758-2946 (ISSN-L)
DOI
10.1186/s13321-018-0286-7
PMC
PMC6041224
OpenAlex
W2808177712
Cited by
421
References
23
Citations by year
2026: 45 · 2025: 62 · 2024: 67 · 2023: 60 · 2022: 55 · 2021: 62 · 2020: 41 · 2019: 26 · 2018: 1
FWCI
24.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Cheminformatics (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University)
  • Figshare (cc-by)
Funders
National Research Foundation of Korea (NRF-2017R1E1A1A01078109)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
Keywords
conditional variational autoencoder, de novo molecular design, generative models, latent space control, drug-like molecules, generative adversarial networks

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