Molecular Pharmaceutics, volume 14, issue 9, pages 3098-3104
druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico
Artur Kadurin
1, 2, 3
,
Sergey I. Nikolenko
2, 3, 4
,
Kuzma Khrabrov
5
,
Alexander Aliper
1
,
Alex Zhavoronkov
1, 6, 7
5
Search
Department, Mail.Ru Group Ltd., Moscow 125167, Russia
|
6
The Biogerontology Research Foundation, Trevissome Park, Truro TR4 8UN, U.K.
|
Publication type: Journal Article
Publication date: 2017-08-04
Journal:
Molecular Pharmaceutics
Quartile SCImago
Q1
Quartile WOS
Q1
Impact factor: 4.5
ISSN: 15438384, 15438392
Drug Discovery
Pharmaceutical Science
Molecular Medicine
Abstract
Deep generative adversarial networks (GANs) are the emerging technology in drug discovery and biomarker development. In our recent work, we demonstrated a proof-of-concept of implementing deep generative adversarial autoencoder (AAE) to identify new molecular fingerprints with predefined anticancer properties. Another popular generative model is the variational autoencoder (VAE), which is based on deep neural architectures. In this work, we developed an advanced AAE model for molecular feature extraction problems, and demonstrated its advantages compared to VAE in terms of (a) adjustability in generating molecular fingerprints; (b) capacity of processing very large molecular data sets; and (c) efficiency in unsupervised pretraining for regression model. Our results suggest that the proposed AAE model significantly enhances the capacity and efficiency of development of the new molecules with specific anticancer properties using the deep generative models.
Top-30
Journals
5
10
15
20
25
|
|
Journal of Chemical Information and Modeling
24 publications, 6.23%
|
|
Journal of Cheminformatics
9 publications, 2.34%
|
|
International Journal of Molecular Sciences
9 publications, 2.34%
|
|
Frontiers in Pharmacology
8 publications, 2.08%
|
|
Drug Discovery Today
8 publications, 2.08%
|
|
Briefings in Bioinformatics
8 publications, 2.08%
|
|
Molecular Informatics
7 publications, 1.82%
|
|
Journal of Medicinal Chemistry
7 publications, 1.82%
|
|
Molecular Pharmaceutics
6 publications, 1.56%
|
|
Methods in Molecular Biology
5 publications, 1.3%
|
|
Aging
4 publications, 1.04%
|
|
Molecules
4 publications, 1.04%
|
|
Scientific Reports
4 publications, 1.04%
|
|
Molecular Diversity
4 publications, 1.04%
|
|
Computers in Biology and Medicine
4 publications, 1.04%
|
|
ACS Omega
4 publications, 1.04%
|
|
Nature Machine Intelligence
3 publications, 0.78%
|
|
Journal of Computer-Aided Molecular Design
3 publications, 0.78%
|
|
Wiley Interdisciplinary Reviews: Computational Molecular Science
3 publications, 0.78%
|
|
Chemical Science
3 publications, 0.78%
|
|
Digital Discovery
3 publications, 0.78%
|
|
Expert Opinion on Drug Discovery
3 publications, 0.78%
|
|
Lecture Notes in Computer Science
3 publications, 0.78%
|
|
Expert Systems with Applications
3 publications, 0.78%
|
|
Journal of Physical Chemistry Letters
3 publications, 0.78%
|
|
Current Pharmaceutical Design
2 publications, 0.52%
|
|
Mini-Reviews in Medicinal Chemistry
2 publications, 0.52%
|
|
Oncotarget
2 publications, 0.52%
|
|
Frontiers in Genetics
2 publications, 0.52%
|
|
5
10
15
20
25
|
Publishers
10
20
30
40
50
60
70
|
|
Elsevier
68 publications, 17.66%
|
|
Springer Nature
64 publications, 16.62%
|
|
American Chemical Society (ACS)
61 publications, 15.84%
|
|
Wiley
28 publications, 7.27%
|
|
Institute of Electrical and Electronics Engineers (IEEE)
27 publications, 7.01%
|
|
MDPI
18 publications, 4.68%
|
|
Frontiers Media S.A.
16 publications, 4.16%
|
|
Royal Society of Chemistry (RSC)
13 publications, 3.38%
|
|
Bentham Science Publishers Ltd.
11 publications, 2.86%
|
|
Oxford University Press
11 publications, 2.86%
|
|
Cold Spring Harbor Laboratory
10 publications, 2.6%
|
|
Taylor & Francis
9 publications, 2.34%
|
|
Impact Journals
6 publications, 1.56%
|
|
IGI Global
4 publications, 1.04%
|
|
IOP Publishing
3 publications, 0.78%
|
|
Public Library of Science (PLoS)
3 publications, 0.78%
|
|
American Physical Society (APS)
2 publications, 0.52%
|
|
Association for Computing Machinery (ACM)
2 publications, 0.52%
|
|
Hindawi Limited
1 publication, 0.26%
|
|
Acoustical Society of America (ASA)
1 publication, 0.26%
|
|
PeerJ
1 publication, 0.26%
|
|
Institution of Engineering and Technology (IET)
1 publication, 0.26%
|
|
World Scientific
1 publication, 0.26%
|
|
Newlands Press Ltd
1 publication, 0.26%
|
|
SAGE
1 publication, 0.26%
|
|
Cambridge University Press
1 publication, 0.26%
|
|
American Association for the Advancement of Science (AAAS)
1 publication, 0.26%
|
|
American Medical Association (AMA)
1 publication, 0.26%
|
|
IntechOpen
1 publication, 0.26%
|
|
10
20
30
40
50
60
70
|
- We do not take into account publications without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
Are you a researcher?
Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Kadurin A. et al. druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico // Molecular Pharmaceutics. 2017. Vol. 14. No. 9. pp. 3098-3104.
GOST all authors (up to 50)
Copy
Kadurin A., Nikolenko S. I., Khrabrov K., Aliper A., Zhavoronkov A. druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico // Molecular Pharmaceutics. 2017. Vol. 14. No. 9. pp. 3098-3104.
Cite this
RIS
Copy
TY - JOUR
DO - 10.1021/acs.molpharmaceut.7b00346
UR - https://doi.org/10.1021/acs.molpharmaceut.7b00346
TI - druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico
T2 - Molecular Pharmaceutics
AU - Khrabrov, Kuzma
AU - Zhavoronkov, Alex
AU - Kadurin, Artur
AU - Nikolenko, Sergey I.
AU - Aliper, Alexander
PY - 2017
DA - 2017/08/04
PB - American Chemical Society (ACS)
SP - 3098-3104
IS - 9
VL - 14
SN - 1543-8384
SN - 1543-8392
ER -
Cite this
BibTex
Copy
@article{2017_Kadurin,
author = {Kuzma Khrabrov and Alex Zhavoronkov and Artur Kadurin and Sergey I. Nikolenko and Alexander Aliper},
title = {druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico},
journal = {Molecular Pharmaceutics},
year = {2017},
volume = {14},
publisher = {American Chemical Society (ACS)},
month = {aug},
url = {https://doi.org/10.1021/acs.molpharmaceut.7b00346},
number = {9},
pages = {3098--3104},
doi = {10.1021/acs.molpharmaceut.7b00346}
}
Cite this
MLA
Copy
Kadurin, Artur, et al. “druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico.” Molecular Pharmaceutics, vol. 14, no. 9, Aug. 2017, pp. 3098-3104. https://doi.org/10.1021/acs.molpharmaceut.7b00346.