Application of Generative Autoencoder in De Novo Molecular Design
Open accessAbstract
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.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
Blaschke et al. applied adversarial autoencoders and Bayesian optimization to generate ligands specific to the dopamine type 2 receptor.
“Blaschke et al. also applied adversarial autoencoders and Bayesian optimization to generate ligands specific to the dopamine type 2 receptor [22].”
From The rise of artificial intelligence in healthcare applications (2020) · cites this paper as [22]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 19 · Cited by 411
Research works printed but not linked: 8
- [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. · arXiv
- [15]H. Abdi, L. J. Williams, Wiley Interdiscip. Rev. Comput. Stat. 2010, 2, 433– 459.
- [18]I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, 2016.
- [21]T. Lei, R. Barzilay, T. Jaakkola, ArXiv:1508.04112 Cs 2015. · arXiv
- [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.
- [26]R. J. Williams, D. Zipser, Neural Comput. 1989, 1, 270– 280.
- [30]C. E. Rasmussen, C. K. I. Williams, Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning), The MIT Press, 2005.
- [31]D. R. Jones, M. Schonlau, W. J. Welch, J. Glob. Optim. 1998, 13, 455– 492.
- Authors
- Blaschke, T., Olivecrona, M., Engkvist, O., Bajorath, J., & Chen, H.
- Affiliations
- University of Bonn (DE)
- AstraZeneca (Sweden) (SE)
- Corresponding author
- Blaschke, Thomas
- Chen, Hongming
- Venue
- Molecular Informatics
- Publisher
- Wiley
- Published
- 2017-12-13
- Volume
- 37
- Issue
- 1-2
- ISSN
- 1868-1743 (ISSN-L)
- 1868-1751
- PMC
- PMC5836887
- OpenAlex
- W2963445908
- Cited by
- 411
- References
- 19
- Citations by year
- 2026: 16 · 2025: 26 · 2024: 38 · 2023: 50 · 2022: 53 · 2021: 91 · 2020: 65 · 2019: 42 · 2018: 28 · 2017: 2
- FWCI
- 28.11
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Molecular Informatics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- European Union's Horizon 2020 research and innovation program (676434)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › History and advancements in chemistry
- Keywords
- generative autoencoders, de novo molecular design, latent space, molecular similarity, structure-activity relationship
- MeSH terms
- Deep Learning, Drug Design, Quantitative Structure-Activity Relationship
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
