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

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 d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of cheminformatics Jg. 10; H. 1; S. 31 - 9
Hauptverfasser: Lim, Jaechang, Ryu, Seongok, Kim, Jin Woo, Kim, Woo Youn
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 11.07.2018
BioMed Central Ltd
Springer Nature B.V
BMC
Schlagworte:
Chemistry
Chemistry and Materials Science
Computational Biology/Bioinformatics
Computer Applications in Chemistry
Conditional variational autoencoder
Deep learning
Documentation and Information in Chemistry
Drug targeting
Encoders (Computers)
Molecular chains
Molecular design
Research Article
Theoretical and Computational Chemistry
Conditional variational autoencoder
Deep learning
Molecular design
ISSN:1758-2946, 1758-2946
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1758-2946
1758-2946
DOI:10.1186/s13321-018-0286-7