druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico

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...

Full description

Saved in:
Bibliographic Details
Published in:Molecular pharmaceutics Vol. 14; no. 9; p. 3098
Main Authors: Kadurin, Artur, Nikolenko, Sergey, Khrabrov, Kuzma, Aliper, Alex, Zhavoronkov, Alex
Format: Journal Article
Language:English
Published: United States 05.09.2017
Subjects:
Artificial Intelligence
Computer Simulation
Concept Formation
Learning
Models, Theoretical
Neural Networks (Computer)
generative adversarial network
deep learning
adversarial autoencoder
drug discovery
variational autoencoder
ISSN:1543-8392, 1543-8392
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1543-8392
1543-8392
DOI:10.1021/acs.molpharmaceut.7b00346