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

By Artur Kadurin, Sergey I. Nikolenko, Kuzma Khrabrov, Alex Aliper, A. Zhavoronkov. Molecular Pharmaceutics, 2017

520 citations recorded by the source corpus.

Subfields: Biophysics, Computational Theory and Mathematics, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/3b1115226eb73af88681fc2dac9bd35ff01c8991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

Citations in the corpus

Converging blockchain and next-generation artificial intelligence technologies to decentralize and accelerate biomedical research and healthcare (2015, background): “As a continuation of this work, authors proposed an enhanced architecture that also included additional molecular parameters such as solubility and enabled the generation of more chemically diverse molecules [42].”
Molecular generative model based on conditional variational autoencoder for de novo molecular design (2018, methodology): “[14] compared the VAE and AAE as a molecular generation model in terms of the reconstruction error and variability of the output molecular fingerprints.”
Artificial intelligence in drug development: present status and future prospects. (2019, background): “Additionally, the advances in precision medicine have resulted in the creation of next-generation AI that offers the ability to design drug molecules from the generative adversarial networks (GANs) [62].”
The rise of deep learning in drug discovery. (2018, methodology): “Following on from Go´mez-Bombarelli’s work, Kadurin et al. [61] used VAE as a molecular descriptor generator coupled with a generative adversarial network (GAN) [62], a special NN architecture, to generate new structures that were claimed to have promising speciﬁc anti-cancer properties.”
Deep Learning in Pharmacogenomics: From Gene Regulation to Patient Stratification (2018, unknown): “design molecules with desired chemical properties [109-111].”
The rise of artificial intelligence in healthcare applications (2020, background): “These results suggest a substantial improvement in the efficiency in generating new drug designs with specific properties [21].”
A Structure-Based Drug Discovery Paradigm (2019, background): “[122] have generated new structures having specific anticancer properties by coupling the generative adversarial network (GAN) with VAE.”