EUVIMEDEUVIMED entdecken
Crossref

Generative Adversarial Networks for De Novo Molecular Design

Young Jae Lee, Hyungu Kahng, Seoung Bum Kim iD

Molecular Informatics · 2021-10 · 40 (10)

DOI: 10.1002/minf.202100045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, online erschienen am 06.07.2021. Verfasst von Young Jae Lee und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Industrial, Management Engineering Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea. Hauptthemen laut MEDLINE: Molecular Structure. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT, South Korea, Ministry of Culture, Sports and Tourism.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the chemical industry, the generation of novel molecular structures with beneficial pharmacological and physicochemical properties in de novo molecular design is a critical problem. The advent of deep learning and neural generative models has recently enabled significant achievements in constructing molecular design models in de novo design. Consequently, studies on new generative models continue to generate molecules that exhibit more useful chemical properties. In this study, we propose a method for de novo design that utilizes generative adversarial networks based on reinforcement learning for realistic molecule generation. This method learns to reproduce the training data distribution of simplified molecular‐input line‐entry system strings. The proposed method is demonstrated to effectively generate novel molecular structures from five benchmark results using a real‐world public dataset, ChEMBL. The code is available at https://github.com/dudwojae/SMILES‐MaskGAN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Structure

Stichwörter der Autor:innen

de novo molecular designdeep learninggenerative adversarial networksreinforcement learningsimplified molecular-input line-entry system (SMILES) strings

Autor:innen und Institutionen

  • Department of Industrial, Management Engineering Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea.

ORCID-Profile: Seoung Bum Kim

Förderung

  • National Research Foundation of Korea
  • Ministry of Science and ICT, South Korea
  • Ministry of Culture, Sports and Tourism
  • Korea Creative Content Agency

Zitieren

APA

Lee, Y. J., Kahng, H., & Kim, S. B. (2021). Generative Adversarial Networks for De Novo Molecular Design. Molecular Informatics, 40(10). https://doi.org/10.1002/minf.202100045

Vancouver

Lee YJ, Kahng H, Kim SB. Generative Adversarial Networks for De Novo Molecular Design. Molecular Informatics. 2021;40(10). doi:10.1002/minf.202100045

BibTeX
@article{Lee2021,
  author = {Lee, Young Jae and Kahng, Hyungu and Kim, Seoung Bum},
  title = {Generative Adversarial Networks for De Novo Molecular Design},
  journal = {Molecular Informatics},
  year = {2021},
  volume = {40},
  number = {10},
  doi = {10.1002/minf.202100045}
}
Kostenlos starten →