Generative Network Complex for the Automated Generation of Drug-like Molecules

Kaifu Gao, Duc Duy Nguyen, Meihua Tu, Guo Wei Wei

Research output: Contribution to journalArticlepeer-review

80 Scopus citations


Current drug discovery is expensive and time-consuming. It remains a challenging task to create a wide variety of novel compounds that not only have desirable pharmacological properties but also are cheaply available to low-income people. In this work, we develop a generative network complex (GNC) to generate new drug-like molecules based on the multiproperty optimization via the gradient descent in the latent space of an autoencoder. In our GNC, both multiple chemical properties and similarity scores are optimized to generate drug-like molecules with desired chemical properties. To further validate the reliability of the predictions, these molecules are reevaluated and screened by independent 2D fingerprint-based predictors to come up with a few hundreds of new drug candidates. As a demonstration, we apply our GNC to generate a large number of new BACE1 inhibitors, as well as thousands of novel alternative drug candidates for eight existing market drugs, including Ceritinib, Ribociclib, Acalabrutinib, Idelalisib, Dabrafenib, Macimorelin, Enzalutamide, and Panobinostat.

Original languageEnglish
Pages (from-to)5682-5698
Number of pages17
JournalJournal of Chemical Information and Modeling
Issue number12
StatePublished - Dec 28 2020

Bibliographical note

Funding Information:
This work was supported in part by NSF Grants DMS-1721024, DMS-1761320, and IIS1900473, NIH Grant GM126189, and Michigan Economic Development Corporation. D.D.N. and G.W.W. are also funded by Bristol-Myers Squibb and Pfizer.

Publisher Copyright:
© 2020 American Chemical Society. All rights reserved.

ASJC Scopus subject areas

  • General Chemistry
  • General Chemical Engineering
  • Computer Science Applications
  • Library and Information Sciences


Dive into the research topics of 'Generative Network Complex for the Automated Generation of Drug-like Molecules'. Together they form a unique fingerprint.

Cite this