Generative Network Complex for the Automated Generation of Drug-like Molecules
Autor: | Kaifu Gao, Guo-Wei Wei, Duc Duy Nguyen, Meihua Tu |
---|---|
Rok vydání: | 2020 |
Předmět: |
Drug
Computer science General Chemical Engineering Reliability (computer networking) media_common.quotation_subject Ribociclib Library and Information Sciences Machine learning computer.software_genre 01 natural sciences Article 0103 physical sciences Drug Discovery Aspartic Acid Endopeptidases Humans media_common 010304 chemical physics Drug discovery business.industry Fingerprint (computing) General Chemistry Autoencoder 0104 chemical sciences Computer Science Applications 010404 medicinal & biomolecular chemistry Pharmaceutical Preparations Artificial intelligence Amyloid Precursor Protein Secretases business Gradient descent computer Generative grammar |
Zdroj: | J Chem Inf Model |
ISSN: | 1549-960X |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |