RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design

De novo molecule generation often results in chemically unfeasible molecules. A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility. However, using currently available proxies still results in highl...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cheng-Hao, Liu, Korablyov, Maksym, Jastrzębski, Stanisław, Włodarczyk-Pruszyński, Paweł, Bengio, Yoshua, Marwin H S Segler
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 25.11.2020
Subjects
Antibiotics
Artificial neural networks
Bias
Chemical synthesis
Graph neural networks
Neural networks
Search process
Software
Online AccessGet full text

Cover

More Information
Summary:De novo molecule generation often results in chemically unfeasible molecules. A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility. However, using currently available proxies still results in highly unrealistic compounds. We investigate the feasibility of training deep graph neural networks to approximate the outputs of a retrosynthesis planning software, and their use to bias the search process. We evaluate our method on a benchmark involving searching for drug-like molecules with antibiotic properties. Compared to enumerating over five million existing molecules from the ZINC database, our approach finds molecules predicted to be more likely to be antibiotics while maintaining good drug-like properties and being easily synthesizable. Importantly, our deep neural network can successfully filter out hard to synthesize molecules while achieving a \(10^5\) times speed-up over using the retrosynthesis planning software.
ISSN:2331-8422