Generative Recurrent Networks for De Novo Drug Design

• Published in: Molecular informatics Vol. 37; no. 1-2
• Main Authors: Gupta, Anvita, Müller, Alex T., Huisman, Berend J. H., Fuchs, Jens A., Schneider, Petra, Schneider, Gisbert
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 01.01.2018; John Wiley and Sons Inc
• Subjects: Artificial intelligence; Chemogenomics; Computer applications; Computer memory; deep learning; Design; Design optimization; Drug Design; Drug development; Drug discovery; Drug Discovery - methods; Enumeration; Generative artificial intelligence; Long short-term memory; machine learning; Mathematical models; medicinal chemistry; Models, Chemical; Neural networks; Neural Networks (Computer); Quantitative Structure-Activity Relationship; Recurrent neural networks; Strings; Transfer learning; deep learning; Chemogenomics; drug discovery; machine learning; medicinal chemistry
• ISSN: 1868-1743; 1868-1751; 1868-1751
• DOI: 10.1002/minf.201700111

Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short‐term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine‐tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN‐LSTM system for high‐impact use cases, such as low‐data drug discovery, fragment based molecular design, and hit‐to‐lead optimization for diverse drug targets.