Abstract
With the rise of artificial intelligence (AI) in drug discovery, de novo molecular generation provides new ways to explore chemical space. However, because de novo molecular generation methods rely on abundant known molecules, generated molecules may have a problem of novelty. Novelty is important in highly competitive areas of medicinal chemistry, such as the discovery of kinase inhibitors. In this study, de novo molecular generation based on recurrent neural networks was applied to discover a new chemical space of kinase inhibitors. During the application, the practicality was evaluated, and new inspiration was found. With the successful discovery of one potent Pim1 inhibitor and two lead compounds that inhibit CDK4, AI-based molecular generation shows potentials in drug discovery and development.
Highlights
Chemical space is defined as the infinite universe of molecules [1], where unknown space is being explored and developed
Generated chemical space with randomized Simplified molecular input line entry specification (SMILES) sequences As described previously, transfer learning (TL) is often applied to generative models based on Recurrent neural networks (RNNs)
Previous models ignore the diversity of SMILES sequences belonging to complex molecules, which helps enlarge datasets so that the enlarged datasets directly related to corresponding tasks can be appropriate inputs
Summary
Chemical space is defined as the infinite universe of molecules [1], where unknown space is being explored and developed. Considering only drug-like molecules, the number of compounds in the drug-like chemical space is estimated to be 1060, which means that there are more drug-like compounds than there are atoms in the solar system [2]. In the drug-like chemical space, only a tiny proportion of molecules have been found as drugs, and for a long time, numerous efforts have been made to modify the drug map. As no Inspired by the successful applications of deep learning in areas such as image recognition and natural language processing [9], researchers have increased their interest in the deployment of AI in drug R&D [10]. The linear form of molecules is similar to sequences in natural language processing and establishes a starting point for de novo molecular generation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
