Abstract
Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.
Highlights
There has been a surge of deep learning methods applied to cheminformatics in the last few years [1,2,3,4,5]
Whereas much impact has been demonstrated in deep learning methods that replace traditional machine learning (ML) approaches (e.g., QSAR modelling [6]), a more profound impact is the application of generative models in de novo drug design [7,8,9]
Notice that the reconstruction error corresponds to decoding to a valid SMILES that belongs to a different
Summary
There has been a surge of deep learning methods applied to cheminformatics in the last few years [1,2,3,4,5]. Whereas much impact has been demonstrated in deep learning methods that replace traditional machine learning (ML) approaches (e.g., QSAR modelling [6]), a more profound impact is the application of generative models in de novo drug design [7,8,9]. The REINVENT method was proposed, which combines RNNs with reinforcement learning to generate structures with desirable properties [8]. Another architecture, the variational autoencoder (VAE), was shown to generate novel chemical space [9, 17]. The variational autoencoder (VAE), was shown to generate novel chemical space [9, 17] This architecture is comprised of an encoder, that converts the molecule to a latent vector
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.
