NEVAE: a deep generative model for molecular graphs

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Samanta, Bidisha
• dc.contributor.author De, Abir
• dc.contributor.author Jana, Gourhari
• dc.contributor.author Gómez, Vicenç
• dc.contributor.author Chattaraj, Pratim Kumar
• dc.contributor.author Ganguly, Niloy
• dc.contributor.author Gomez-Rodriguez, Manuel
• dc.date.accessioned 2021-04-22T09:34:35Z
• dc.date.available 2021-04-22T09:34:35Z
• dc.date.issued 2020
• dc.description.abstract Deep generative models have been praised for their ability to learn smooth latent representations of images, text, and audio, which can then be used to generate new, plausible data. Motivated by these success stories, there has been a surge of interest in developing deep generative models for automated molecule design. However, these models face several difficulties due to the unique characteristics of molecular graphs—their underlying structure is not Euclidean or grid-like, they remain isomorphic under permutation of the nodes’ labels, and they come with a different number of nodes and edges. In this paper, we first propose a novel variational autoencoder for molecular graphs, whose encoder and decoder are specially designed to account for the above properties by means of several technical innovations. Moreover, in contrast with the state of the art, our decoder is able to provide the spatial coordinates of the atoms of the molecules it generates. Then, we develop a gradient-based algorithm to optimize the decoder of our model so that it learns to generate molecules that maximize the value of certain property of interest and, given any arbitrary molecule, it is able to optimize the spatial configuration of its atoms for greater stability. Experiments reveal that our variational autoencoder can discover plausible, diverse and novel molecules more effectively than several state of the art models. Moreover, for several properties of interest, our optimized decoder is able to identify molecules with property values 121% higher than those identified by several state of the art methods based on Bayesian optimization and reinforcement learning.en
• dc.description.sponsorship The project was supported by Google India Ph.D. Fellowship and the “Learning Representations from Network Data” project sponsored by Intel. The project leading to these results has also received funding from “la Caixa” Foundation (ID 100010434), under the agreement LCF/PR/PR16/- 51110009. We would also like to thank MHRD India for their support on the IMPRINT project of ”Development of a remote healthcare delivery system”.
• dc.format.mimetype application/pdf
• dc.identifier.citation Samanta B, De A, Jana G, Gomez V, Chattaraj PK, Ganguly N, Gomez-Rodriguez M. NEVAE: a deep generative model for molecular graphs. J Mach Learn Res. 2020 Apr;21(114):1-33.
• dc.identifier.issn 1532-4435
• dc.identifier.uri http://hdl.handle.net/10230/47190
• dc.language.iso eng
• dc.publisher Journal of Machine Learning Research
• dc.relation.ispartof Journal of machine learning research. 2020 Apr;21(114):1-33
• dc.rights © 2020 Bidisha Samanta, Abir De, Gourhari Jana,Vicenc¸ Gomez, Pratim Kumar Chattaraj,Niloy Ganguly, Manuel Gomez-Rodriguez. CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Drug designen
• dc.subject.keyword Molecule discoveryen
• dc.subject.keyword Deep generative modelsen
• dc.subject.keyword Variational autoencodersen
• dc.subject.keyword Geometric deep learningen
• dc.title NEVAE: a deep generative model for molecular graphsen
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion