Show simple item record

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.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.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.
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.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.uri https://creativecommons.org/licenses/by/4.0/
dc.title NEVAE: a deep generative model for molecular graphs
dc.type info:eu-repo/semantics/article
dc.subject.keyword Drug design
dc.subject.keyword Molecule discovery
dc.subject.keyword Deep generative models
dc.subject.keyword Variational autoencoders
dc.subject.keyword Geometric deep learning
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking