\textsc{NeVAE}: a deep generative model for molecular graphs

MaRDI QIDQ4969182zbMATH OpenFDO

Authors B. Samanta, Abir de, Gourhari Jana, Vicenç Gómez, Niloy Ganguly, Manuel Gomez-Rodriguez, P. K. Chattaraj

Publication date 5 October 2020

Full work available at URL https://arxiv.org/abs/1802.05283, https://jmlr.csail.mit.edu/papers/v21/19-671.html

zbMATH Keywords

deep generative modelsdrug designgeometric deep learningmolecule discoveryvariational autoencoders

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Artificial neural networks and deep learning (68T07)

Recommendations

• Learning an efficient constructive sampler for graphs
• Generative network complex (GNC) for drug discovery
• scientific article; zbMATH DE number 614365
• Improving latent variable descriptiveness by modelling rather than ad-hoc factors
• Deep Generative Models and Inverse Problems

Cites work

• Efficient global optimization of expensive black-box functions
• Emergence of Scaling in Random Networks
• Kronecker graphs: an approach to modeling networks
• On Information and Sufficiency
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Stochastic Estimation of the Maximum of a Regression Function

Cited in

(5)

• Generative network complex (GNC) for drug discovery
• Geometric deep learning for design of catalysts and molecules
• Learning an efficient constructive sampler for graphs
• CDGCN: conditional de novo drug generative model using graph convolution networks
• Conformal load prediction with transductive graph autoencoders

Describes a project that uses

Uses Software

• word2vec
• GAUSSIAN
• KronFit
• MolGAN

This page was built for publication: \textsc{NeVAE}: a deep generative model for molecular graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969182)