In recent years, deep generative models for graphs have been used to generate new molecules. These models have produced good results, leading to several proposals in the literature. However, these models may have troubles learning some of the complex laws governing the chemical world. In this work, we explore the usage of the histogram of atom valences to drive the generation of molecules in such models. We present Conditional Constrained Graph Variational Autoencoder (CCGVAE), a model that implements this key-idea in a state-of-the-art model, and shows improved results on several evaluation metrics on two commonly adopted datasets for molecule generation
Deep generative models of molecules have grown immensely in popularity, trained on relevant datasets...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Abstract: Computational molecular design can yield chemically unreasonable compounds when performed ...
Deep generative models have been praised for their ability to learn smooth latent representation of ...
© 2018 by authors.All right reserved. We seek to automate the design of molecules based on specific ...
International audienceIn this paper we propose a generative model for graphs formulated as a variati...
Abstract We propose a molecular generative model based on the conditional variational autoencoder fo...
Variational autoencoders have emerged as one of the most common approaches for automating molecular ...
Although machine learning has been successfully used to propose novel molecules that satisfy desired...
International audienceDeep learning on graphs has become a popular research topic with many applicat...
Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative app...
The design of molecules with bespoke chemical properties has wide-ranging applications in materials ...
Great computational effort is invested in generating equilibrium states for molecular systems using,...
Recent advancements in deep learning based modelling of molecules promise to accelerate in silico dr...
Molecular design is a critical aspect of various scientific and industrial fields, where the propert...
Deep generative models of molecules have grown immensely in popularity, trained on relevant datasets...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Abstract: Computational molecular design can yield chemically unreasonable compounds when performed ...
Deep generative models have been praised for their ability to learn smooth latent representation of ...
© 2018 by authors.All right reserved. We seek to automate the design of molecules based on specific ...
International audienceIn this paper we propose a generative model for graphs formulated as a variati...
Abstract We propose a molecular generative model based on the conditional variational autoencoder fo...
Variational autoencoders have emerged as one of the most common approaches for automating molecular ...
Although machine learning has been successfully used to propose novel molecules that satisfy desired...
International audienceDeep learning on graphs has become a popular research topic with many applicat...
Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative app...
The design of molecules with bespoke chemical properties has wide-ranging applications in materials ...
Great computational effort is invested in generating equilibrium states for molecular systems using,...
Recent advancements in deep learning based modelling of molecules promise to accelerate in silico dr...
Molecular design is a critical aspect of various scientific and industrial fields, where the propert...
Deep generative models of molecules have grown immensely in popularity, trained on relevant datasets...
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Comput...
Abstract: Computational molecular design can yield chemically unreasonable compounds when performed ...