Log In Sign Up

Conditional Constrained Graph Variational Autoencoders for Molecule Design

by   Davide Rigoni, et al.

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.


Conditional molecular design with deep generative models

Although machine learning has been successfully used to propose novel mo...

Designing Random Graph Models Using Variational Autoencoders With Applications to Chemical Design

Deep generative models have been praised for their ability to learn smoo...

A Systematic Assessment of Deep Learning Models for Molecule Generation

In recent years the scientific community has devoted much effort in the ...

GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders

Deep learning on graphs has become a popular research topic with many ap...

Constrained Graph Variational Autoencoders for Molecule Design

Graphs are ubiquitous data structures for representing interactions betw...

Barking up the right tree: an approach to search over molecule synthesis DAGs

When designing new molecules with particular properties, it is not only ...

Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models

In this work, we present some recommendations on the evaluation of state...