Graph networks for molecular design
Artikel i vetenskaplig tidskrift, 2021

Deep learning methods applied to chemistry can be used to accelerate the discovery of new molecules. This work introduces GraphINVENT, a platform developed for graph-based molecular design using graph neural networks (GNNs). GraphINVENT uses a tiered deep neural network architecture to probabilistically generate new molecules a single bond at a time. All models implemented in GraphINVENT can quickly learn to build molecules resembling the training set molecules without any explicit programming of chemical rules. The models have been benchmarked using the MOSES distribution-based metrics, showing how GraphINVENT models compare well with state-of-the-art generative models. This work compares six different GNN-based generative models in GraphINVENT, and shows that ultimately the gated-graph neural network performs best against the metrics considered here.

Graph neural networks

Drug discovery

Molecular design

Deep generative models


Rocio Mercado

AstraZeneca AB

Tobias Rastemo

AstraZeneca AB

Student vid Chalmers

Edvard Lindelöf

AstraZeneca AB

Student vid Chalmers

Gunter Klambauer

Johannes Kepler Universität Linz (JKU)

Ola Engkvist

AstraZeneca AB

Hongming Chen

Guangdong Laboratory

Esben Jannik Bjerrum

AstraZeneca AB

Machine Learning: Science and Technology

26322153 (eISSN)

Vol. 2 2 025023


Annan data- och informationsvetenskap

Bioinformatik (beräkningsbiologi)




Mer information

Senast uppdaterat