Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Junction Tree Variational Autoencoder for Molecular Graph Generation

About

We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings instead of graphs. Our junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network. This approach allows us to incrementally expand molecules while maintaining chemical validity at every step. We evaluate our model on multiple tasks ranging from molecular generation to optimization. Across these tasks, our model outperforms previous state-of-the-art baselines by a significant margin.

Wengong Jin, Regina Barzilay, Tommi Jaakkola• 2018

Related benchmarks

TaskDatasetResultRank
Property optimizationZINC250k (test)
1st Order Metric0.925
33
Molecular Generationfa7
Top-Hit 5% Docking Score (kcal/mol)-7.683
27
Molecular Generation5ht1b
Docking Score (Top-Hit 5%, kcal/mol)-9.382
27
Molecular Generationjak2
Top-Hit 5% Docking Score (kcal/mol)-8.885
27
Molecular Generationparp1
Top-Hit 5% Docking Score (kcal/mol)-9.482
27
Constrained Property OptimizationZINC250K
Improvement1.68
27
Molecular Generationbraf
Top-Hit 5% Docking Score (kcal/mol)-9.079
26
Molecular Dockingjak2
Mean Docking Score-8.885
18
Molecular Dockingfa7
Mean Docking Score-7.683
18
Molecular Docking5ht1b
Mean Docking Score-9.382
18
Showing 10 of 40 rows

Other info

Follow for update