Timezone: »

 
Oral
Junction Tree Variational Autoencoder for Molecular Graph Generation
Wengong Jin · Regina Barzilay · Tommi Jaakkola

Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A7
in Generative Models 3 »

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.

[ PDF]  [ Video] 

Author Information

Wengong Jin (MIT Computer Science and Artificial Intelligence Laboratory)
Regina Barzilay (MIT CSAIL)
Regina Barzilay

Regina Barzilay is an Israeli-American computer scientist. She is a professor at the Massachusetts Institute of Technology and a faculty lead for artificial intelligence at the MIT Jameel Clinic. Her research interests are in natural language processing and applications of deep learning to chemistry and oncology.

Tommi Jaakkola (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors