Tuesday, October 30, 2018

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

Jiaxuan You, Bowen Liu, Rex Ying, Vijay Pande, Jure Leskovec (2018)
Highlighted by Jan Jensen

Ever since Alán Aspuru-Guzik and co-workers published their seminal paper there has been a flurry of activity on generative models, which is not surprising given that they offer a radically new alternative to screening chemical libraries as a way to discover new molecules.

Almost all the new efforts on generative models have been based on adapting machine learning techniques used for natural language processing to text-based representation of molecules, i.e. SMILES strings. While very promising the SMILES syntax has some quirks which makes them hard to predicts efficiently. One solution is to change the syntax to be more ML-friendly, but this has yet to be tested for generative models.

Another option is to work with a graph (i.e. atoms and bonds) representation of the molecule and this paper is the first I've seen that does that for an ML-based generative model. In this case the ML method is reinforcement learning where the addition of each atom is treated as an action which can be trained to towards a particular outcome, here molecules with certain properties. This approach seems to outperform the SMILES based approaches for the prediction of some properties.

The code is available here.

This work is licensed under a Creative Commons Attribution 4.0 International License.


  1. I was actually surprised tremendously after finding this excellent post because I was actually tempted to learn about social graph game and sites and it was on the first page of google. Just feel an exceptional thirst to have a tour to this post and really I found good graph generation to store in my learning hut. Love this type of educative contribution. The graph images also are twinkling on this cleanly sharp white page. I honestly appreciate your brilliant effort. I have to take my tour very often no doubt. 그래프게임

  2. Superbly written article, if only all bloggers offered the same content as you, the internet would be a far better place..