top of page


In addition to our proprietary work, we also contribute to research articles,  host seminars, and attend speaking events. Visit the connect page to enquire about engagement opportunities.

Here is some more information about Molecule One.

white gradient.png

Top publications

We investigate the feasibility of training deep graph neural networks to approximate the outputs of a retrosynthesis planning software, and their use to bias the search result

We proposed Molecule Edit Graph Attention Network (MEGAN), a template free neural model that encodes reaction as a sequence of graph edit.


Thanks for subscribing!

join our quarterly newsletter

bottom of page