SynNet is a model for synthetic tree generation using neural networks. The model can be used for synthesizability-constrained molecular design, molecular optimization, and computer-aided synthesis planning.


Molecular design and synthesis planning are two critical steps in the process of molecular discovery that we formulate as a single shared task of conditional synthetic pathway generation. Here, we generate synthetic pathways from a target molecular embedding. This approach allows us to conduct synthesis planning in a bottom-up manner and design synthesizable molecules by decoding from optimized conditional codes, demonstrating the potential to solve both problems of design and synthesis simultaneously.

See the GitHub repo for links to:

  • code
  • running instructions
  • publication