A collection of deep reinforcement learning-based & GFlowNet drug molecule generators focused on generation of molecules using Graphs/SELFIES guided by modern retrosynthesis tools to increase synthetic accessibility of de-novo designed drugs.

Command line and webapp for retrosynthetic disconnections, molecular complexity and synthetic accessibility metrics

Synthesis-oriented generative model to discover diverse drug candidates through a large action space and GFlowNet objective.

The NeoChemSynthWave: Chemistry project.