aizynthfinder documentation — aizynthfinder 4.4.1 documentation
aizynthfinder is a tool for retrosynthetic planning. The default algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by a policy that suggests possible precursors by utilizing a neural network trained on a library of known reaction templates. You run retrosynthesis experiments you need a trained model and a stock collection. You can download a public available model based on USPTO and a stock collection from ZINC database. This will download the data to your current directory. The config.yml file can be used directly with the interfaces. There are two main interfaces provided by the package: a script that performs tree search in batch mode and an interface that is providing a GUI within a Jupyter notebook. The GUI interface should be run in a Jupyter notebook. This is a simple example of the code in a Jupyter notebook cell. where the AiZynthApp class needs to be instantiated with the path to a conf