aizynthfinder is a tool for retrosynthetic planning. The 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.



First time, execute the following command in a console or an Anaconda prompt

In [ ]:
#conda env create -f


In [ ]:
#conda env update -n aizynth-env -f

Activate the environement

In [ ]:
# conda activate aizynth-env

Open Jupyter Notebook

In [ ]:
#jupyter notebook

AiZynthFinder Jupyter Notebook GUI

In [1]:
from aizynthfinder.interfaces import AiZynthApp
app = AiZynthApp("/mnt/NVMe/AIsynth/data/config_cli.yml") #adapt the path to your yml file
#example smiles: O=C1N(Cc2ccccc2Cl)CCN1c1cncc2ccc(Cl)cc12
Loading expansion policy model from /mnt/NVMe/aizynthfinder/full_uspto_03_05_19_rollout_policy.hdf5 to full_uspto
Loading templates from /mnt/NVMe/aizynthfinder/full_uspto_03_05_19_unique_templates.hdf5 to full_uspto
Loading stock from /mnt/NVMe/aizynthfinder/zinc_stock_17_04_20.hdf5 to zinc
Loading stock from /mnt/NVMe/aizynthfinder/stock_Enamine_MolPort.hdf5 to Enamine_MolPort
In [ ]: