This algorithm uses a new reaction fingerprint to predict the reaction type of a reaction. The fingerprint is made up of a concatenation of the fingerprints of the reactant and reagent molecules in the reaction.

The code in the neural fingerprint directory is heavily based on :

Convolutional Networks on Graphs for Learning Molecular Fingerprints

The code for the above paper can be found at : HIPS/neural-fingerprint

This package requires:

• Scipy version >= 0.15.0
• RDkit
• Autograd (Just run pip install autograd)
• Hyperopt

This software was primarily written by Jennifer Wei and David Duvenaud We'd also love to hear about your experiences with this package in general. Drop us an email!