AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning

dataset

posted on 2020-06-11, 14:59 authored by Samuel GenhedenSamuel Genheden, Esben Jannik Bjerrum, Amol Thakkar, Jean-Louis Reymond, Veronika Chadimova, Ola Engkvist

This is public data to be used with the aizynthfinder tool for retrosynthesis planning (https://github.com/MolecularAI/aizynthfinder)

There are three files available:

* full_uspto_03_05_19_rollout_policy.hdf5 - the Keras neural network model used as rollout policy

* full_uspto_03_05_19_unique_templates.hdf5 - unique template codes that are used together with the policy to generate new precursors in the tree search

* zinc_stock_17_04_20.hdf - stock file made from the ZINC database on 17:th of april 2020.

Funding

Amol Thakkar was supported financially by the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement no. 676434, “Big Data in Chemistry” (“BIGCHEM,” http://bigchem.eu).

History

Usage metrics

Keywords

aizynthfinder monte carlo tree search neural networks chemical reactions USPTO reaction informatics Organic Chemical Synthesis Cheminformatics

Licence

MIT

Exports

RefWorks

BibTeX

Ref. manager

Endnote

DataCite

NLM