Downloads

Register

Registration is optional. If you register, we'll keep in touch with news and updates.

Releases

ChemDataExtractor is available as an open source python package. Installation using conda or pip is highly recommended.

For the latest unstable development version, clone the source code repository on GitHub.

Alternatively, you can download the latest release below. For help with installation and getting started, check out the documentation.

3rd February 2017
Latest release

ChemDataExtractor 1.3.0

Source code for the ChemDataExtractor toolkit.

Download

Evaluation files

ChemDataExtractor performance was evaluated as part of the following publication:

M.C. Swain and J.M. Cole. "ChemDataExtractor: A Toolkit for Automated Extraction of Chemical Information from the Scientific Literature", J. Chem. Inf. Model. 2016 (Accepted) 10.1021/acs.jcim.6b00207
14th September 2016

ChemDataExtractor patent melting points

An SDF file containing melting points extracted from 2,000 patents by ChemDataExtractor.

Download
14th September 2016

ChemDataExtractor patent melting points - filtered

An SDF file containing melting points extracted from 2,000 patents by ChemDataExtractor, with duplicate compounds removed.

Download
11th April 2016

Evaluation journal articles

A collection of 50 open access journal articles that were used in the evaluation.

Download
11th April 2016

Gold standard journal data

Manually extracted chemical information from the evaluation articles, in JSON format.

Download
11th April 2016

ChemDataExtractor journal outputs

Output from applying ChemDataExtractor to the evaluation articles, in JSON format.

Download