AOP-toolkit (aoptk) is a Python package for mining and analyzing toxicological and biomedical literature. Originally developed to support the construction of Adverse Outcome Pathways (AOPs), it provides general-purpose tools for retrieving, processing, and analyzing scientific publications.
The toolkit enables users to collect literature from databases such as PubMed Central and Europe PMC, extract information from full-text articles, analyze unstructured text and images using large language models, and normalize chemical names across publications to improve data consistency and interoperability.
To install aoptk from GitHub repository, do:
git clone git@github.com:rdurnik/aoptk.git
cd aoptk
python -m pip install .TBA
If you want to contribute to the development of aoptk, have a look at the contribution guidelines.
This package was created with Copier and the NLeSC/python-template.