Abstract
This article describes biomarker_nlp, a Python package that aims to provide natural language processing (NLP) functionalities for mining and processing biomarker information from the drug labels in DailyMed for targeted cancer therapies approved by the U.S. Food and Drug Administration (FDA), as well as other biomedical free text. It contains modules and functions supporting the recognition and extraction of a variety of biomarkers, such as gene/protein, therapy, disease, and drug label. This package may be helpful for users who want to extract and analyze biomarker information related to FDA-approved products, focusing on FDA-approved targeted cancer therapies.