Biomedical Natural Language Processing (BioNLP)
Biomedical Natural Language Processing (BioNLP), also known as biomedical text mining, is a multidisciplinary research field on the edge of computer science, natural language processing, bioinformatics, medical & health informatics and computational linguistics. It refers to text mining approaches and methods applied to biomedical literature.
BioNLP main applications
- The identification of biological entities (named entity recognition) such us genes, transcripts, proteines, chemical compounds, and drugs.,,
- Identification of gene-gene or gene-drug interactions from published clinical trials and biomedical literature.
- Text Clustering
NLP libraries and frameworks
The main clinical trial registries are:
Lou Y et al. (2017). A Transition-based Joint Model for Disease Named Entity Recognition and Normalization. Bioinformatics; btx172. PubMed Saha S et al. (2015). Named entity recognition and classification in biomedical text using classifier ensemble. Int J Data Min Bioinform.; 11(4):365-91. PubMed M Krallinger, F Leitner, O Rabal, M Vazquez, J Oyarzabal and A Valencia, Overview of the chemical compound and drug name recognition (CHEMDNER) task. Proceedings of the Fourth BioCreative Challenge Evaluation Workshop vol. 2. 6-37.www.biocreative.org/media/store/files/2013/bc4_v2_1.pdf