Biomedical Data Mining

Natural Language Processing (NLP) deals with creating computational techniques to process and comprehend natural languages. Biomedical Natural Language Processing (BioNLP) and text mining is an emerging and interdisciplinary area of NLP which combines biology, linguistics and computer science. The amount of online biology resources has been increasing exponentially. This data is available in the form of large number of electronically available publications stored in online journals and databases. It is impossible to manually integrate the information present in these texts.

Biomedical text mining can facilitate and accelerate the process of discovery and integration of data present in literature. Specialized areas like translational bioinformatics have been emerging with the aim of integrating biological and clinical data. A dimension of our research is focussed on biomedical text mining aimed at correlating diseases and molecular entities as well as associating food with their nutritional values.

References:

• Jensen, K., Panagiotou, G., and Kouskoumvekaki, I. (2014). Integrated text mining and chemoinformatics analysis associates diet to health benefit at molecular level. PLoS Computational Biology, 10(1), e1003432.
• Srinivasan, P. and Libbus, B. (2004). Mining MEDLINE for implicit links between dietary substances and diseases. Bioinformatics, 20 Suppl 1(C), i290–6.
• Yang, H., Swaminathan, R., & Sharma, A. (2011). Mining Biomedical Text towards Building a Quantitative Food-Disease-Gene Network. In Learning Structure and Schemas from Documents (pp. 205–225). Springer.