Python for Bioinformatics

15 Text Mining

Biological information tends to be more qualitative than quantitative. The result is that a lot of the information is presented as textual descriptions rather than equations and numbers. As a consequence, the field of mining biological texts for information is emerging. Like many topics in this book, this field is large in scope and evolving. Thus only a few introductory topics are presented here, and readers desiring more information should consider resources dedicated solely to this topic.

15.1 An Introduction to Text Mining

The goal of text mining in this chapter is to extract information from written documents. While that sounds fairly straightforward, it is a difficult task. A scientific document presents information in many ...