Text mining for discovery of host-pathogen interactions

Stephen Anthony*, Vitali Sintchenko, Enrico Coiera

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

3 Citations (Scopus)


Text processing systems now supplement the information needs of professionals across a variety of industries. Applications such as relationship extraction, information retrieval, document summarization, question answering, and multilingual machine translation demonstrate practical utility in terms of accuracy and speed. Significant drivers behind these advances stem from performance improvements in underlying technologies such as syntactic parsing, named entity recognition, and semantic interpretation. Text mining consolidates these and other language processing technologies to extract meaningful information. This chapter surveys the field of biomedical text mining and develops a case study to illustrate the underlying resources that are available, as well as the technologies that are commonly applied. The case study is designed to identify and extract relationships between genotypes, pathogens, and syndromes. Through the use of text processing it is possible to transform such relationships from disparate unstructured text sources into structured repositories. By identifying and organizing relationships that are scattered across diverse areas and literatures, it is possible to enhance our understanding of the complex machinery that drives biological processes.

Original languageEnglish
Title of host publicationInfectious disease informatics
EditorsVitali Sintchenko
Place of PublicationNew York
PublisherSpringer, Springer Nature
Number of pages17
ISBN (Electronic)9781441913272
ISBN (Print)9781441913265
Publication statusPublished - 2010
Externally publishedYes


Dive into the research topics of 'Text mining for discovery of host-pathogen interactions'. Together they form a unique fingerprint.

Cite this