New EPSRC research grant for Mark Stevenson 

21st April 2012

Mark Stevenson of the Natural Language Processing (NLP) research group has been awarded a new EPSRC research grant on the topic of language processing for literature based discovery in medicine. The grant will run for 3 years and is held jointly with Rob Gaizauskas (Computer Science), Oliver Bandmann (Neuroscience) and Sarah Danson (Oncology).

The amount of published material in biomedicine has been growing exponentially in recent years. The knowledge it contains is now so vast and fragmented that it is no longer possible for any individual or research group to keep up to with the advances relevant to their area. The research literature is also fragmented and researchers naturally concentrate their attention on their own area of expertise, meaning they may not identify research that is relevant to their own if it does not appear within the literature of their scientific discipline. However, medical research is becoming increasingly interdisciplinary with progress being made by combining outputs from various fields.

Automatic analysis of research literature allows large numbers of documents to be examined and information from multiple documents to be combined. This approach has already been used to used to identify include treatments for diseases (eg. that fish oil can be used to treat Raynaud's syndrome) and cases of diseases (eg. that migraines can be related to magnesium deficiency). Despite these successes, the knowledge that has been discovered has been limited by the relatively simple techniques used to analyse the literature.

This project will develop improved approaches for identifying new knowledge from biomedical literature by making use of recent advances in techniques for analysing these documents. The project, which is a collaboration between researchers in Computer Science Department and the Medical School, will focus on the fields of oncology and neuroscience, particularly the causes of and potential treatments for melanoma and Parkinson's disease.