SMEE: a tool to extract sorting motif data from PubMed Central abstracts and full text documents

  • Authors:
  • Lewis Cawthorne

  • Affiliations:
  • University of South Carolina, Columbia, SC

  • Venue:
  • Proceedings of the 49th Annual Southeast Regional Conference
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Data from biological research experiments is being posted online at a phenomenal rate. Even in a fairly narrow topic, one can easily become overloaded trying to keep up with information relevant to a single researcher. An automated method for analyzing and presenting this data is the key to conducting efficient and fruitful research in any biological field. Before now, there has not been a freely available semi-automated protein sorting motif text mining solution. This paper details a current work in progress to create a novel procedure for text mining protein sorting motif data from both full text documents and abstracts retrieved from PubMed Central. A full set of processing stages are currently implemented and early results are promising. We expect further work to yield a valuable tool to be made freely available for the community.