Text-based summarization and visualization of gene clusters

ABSTRACT

We present a system named MedSummarizer which uses biomedical literature information to assign biological meaning to a cluster of genes. Using relevant PubMed citations, it creates a ranked list of important biological concepts that describes the gene list. Further, based on the assigned concepts, it computes similarity between each pair of genes and displays this using a graph based visualization technique. The system allows use of human curated index (e.g. Mesh terms) as well as automatic annotations derived from free-text. We compare the results obtained using these two types of terms.

REFERENCES

• 1: H. Shaktay, S. Edwards, J. Wilbur, and M. Boguski. Genes, Themes and Microarrays: Using Information Retrieval for large-scale Gene analysis. In the Proceedings of ISMB, 1999.
• 2: L. Tanabe, U. Schref, L. Smith, and J. Lee et al. MedMiner: An Internet Text-Mining tool for Biomedical information with application to Gene Expression Profiling. Bio Techniques, 27:1210--1217, 1999.
• 3: L. Venkata Subramaniam , Sougata Mukherjea , Pankaj Kankar , Biplav Srivastava , Vishal S. Batra , Pasumarti V. Kamesam , Ravi Kothari, Information extraction from biomedical literature: methodology, evaluation and an application, Proceedings of the twelfth international conference on Information and knowledge management, November 03-08, 2003, New Orleans, LA, USA [doi>10.1145/956863.956941]
• 4: MeSH - http://www.nlm.nih.gov/mesh/meshhome.html
• 5: PubMed - http://www.ncbi.nlm.nih.gov/PubMed

INDEX TERMS

Keywords:
biological text mining, gene cluster summarization, gene similarity visualization, microarray analysis