PolySearch -- comprehensive biomedical text searching
What you can do:
A web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites.
Highlights:
- A particular challenge in biomedical text mining is to find ways of handling 'comprehensive' or 'associative' queries such as 'Find all genes associated with breast cancer'.
- Given that many queries in genomics, proteomics or metabolomics involve these kind of comprehensive searches we believe that a web-based tool that could support these searches would be quite useful.
- PolySearch supports >50 different classes of queries against nearly a dozen different types of text, scientific abstract or bioinformatic databases.
- The typical query supported by PolySearch is 'Given X, find all Y's' where X or Y can be diseases, tissues, cell compartments, gene/protein names, SNPs, mutations, drugs and metabolites.
- PolySearch also exploits a variety of techniques in text mining and information retrieval to identify, highlight and rank informative abstracts, paragraphs or sentences.
- PolySearch's performance has been assessed in tasks such as gene synonym identification, protein-protein interaction identification and disease gene identification using a variety of manually assembled 'gold standard' text corpuses.
- Its f-measure on these tasks is 88, 81 and 79%, respectively. These values are between 5 and 50% better than other published tools.
Keywords:
- text mining
- literature search
- biomedical text
- comprehensive query
- comprehensive searches
- information retrieval
Literature & Tutorials:
This record last updated: 07-29-2008