A key challenge in biomedical text mining is to handle "comprehensive" or "associative" queries such as "Find all genes associated with
breast cancer". Given that many queries in genomics, proteomics or metabolomics involve these kinds of comprehensive searches, we have
developed a web-based tool called PolySearch. PolySearch supports more than 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.
To use this server:
- Decide which type of search you wish to do
- Select search restraints from the pull-down menus (Given X, Find Y)
- Press Next
- Follow the instructions on the input page to fine tune your search
- If you need more help or detailed explanations of the methods or databases, see the help section