Medical intelligent agent search engine Marvin: a prototype Grid applications

Brussels 23 March 2001 The Grid is not only about high-performance computing, explained Jean-Raoul Scherrer from the Swiss Institute of Bioinformatics at the Grid workshop organised in March 2001 by the European Commission in Brussels. Hundreds of large medical and bio-molecular databases and information sources already exists, that can benifit from Grid technologies to make them more accesisble."If it is allowed somehow to consider the 'Grid' as an offspring of the HPCC action, then one large part of the use of such an infrastructure should be devoted to 'Education, Research and Health" (ERH) dealing with co-ordinated resource sharing and problem solving in dynamic, multi-institutional organisations' Scherrer notes. In a pioneering experiment, called Health on the Net, several Swiss organisations built an advanced intelligent agent based search engine called MARVIN, that searches the Internet for medical information, that can be considered a prototype for future implementations in the Grid's knowledge layer.

The information on the World Wide Web is unstructured. Many distributed, multimedia and multilingual many tools have been developed to help users search for useful information, such as subject hierarchies, general search engines, browsers and search assistants. These tools, however, lack a lot, mainly in terms of precision, multilingual indexing and distribution.

That is why the Swiss have developed MARVIN: a multi-agent indexer. For a given domain MARVIN filters all relevant documents from a set of Web pages, by following links to new documents. Currently MARVIN is implementedfor medical information by Health on the Net. Marvin consists of a set of agents running in parallel that download, filter and index the web pages.

The indexing can be done by several agents running in parallel even distributed over a cluster of workstations. The agents co-operate in order to synchronise their activities. As an example of co-operation, before filtering and indexing a page, an agent checks that the page has not been previously analysed or is present indexed by another agent. The agent broadcasts a message to all other agents and starts analysing the page only if this is OKed by the other agents.Agents can be specialised, for instance in analysing documents from a given Internet domain. The global index can therefore be distributed over several local indexes when agents are run on remote workstations.

According to Scherrer, being able to ask such questions such as 'how does a disease tissue compare with healthy tissue?' based on data from large databases all around the world, will enormously increase our understanding of biology and move us towards the understanding of function.

For more information, check in at theHealth on the Net web site.


Ad Emmen

[News on Advanced IT][Calendar][Analysis][IT in Medicine]