About the WikiProfessional Concept Web Navigator

Recent research has indicated that the literature contains a wealth of implicit knowledge that is too complex and dispersed for the reader to pick up without computer assistance. The potential to discover these 'hidden associations' goes far beyond classical text mining. Therefore, to we have devised the Knowlet approach to make the Concept Web accessible to all users.

The Knowlet approach enables the combined description of multiple categories of relationships. Any concept in the literature, for instance a protein or a disease, can be treated as a source concept (depicted as a blue ball in the histogram). There may be information annotated by hand in authoritative databases such the Unified Medical Language System, UniProtKB, and GeneOntology on the concept. This annotated information is captured and all concepts that have a 'factual' relationship with the source concept are thus included in the Knowlet of that concept. These 'factually associated concepts' are depicted in the Knowlet visualisation as solid green balls. In addition, the source concept may be mentioned with other concepts in one and the same sentence in the literature. In that case, there is a high chance for a meaningful relationship between the two concepts. Related concepts which co-occur minimally once in the same sentence as the source concept, are depicted as green rings in the visualization of the Knowlet. The last category of concepts is formed by those concepts that have sufficient concepts in common with the source concepts in their own Knowlet to be of potential interest. These concepts are depicted as yellow rings and could represent implicit associations. Over one million Knowlets have been created so far. Each source concept has a relationship of varying strength with other (related) concepts and each of these distances has been assigned with a value for Factual [F], Co-occurrence [C]and associative [A] factors. The distance between each concept pair (source concept and related concept) is computed based on these values and depicted on the histogram as the distance from the origin. In the near future additional data will be added, such as co-expression statistics between genes.

A Wiki environment supported by authoritative sources is crucial as source information for this kind of knowledge discovery. It is intuitive that the more facts are available to a discovery system in unambiguous, computer readable format, the better algorithms for knowledge discovery can unearth new associations. Based on frequent meta-analysis of biomedical ontologies, databases, the Wiki and the scientific literature, the system will actively provide new or suggested associations to experts for review and annotation in a Wiki-environment.

Other WikiProfessional functionality