Coremine Medical

 

Coremine Medical is a product of the PubGene Company designed to be used by anyone seeking information on health, medicine and biology. It is ideal for those seeking an overview of a complex subject while allowing the possibility to "drill down" to specific details. Search results are presented in a dashboard format comprised of panels containing various categories of information ranging from introductory sources to the latest scientific articles.

 

Coremine literature network

Relationship networks through co-occurrence: Coremine compares a list of terms (represented as a blue rectangle) to a series of electronic records (green rectangles). When any two terms are both found in any particular record they become connected in the network (blue network nodes connected by green network edges). The figure shown here represents a hypothetical network "neighborhood" rather than a complete network encompassing all n terms.

Importantly, Coremine presents search results as a graphic network that describes relationships discovered through text-mining. Relationship networks provide an overview of a topic by clustering important terms. The network is also a navigational tool that can help searchers explore concepts related to their search term (the graphic is hyperlinked to source information). Coremine Medical uses the approach to show relationships between a huge range of biomedical terms, including Medical Subject Heading, Gene Ontology, Pharmaceutical, Herbal medicine and Chemical as well as Gene and Protein terms. The co-occurrence of terms from these lists create relationship networks. The text records indexed are those comprising the MEDLINE data base (i.e. titles and abstracts contained in PubMed). So, relationship networks provide both an overview of related terms and an intuitive system for exploring the information space.


Coremine Medical is a domain specific search and navigation system that employs the patented and proprietary technologies developed at PubGene As. In general, the Coremine method could be applied to any information domain as outlined in the figure.