Semantic MEDLINE is a Web application that summarizes MEDLINE citations returned by a PubMed search. Natural language processing is used to extract semantic predications from titles and abstracts. The predications are presented in a graph that has links to the MEDLINE text processed.
In using Semantic MEDLINE, begin at the Search tab by issuing a PubMed query; then move to the Summarize tab. Choose a summary type to specify the point of view of the summary (Treatment of Disease, Substance Interactions, Diagnosis, or Pharmacogenomics). After selecting the topic of the summary, click the Summarize and Visualize buttons. A graph representing the summarized predications appears in the next screen; nodes represent concepts and edges correspond to relations of the predications. Clicking on an edge and then the Citations button located at the lower right corner displays the MEDLINE citations from which the predication was extracted.
A quick tour video explaining Semantic Medline features can be watched here.