Skip to main content
. 2014 Oct 14;13(Suppl 1):103–111. doi: 10.4137/CIN.S13889

Figure 1.

Figure 1

Prostate cancer concepts are found from the UMLS using MetaMap. SemRep extracts semantic predications from the MEDLINE database and stores them in SemMedDB. Predications from SemMedDB are found containing the prostate cancer concepts as objects and genes as subjects and more predications are found that contain drugs as subjects and genes as objects. Additional predications are selected that contain genes as both subject and object. These predications are lined up in either the Drug→Gene→Cancer pathway schema or the Drug→ Gene1→ Gene2→Cancer pathway schema to produce a list of potential drugs and their mechanism of action in treating prostate cancer. A physician selects the best candidates based on the source citations and other relevant knowledge.