. Author manuscript; available in PMC: 2014 Dec 1.

Published in final edited form as: J Biomed Inform. 2013 Aug 15;46(6):10.1016/j.jbi.2013.08.004. doi: 10.1016/j.jbi.2013.08.004

Table 2.

Domain representations for entity classes in the i2b2 and GENIA corpora (ST: semantic type; SG: semantic group; C: concept).

Dataset	Class	Domain representation	# Seed terms
i2b2	Problem	Disorders (SG)	398,725
	Treatment	Therapeutic or Preventive Procedure (ST) + Clinical Drug (ST)	153,084
	Test	Laboratory Procedure (ST) + Laboratory or Test Result (ST) + Diagnostic Procedure (ST)	66,015

GENIA	protein	Amino Acid, Peptide, or Protein (ST)	35,351
	DNA	C0012854 (C)	45,671
	RNA	C0035668 (C)	1,029
	cell type	C0007600 (C)	423
	cell line	C0449475 (C)	264,729