Sequential pattern mining for discovering gene interactions and their contextual information from biomedical texts

Table 1 Example of a sequence database

ID	Sequence
...	...
S1	〈R e c e n t @ j j s t u d y @ n n s h a v e @ v h p s u g g e s t @ v v n t h a t @ i n/t h a t A G E N E m a y @ m d b e @ v b v i t a l @ j j
	for@in regulation@nn of@in AGENE mrna@np expression@nn and@cc telomerase@nn
	activity@nn.@sent 〉
S2	〈i n j e c t i o n @ n n o f @ i n A G E N E m r n a @ n p i n @ i n x e n o p u s @ n p e m b r y o @ n n s i n h i b i t @ v v d t h e @ d t
	AGENE mediate@vvd dorsal@jj axis@nn duplication@nn.@sent 〉
...	...

Table 1 shows an excerpt of a sequence database which contains two interaction sentences:
S1: “Recent studies have suggested that c-myc may be vital for regulation of hTERT mRNA expression and telomerase activity.” and
S2: “Injection of frpHE mRNA in Xenopus embryos inhibited the Wnt-8 mediated dorsal axis duplication.”.

ISSN: 2041-1480