Table 1

Some entries in the context matrix. Scores are derived from the ratio between frequency of the given word in the given position with respect to the gene (position +1 means immediately after the gene name, position +2 means two words behind, etc.) and the total frequency of the word.

WORD

POSITION


-3

-2

-1

+1

+2

+3

gene

0

0.5

5.0

5.0

0.5

0

function

0

1.8

0

2.1

0

0

cell

0

0

-2.5

-5.0

0

0


Tamames BMC Bioinformatics 2005 6(Suppl 1):S10   doi:10.1186/1471-2105-6-S1-S10

Open Data