Prediction of protein-protein interaction types using association rule based classification

BMC Bioinformatics

Table 3 The number of association rules discovered for each PPI type

Type	#. of Domains^a	#. of Rules^b	Unique Rules^c	Overlapping Rules^d
ENZ	49	65	34 (52.31%)	31 (47.69%)
nonENZ	47	49	16 (32.65%)	33 (67.35%)
HET	33	19	7 (36.84%)	12 (63.16%)
HOM	225	24	1 (4.17%)	23 (95.83%)
Total	354	157	58 (36.94%)	99 (63.06%)

^a#. of Domains: A number of domains in each PPI type;
^b#. of Rules: A number of association rules discovered for each PPI type;
^cUnique Rules: A number of association rules associated with just one PPI type;
^dOverlapping Rules: A number of rules of which bodies are identical to those of rules in other types.

ISSN: 1471-2105