The use of Gene Ontology terms for predicting highly-connected 'hub' nodes in protein-protein interaction networks

Table 4 Hub prediction comparison of the classifier and the hypothetical PINs in MRSA252.

Hub classifier
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	109	11	30.77%	90.83%	84.96%	26.67%	92.37%
hub	9	4
Hypothetical PIN – pathway maps
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	111	9	0.00%	92.50%	83.46%	0.00%	89.52%
hub	13	0
Hypothetical PIN – orthologous interactions
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	110	10	23.08%	91.67%	84.96%	23.08%	91.67%
hub	10	3
Hypothetical PIN – interacting domains
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	117	3	0.00%	97.50%	87.97%	0.00%	90.00%
hub	13	0
Combined hypothetical PIN – (pathway maps + orthologous interactions)
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	110	10	23.08%	91.67%	84.96%	23.08%	91.67%
hub	10	3
Combined hypothetical PIN – (pathway maps + orthologous interactions + interacting domains)
observed	predicted non-hub	predicted hub	sensitivity	specificity	accuracy	PPV	NPV
non-hub	108	12	7.69%	90.00%	81.95%	7.69%	90.00%
hub	12	1

The prediction performance of the hub classifier is compared to that of the hypothetical PINs in MRSA252. The classification statistics is reported.

ISSN: 1752-0509