Skip to main content

Table 7 Statistics about the comparative performance of GEST classifiers and our label similarity-incorporated classifiers using information in the whole GO biological process ontology, measured in terms of the number of classes for which AUC scores are improved by the latter over the former, and the average and maximum improvement in AUC scores.

From: Incorporating functional inter-relationships into protein function prediction algorithms

Method Total # classes # Classes improved Average improvement over all classes Maximum improvement
GEST-PK-TS 137 75 0.0235 (3.82%) 0.2171 (42.04%)
GEST-SB-TS 137 77 0.0144 (2.34%) 0.2137 (47.4%)