iMPT-FDNPL: Identification of Membrane Protein Types with Functional Domains and a Natural Language Processing Approach

Table 4

Performance of different multilabel classifiers with features derived from gene ontology and pathway information via a natural language processing approach.

Scheme (base classifier)	Exact match	Accuracy	Hamming loss	Integrated score
RAKEL (RF)	0.761	0.762	0.083	0.5324
RAKEL (SVM-polynomial kernel)	0.808	0.810	0.067	0.6106
RAKEL (SVM-RBF kernel)	0.808	0.810	0.068	0.6099
BR (RF)	0.584	0.584	0.087	0.3113
BR (SVM-polynomial kernel)	0.717	0.738	0.068	0.4931
BR (SVM-RBF kernel)	0.747	0.755	0.063	0.5284