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

Table 5

Performance of different multilabel classifiers with features derived from protein networks via a network embedding algorithm.

Scheme (base classifier)	Exact match	Accuracy	Hamming loss	Integrated score
RAKEL (RF)	0.758	0.759	0.085	0.5264
RAKEL (SVM-polynomial kernel)	0.805	0.807	0.068	0.6054
RAKEL (SVM-RBF kernel)	0.801	0.803	0.070	0.5981
BR (RF)	0.584	0.584	0.088	0.3110
BR (SVM-polynomial kernel)	0.712	0.730	0.068	0.4844
BR (SVM-RBF kernel)	0.746	0.756	0.063	0.5284